Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs

Transitioning sleeping position detection in late pregnancy using computer vision from controlled to real-world settings: an observational study

Sleeping on the back after 28 weeks of pregnancy has recently been associated with giving birth to a small-for-gestational-age infant and late stillbirth, but whether a causal relationship exists is currently unknown and difficult to study prospectively. This study was conducted to build a computer vision model that can automatically detect sleeping position in pregnancy under real-world conditions. Real-world overnight video recordings were collected from an ongoing, Canada-wide, prospective, four-night, home sleep apnea study and controlled-setting video recordings were used from a previous study. Images were extracted from the videos and body positions were annotated. Five-fold cross validation was used to train, validate, and test a model using state-of-the-art deep convolutional neural networks. The dataset contained 39 pregnant participants, 13 bed partners, 12,930 images, and 47,001 annotations. The model was trained to detect pillows, twelve sleeping positions, and a sitting position in both the pregnant person and their bed partner simultaneously. The model significantly outperformed a previous similar model for the three most commonly occurring natural sleeping positions in pregnant and non-pregnant adults, with an 82-to-89% average probability of correctly detecting them and a 15-to-19% chance of failing to detect them when any one of them is present.

Integration of Tracking, Re-Identification, and Gesture Recognition for Facilitating Human-Robot Interaction

For successful human-robot collaboration, it is crucial to establish and sustain quality interaction between humans and robots, making it essential to facilitate human-robot interaction (HRI) effectively. The evolution of robot intelligence now enables robots to take a proactive role in initiating and sustaining HRI, thereby allowing humans to concentrate more on their primary tasks. In this paper, we introduce a system known as the Robot-Facilitated Interaction System (RFIS), where mobile robots are employed to perform identification, tracking, re-identification, and gesture recognition in an integrated framework to ensure anytime readiness for HRI. We implemented the RFIS on an autonomous mobile robot used for transporting a patient, to demonstrate proactive, real-time, and user-friendly interaction with a caretaker involved in monitoring and nursing the patient. In the implementation, we focused on the efficient and robust integration of various interaction facilitation modules within a real-time HRI system that operates in an edge computing environment. Experimental results show that the RFIS, as a comprehensive system integrating caretaker recognition, tracking, re-identification, and gesture recognition, can provide an overall high quality of interaction in HRI facilitation with average accuracies exceeding 90% during real-time operations at 5 FPS.

Explainable AI based automated segmentation and multi-stage classification of gastroesophageal reflux using machine learning techniques

Presently, close to two million patients globally succumb to gastrointestinal reflux diseases (GERD). Video endoscopy represents cutting-edge technology in medical imaging, facilitating the diagnosis of various gastrointestinal ailments including stomach ulcers, bleeding, and polyps. However, the abundance of images produced by medical video endoscopy necessitates significant time for doctors to analyze them thoroughly, posing a challenge for manual diagnosis. This challenge has spurred research into computer-aided techniques aimed at diagnosing the plethora of generated images swiftly and accurately. The novelty of the proposed methodology lies in the development of a system tailored for the diagnosis of gastrointestinal diseases. The proposed work used an object detection method called Yolov5 for identifying abnormal region of interest and Deep LabV3+ for segmentation of abnormal regions in GERD. Further, the features are extracted from the segmented image and given as an input to the seven different machine learning classifiers and custom deep neural network model for multi-stage classification of GERD. The DeepLabV3+ attains an excellent segmentation accuracy of 95.2% and an F1 score of 93.3%. The custom dense neural network obtained a classification accuracy of 90.5%. Among the seven different machine learning classifiers, support vector machine (SVM) outperformed with classification accuracy of 87% compared to all other class outperformed combination of object detection, deep learning-based segmentation and machine learning classification enables the timely identification and surveillance of problems associated with GERD for healthcare providers.

Comprehensive Investigation of Unmanned Aerial Vehicles (UAVs): An In-Depth Analysis of Avionics Systems

The evolving technologies regarding Unmanned Aerial Vehicles (UAVs) have led to their extended applicability in diverse domains, including surveillance, commerce, military, and smart electric grid monitoring. Modern UAV avionics enable precise aircraft operations through autonomous navigation, obstacle identification, and collision prevention. The structures of avionics are generally complex, and thorough hierarchies and intricate connections exist in between. For a comprehensive understanding of a UAV design, this paper aims to assess and critically review the purpose-classified electronics hardware inside UAVs, each with the corresponding performance metrics thoroughly analyzed. This review includes an exploration of different algorithms used for data processing, flight control, surveillance, navigation, protection, and communication. Consequently, this paper enriches the knowledge base of UAVs, offering an informative background on various UAV design processes, particularly those related to electric smart grid applications. As a future work recommendation, an actual relevant project is openly discussed.

Second mesiobuccal canal segmentation with YOLOv5 architecture using cone beam computed tomography images

The objective of this study is to use a deep-learning model based on CNN architecture to detect the second mesiobuccal (MB2) canals, which are seen as a variation in maxillary molars root canals. In the current study, 922 axial sections from 153 patients' cone beam computed tomography (CBCT) images were used. The segmentation method was employed to identify the MB2 canals in maxillary molars that had not previously had endodontic treatment. Labeled images were divided into training (80%), validation (10%) and testing (10%) groups. The artificial intelligence (AI) model was trained using the You Only Look Once v5 (YOLOv5x) architecture with 500 epochs and a learning rate of 0.01. Confusion matrix and receiver-operating characteristic (ROC) analysis were used in the statistical evaluation of the results. The sensitivity of the MB2 canal segmentation model was 0.92, the precision was 0.83, and the F1 score value was 0.87. The area under the curve (AUC) in the ROC graph of the model was 0.84. The mAP value at 0.5 inter-over union (IoU) was found as 0.88. The deep-learning algorithm used showed a high success in the detection of the MB2 canal. The success of the endodontic treatment can be increased and clinicians' time can be preserved using the newly created artificial intelligence-based models to identify variations in root canal anatomy before the treatment.

Design and Characterization of a Powered Wheelchair Autonomous Guidance System

The current technological revolution driven by advances in machine learning has motivated a wide range of applications aiming to improve our quality of life. Representative of such applications are autonomous and semiautonomous Powered Wheelchairs (PWs), where the focus is on providing a degree of autonomy to the wheelchair user as a matter of guidance and interaction with the environment. Based on these perspectives, the focus of the current research has been on the design of lightweight systems that provide the necessary accuracy in the navigation system while enabling an embedded implementation. This motivated us to develop a real-time measurement methodology that relies on a monocular RGB camera to detect the caregiver's feet based on a deep learning method, followed by the distance measurement of the caregiver from the PW. An important contribution of this article is the metrological characterization of the proposed methodology in comparison with measurements made with dedicated depth cameras. Our results show that despite shifting from 3D imaging to 2D imaging, we can still obtain comparable metrological performances in distance estimation as compared with Light Detection and Ranging (LiDAR) or even improved compared with stereo cameras. In particular, we obtained comparable instrument classes with LiDAR and stereo cameras, with measurement uncertainties within a magnitude of 10 cm. This is further complemented by the significant reduction in data volume and object detection complexity, thus facilitating its deployment, primarily due to the reduced complexity of initial calibration, positioning, and deployment compared with three-dimensional segmentation algorithms.

Lightweight Vehicle Detection Based on Improved YOLOv5s

A vehicle detection algorithm is an indispensable component of intelligent traffic management and control systems, influencing the efficiency and functionality of the system. In this paper, we propose a lightweight improvement method for the YOLOv5 algorithm based on integrated perceptual attention, with few parameters and high detection accuracy. First, we propose a lightweight module IPA with a Transformer encoder based on integrated perceptual attention, which leads to a reduction in the number of parameters while capturing global dependencies for richer contextual information. Second, we propose a lightweight and efficient multiscale spatial channel reconstruction (MSCCR) module that does not increase parameter and computational complexity and facilitates representative feature learning. Finally, we incorporate the IPA module and the MSCCR module into the YOLOv5s backbone network to reduce model parameters and improve accuracy. The test results show that, compared with the original model, the model parameters decrease by about 9%, the average accuracy (mAP@50) increases by 3.1%, and the FLOPS does not increase.

A pilot study of measuring emotional response and perception of LLM-generated questionnaire and human-generated questionnaires

The advent of ChatGPT has sparked a heated debate surrounding natural language processing technology and AI-powered chatbots, leading to extensive research and applications across various disciplines. This pilot study aims to investigate the impact of ChatGPT on users' experiences by administering two distinct questionnaires, one generated by humans and the other by ChatGPT, along with an Emotion Detecting Model. A total of 14 participants (7 female and 7 male) aged between 18 and 35 years were recruited, resulting in the collection of 8672 ChatGPT-associated data points and 8797 human-associated data points. Data analysis was conducted using Analysis of Variance (ANOVA). The results indicate that the utilization of ChatGPT enhances participants' happiness levels and reduces their sadness levels. While no significant gender influences were observed, variations were found about specific emotions. It is important to note that the limited sample size, narrow age range, and potential cultural impacts restrict the generalizability of the findings to a broader population. Future research directions should explore the impact of incorporating additional language models or chatbots on user emotions, particularly among specific age groups such as older individuals and teenagers. As one of the pioneering works evaluating the human perception of ChatGPT text and communication, it is noteworthy that ChatGPT received positive evaluations and demonstrated effectiveness in generating extensive questionnaires.

Comparison Using Intelligent Systems for Data Prediction and Near Miss Detection Techniques

Malaysia ranks third among ASEAN countries in terms of deaths due to accidents, with an alarming increase in the number of fatalities each year. Road conditions contribute significantly to near-miss incidents, while the inefficiency of installed CCTVs and the lack of monitoring system algorithms worsen the situation. The objective of this research is to address the issue of increasing accidents and fatalities on Malaysian roads. Specifically, the study aims to investigate the use of video technology and machine learning algorithms for the car detection and analysis of near-miss accidents. To achieve this goal, the researchers focused on Penang, where the MBPP has deployed 1841 CCTV cameras to monitor traffic and document near-miss accidents. The study utilised the YOLOv3, YOLOv4, and Faster RCNN algorithms for vehicle detection. Additionally, the study employed image processing techniques such as Bird’s Eye View and Social Distancing Monitoring to detect and analyse how near misses occur. Various video lengths (20s, 40s, 60s and 80s) were tested to compare the algorithms’ error detection percentage and test duration. The results indicate that Faster RCNN beats YOLOv3 and YOLOV4 in car detection with low error detection, whereas YOLOv3 and YOLOv4 outperform near-miss detection, while Faster RCNN does not perform it. Overall, this study demonstrates the potential of video technology and machine learning algorithms in near-miss accident detection and analysis. Transportation authorities can better understand the causes of accidents and take appropriate measures to improve road safety using these models. This research can be a foundation for further traffic safety and accident prevention studies.

Hand acupuncture point localization method based on a dual-attention mechanism and cascade network model

Deep learning techniques have, to a certain extent, solved the problem of overreliance on clinical experience for traditional acupoint localization, but the accuracy and repetition rate of its localization still need to be improved. This paper proposes a hand acupoint localization method based on the dual-attention mechanism and cascade network model. First, by superimposing the dual-attention mechanism SE and CA in the YOLOv5 model and calculating the prior box size using K-means++ to optimize the hand location, we cascade the heatmap regression algorithm with HRNet as the backbone network to detect 21 predefined key points on the hand. Finally, "MF-cun" is combined to complete the acupoint localization. The FPS value is 35 and the average offset error value is 0.0269, which is much lower than the error threshold through dataset validation and real scene testing. The results show that this method can reduce the offset error value by more than 40% while ensuring real-time performance and can combat complex scenes such as unequal lighting, occlusion, and skin color interference.

YOLOv5-MS: Real-Time Multi-Surveillance Pedestrian Target Detection Model for Smart Cities

Intelligent video surveillance plays a pivotal role in enhancing the infrastructure of smart urban environments. The seamless integration of multi-angled cameras, functioning as perceptive sensors, significantly enhances pedestrian detection and augments security measures in smart cities. Nevertheless, current pedestrian-focused target detection encounters challenges such as slow detection speeds and increased costs. To address these challenges, we introduce the YOLOv5-MS model, an YOLOv5-based solution for target detection. Initially, we optimize the multi-threaded acquisition of video streams within YOLOv5 to ensure image stability and real-time performance. Subsequently, leveraging reparameterization, we replace the original BackBone convolution with RepvggBlock, streamlining the model by reducing convolutional layer channels, thereby enhancing the inference speed. Additionally, the incorporation of a bioinspired "squeeze and excitation" module in the convolutional neural network significantly enhances the detection accuracy. This module improves target focusing and diminishes the influence of irrelevant elements. Furthermore, the integration of the K-means algorithm and bioinspired Retinex image augmentation during training effectively enhances the model's detection efficacy. Finally, loss computation adopts the Focal-EIOU approach. The empirical findings from our internally developed smart city dataset unveil YOLOv5-MS's impressive 96.5% mAP value, indicating a significant 2.0% advancement over YOLOv5s. Moreover, the average inference speed demonstrates a notable 21.3% increase. These data decisively substantiate the model's superiority, showcasing its capacity to effectively perform pedestrian detection within an Intranet of over 50 video surveillance cameras, in harmony with our stringent requisites.

Research on Fine-Grained Image Recognition of Birds Based on Improved YOLOv5

Birds play a vital role in maintaining biodiversity. Accurate identification of bird species is essential for conducting biodiversity surveys. However, fine-grained image recognition of birds encounters challenges due to large within-class differences and small inter-class differences. To solve this problem, our study took a part-based approach, dividing the identification task into two parts: part detection and identification classification. We proposed an improved bird part detection algorithm based on YOLOv5, which can handle partial overlap and complex environmental conditions between part objects. The backbone network incorporates the Res2Net-CBAM module to enhance the receptive fields of each network layer, strengthen the channel characteristics, and improve the sensitivity of the model to important information. Additionally, in order to boost data on features extraction and channel self-regulation, we have integrated CBAM attention mechanisms into the neck. The success rate of our suggested model, according to experimental findings, is 86.6%, 1.2% greater than the accuracy of the original model. Furthermore, when compared with other algorithms, our model's accuracy shows noticeable improvement. These results show how useful the method we suggested is for quickly and precisely recognizing different bird species.

Broiler Mobility Assessment via a Semi-Supervised Deep Learning Model and Neo-Deep Sort Algorithm

Mobility is a vital welfare indicator that may influence broilers' daily activities. Classical broiler mobility assessment methods are laborious and cannot provide timely insights into their conditions. Here, we proposed a semi-supervised Deep Learning (DL) model, YOLOv5 (You Only Look Once version 5), combined with a deep sort algorithm conjoined with our newly proposed algorithm, neo-deep sort, for individual broiler mobility tracking. Initially, 1650 labeled images from five days were employed to train the YOLOv5 model. Through semi-supervised learning (SSL), this narrowly trained model was then used for pseudo-labeling 2160 images, of which 2153 were successfully labeled. Thereafter, the YOLOv5 model was fine-tuned on the newly labeled images. Lastly, the trained YOLOv5 and the neo-deep sort algorithm were applied to detect and track 28 broilers in two pens and categorize them in terms of hourly and daily travel distances and speeds. SSL helped in increasing the YOLOv5 model's mean average precision (mAP) in detecting birds from 81% to 98%. Compared with the manually measured covered distances of broilers, the combined model provided individual broilers' hourly moved distances with a validation accuracy of about 80%. Eventually, individual and flock-level mobilities were quantified while overcoming the occlusion, false, and miss-detection issues.

Artificial Intelligence-Based Hazard Detection in Robotic-Assisted Single-Incision Oncologic Surgery

THE PROBLEM

Single-incision surgery is a complex procedure in which any additional information automatically collected from the operating field can be of significance. While the use of robotic devices has greatly improved surgical outcomes, there are still many unresolved issues. One of the major surgical complications, with higher occurrence in cancer patients, is intraoperative hemorrhages, which if detected early, can be more efficiently controlled.

AIM

This paper proposes a hazard detection system which incorporates the advantages of both Artificial Intelligence (AI) and Augmented Reality (AR) agents, capable of identifying, in real-time, intraoperative bleedings, which are subsequently displayed on a Hololens 2 device.

METHODS

The authors explored the different techniques for real-time processing and determined, based on a critical analysis, that YOLOv5 is one of the most promising solutions. An innovative, real-time, bleeding detection system, developed using the YOLOv5 algorithm and the Hololens 2 device, was evaluated on different surgical procedures and tested in multiple configurations to obtain the optimal prediction time and accuracy.

RESULTS

The detection system was able to identify the bleeding occurrence in multiple surgical procedures with a high rate of accuracy. Once detected, the area of interest was marked with a bounding box and displayed on the Hololens 2 device. During the tests, the system was able to differentiate between bleeding occurrence and intraoperative irrigation; thus, reducing the risk of false-negative and false-positive results.

CONCLUSION

The current level of AI and AR technologies enables the development of real-time hazard detection systems as efficient assistance tools for surgeons, especially in high-risk interventions.

Forest Fire Smoke Detection Based on Deep Learning Approaches and Unmanned Aerial Vehicle Images

Wildfire poses a significant threat and is considered a severe natural disaster, which endangers forest resources, wildlife, and human livelihoods. In recent times, there has been an increase in the number of wildfire incidents, and both human involvement with nature and the impacts of global warming play major roles in this. The rapid identification of fire starting from early smoke can be crucial in combating this issue, as it allows firefighters to respond quickly to the fire and prevent it from spreading. As a result, we proposed a refined version of the YOLOv7 model for detecting smoke from forest fires. To begin, we compiled a collection of 6500 UAV pictures of smoke from forest fires. To further enhance YOLOv7's feature extraction capabilities, we incorporated the CBAM attention mechanism. Then, we added an SPPF+ layer to the network's backbone to better concentrate smaller wildfire smoke regions. Finally, decoupled heads were introduced into the YOLOv7 model to extract useful information from an array of data. A BiFPN was used to accelerate multi-scale feature fusion and acquire more specific features. Learning weights were introduced in the BiFPN so that the network can prioritize the most significantly affecting characteristic mapping of the result characteristics. The testing findings on our forest fire smoke dataset revealed that the proposed approach successfully detected forest fire smoke with an AP50 of 86.4%, 3.9% higher than previous single- and multiple-stage object detectors.

A Quality Assessment Network for Failure Detection in 3D Printing for Future Space-Based Manufacturing

The application of space manufacturing technology holds tremendous potential for the advancement of space exploration. With significant investment from respected research institutions such as NASA, ESA, and CAST, along with private companies such as Made In Space, OHB System, Incus, and Lithoz, this sector has recently experienced a notable surge in development. Among the available manufacturing technologies, 3D printing has been successfully tested in the microgravity environment onboard the International Space Station (ISS), emerging as a versatile and promising solution for the future of space manufacturing. In this paper, an automated Quality Assessment (QA) approach for space-based 3D printing is proposed, aiming to enable the autonomous evaluation on the 3D printed results, thus freeing the system from reliance on human intervention, an essential requirement for the operation of space-based manufacturing platforms functioning in the exposed space environment. Specifically, this study investigates three types of common 3D printing failures, namely, indentation, protrusion, and layering to design an effective and efficient fault detection network that outperforms its counterparts backboned with other existing networks. The proposed approach has achieved a detection rate of up to 82.7% with an average confidence of 91.6% by training with the artificial samples, demonstrating promising results for the future implementation of 3D printing in space manufacturing.

Utilizing High Resolution Satellite Imagery for Automated Road Infrastructure Safety Assessments

The European Commission (EC) has published a European Union (EU) Road Safety Framework for the period 2021 to 2030 to reduce road fatalities. In addition, the EC with the EU Directive 2019/1936 requires a much more detailed recording of road attributes. Therefore, automatic detection of school routes, four classes of crosswalks, and divided carriageways were performed in this paper. The study integrated satellite imagery as a data source and the Yolo object detector. The satellite Pleiades Neo 3 with a spatial resolution of 0.3 m was used as the source for the satellite images. In addition, the study was divided into three phases: vector processing, satellite imagery processing, and training and evaluation of the You Only Look Once (Yolo) object detector. The training process was performed on 1951 images with 2515 samples, while the evaluation was performed on 651 images with 862 samples. For school zones and divided carriageways, this study achieved accuracies of 0.988 and 0.950, respectively. For crosswalks, this study also achieved similar or better results than similar work, with accuracies ranging from 0.957 to 0.988. The study also provided the standard performance measure for object recognition, mean average precision (mAP), as well as the values for the confusion matrix, precision, recall, and f1 score for each class as benchmark values for future studies.

Automatic classification of distal radius fracture using a two-stage ensemble deep learning framework

Distal radius fractures (DRFs) are one of the most common types of wrist fracture and can be subdivided into intra- and extra-articular fractures. Compared with extra-articular DRFs which spare the joint surface, intra-articular DRFs extend to the articular surface and can be more difficult to treat. Identification of articular involvement can provide valuable information about the characteristics of fracture patterns. In this study, a two-stage ensemble deep learning framework was proposed to differentiate intra- and extra-articular DRFs automatically on posteroanterior (PA) view wrist X-rays. The framework firstly detects the distal radius region of interest (ROI) using an ensemble model of YOLOv5 networks, which imitates the clinicians' search pattern of zooming in on relevant regions to assess abnormalities. Secondly, an ensemble model of EfficientNet-B3 networks classifies the fractures in the detected ROIs into intra- and extra-articular. The framework achieved an area under the receiver operating characteristic curve of 0.82, an accuracy of 0.81, a true positive rate of 0.83 and a false positive rate of 0.27 (specificity of 0.73) for differentiating intra- from extra-articular DRFs. This study has demonstrated the potential in automatic DRF characterization using deep learning on clinically acquired wrist radiographs and can serve as a baseline for further research in incorporating multi-view information for fracture classification.

Diagnostic accuracy of a deep learning model using YOLOv5 for detecting developmental dysplasia of the hip on radiography images

Developmental dysplasia of the hip (DDH) is a cluster of hip development disorders and one of the most common hip diseases in infants. Hip radiography is a convenient diagnostic tool for DDH, but its diagnostic accuracy is dependent on the interpreter's level of experience. The aim of this study was to develop a deep learning model for detecting DDH. Patients younger than 12 months who underwent hip radiography between June 2009 and November 2021 were selected. Using their radiography images, transfer learning was performed to develop a deep learning model using the "You Only Look Once" v5 (YOLOv5) and single shot multi-box detector (SSD). A total of 305 anteroposterior hip radiography images (205 normal and 100 DDH hip images) were collected. Of these, 30 normal and 17 DDH hip images were used as the test dataset. The sensitivity and the specificity of our best YOLOv5 model (YOLOv5l) were 0.94 (95% confidence interval [CI] 0.73-1.00) and 0.96 (95% CI 0.89-0.99), respectively. This model also outperformed the SSD model. This is the first study to establish a model for detecting DDH using YOLOv5. Our deep learning model provides good diagnostic performance for DDH. We believe our model is a useful diagnostic assistant tool.

Cooktop Sensing Based on a YOLO Object Detection Algorithm

Deep Learning (DL) has provided a significant breakthrough in many areas of research and industry. The development of Convolutional Neural Networks (CNNs) has enabled the improvement of computer vision-based techniques, making the information gathered from cameras more useful. For this reason, recently, studies have been carried out on the use of image-based DL in some areas of people's daily life. In this paper, an object detection-based algorithm is proposed to modify and improve the user experience in relation to the use of cooking appliances. The algorithm can sense common kitchen objects and identify interesting situations for users. Some of these situations are the detection of utensils on lit hobs, recognition of boiling, smoking and oil in kitchenware, and determination of good cookware size adjustment, among others. In addition, the authors have achieved sensor fusion by using a cooker hob with Bluetooth connectivity, so it is possible to automatically interact with it via an external device such as a computer or a mobile phone. Our main contribution focuses on supporting people when they are cooking, controlling heaters, or alerting them with different types of alarms. To the best of our knowledge, this is the first time a YOLO algorithm has been used to control the cooktop by means of visual sensorization. Moreover, this research paper provides a comparison of the detection performance among different YOLO networks. Additionally, a dataset of more than 7500 images has been generated and multiple data augmentation techniques have been compared. The results show that YOLOv5s can successfully detect common kitchen objects with high accuracy and fast speed, and it can be employed for realistic cooking environment applications. Finally, multiple examples of the identification of interesting situations and how we act on the cooktop are presented.

Sensor-Model-Based Trajectory Optimization for UAVs to Enhance Detection Performance: An Optimal Control Approach and Experimental Results

UAVs are widely used for aerial reconnaissance with imaging sensors. For this, a high detection performance (accuracy of object detection) is desired in order to increase mission success. However, different environmental conditions (negatively) affect sensory data acquisition and automated object detection. For this reason, we present an innovative concept that maps the influence of selected environmental conditions on detection performance utilizing sensor performance models. These models are used in sensor-model-based trajectory optimization to generate optimized reference flight trajectories with aligned sensor control for a fixed-wing UAV in order to increase detection performance. These reference trajectories are calculated using nonlinear model predictive control as well as dynamic programming, both in combination with a newly developed sensor performance model, which is described in this work. To the best of our knowledge, this is the first sensor performance model to be used in unmanned aerial reconnaissance that maps the detection performance for a perception chain with a deep learning-based object detector with respect to selected environmental states. The reference trajectory determines the spatial and temporal positioning of the UAV and its imaging sensor with respect to the reconnaissance object on the ground. The trajectory optimization aims to influence sensor data acquisition by adjusting the sensor position, as part of the environmental states, in such a way that the subsequent automated object detection yields enhanced detection performance. Different constraints derived from perceptual, platform-specific, environmental, and mission-relevant requirements are incorporated into the optimization process. We evaluate the capabilities of the sensor performance model and our approach to sensor-model-based trajectory optimization by a series of simulated aerial reconnaissance tasks for ground vehicle detection. Compared to a variety of benchmark trajectories, our approach achieves an increase in detection performance of 4.48% on average for trajectory optimization with nonlinear model predictive control. With dynamic programming, we achieve even higher performance values that are equal to or close to the theoretical maximum detection performance values.

Embedded Vision Intelligence for the Safety of Smart Cities

Advances in Artificial intelligence (AI) and embedded systems have resulted on a recent increase in use of image processing applications for smart cities' safety. This enables a cost-adequate scale of automated video surveillance, increasing the data available and releasing human intervention. At the same time, although deep learning is a very intensive task in terms of computing resources, hardware and software improvements have emerged, allowing embedded systems to implement sophisticated machine learning algorithms at the edge. Additionally, new lightweight open-source middleware for constrained resource devices, such as EdgeX Foundry, have appeared to facilitate the collection and processing of data at sensor level, with communication capabilities to exchange data with a cloud enterprise application. The objective of this work is to show and describe the development of two Edge Smart Camera Systems for safety of Smart cities within S4AllCities H2020 project. Hence, the work presents hardware and software modules developed within the project, including a custom hardware platform specifically developed for the deployment of deep learning models based on the I.MX8 Plus from NXP, which considerably reduces processing and inference times; a custom Video Analytics Edge Computing (VAEC) system deployed on a commercial NVIDIA Jetson TX2 platform, which provides high level results on person detection processes; and an edge computing framework for the management of those two edge devices, namely Distributed Edge Computing framework, DECIoT. To verify the utility and functionality of the systems, extended experiments were performed. The results highlight their potential to provide enhanced situational awareness and demonstrate the suitability for edge machine vision applications for safety in smart cities.

Influence of Insufficient Dataset Augmentation on IoU and Detection Threshold in CNN Training for Object Detection on Aerial Images

The objects and events detection tasks are being performed progressively often by robotic systems like unmanned aerial vehicles (UAV) or unmanned surface vehicles (USV). Autonomous operations and intelligent sensing are becoming standard in numerous scenarios such as supervision or even search and rescue (SAR) missions. The low cost of autonomous vehicles, vision sensors and portable computers allows the incorporation of the deep learning, mainly convolutional neural networks (CNN) in these solutions. Many systems meant for custom purposes rely on insufficient training datasets, what may cause a decrease of effectiveness. Moreover, the system's accuracy is usually dependent on the returned bounding boxes highlighting the supposed targets. In desktop applications, precise localisation might not be particularly relevant; however, in real situations, with low visibility and non-optimal camera orientation, it becomes crucial. One of the solutions for dataset enhancement is its augmentation. The presented work is an attempt to evaluate the influence of the training images augmentation on the detection parameters important for the effectiveness of neural networks in the context of object detection. In this research, network appraisal relies on the detection confidence and bounding box prediction accuracy (IoU). All the applied image modifications were simple pattern and colour alterations. The obtained results imply that there is a measurable impact of the augmentation process on the localisation accuracy. It was concluded that a positive or negative influence is related to the complexity and variability of the objects classes.

1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches

Recent advancement in Deep Learning-based Convolutional Neural Networks (D-CNNs) has led research to improve the efficiency and performance of barcode recognition in Supply Chain Management (SCM). D-CNNs required real-world images embedded with ground truth data, which is often not readily available in the case of SCM barcode recognition. This study introduces two invented barcode datasets: InventBar and ParcelBar. The datasets contain labeled barcode images with 527 consumer goods and 844 post boxes in the indoor environment. To explore the influential capability of the datasets that affect recognition process, five existing D-CNN algorithms were applied and compared over a set of recently available barcode datasets. To confirm the model's performance and accuracy, runtime and Mean Average Precision (mAP) were examined based on different IoU thresholds and image transformation settings. The results show that YOLO v5 works best for the ParcelBar in terms of speed and accuracy. The situation is different for the InventBar since Faster R-CNN could allow the model to learn faster with a small drop in accuracy. It is proven that the proposed datasets can be practically utilized for the mainstream D-CNN frameworks. Both are available for developing barcode recognition models and positively affect comparative studies.

Sensor Fusion for Social Navigation on a Mobile Robot Based on Fast Marching Square and Gaussian Mixture Model

Mobile robot navigation has been studied for a long time, and it is nowadays widely used in multiple applications. However, it is traditionally focused on two-dimensional geometric characteristics of the environments. There are situations in which robots need to share space with people, so additional aspects, such as social distancing, need to be considered. In this work, an approach for social navigation is presented. A multi-layer model of the environment containing geometric and topological characteristics is built based on the fusion of multiple sensor information. This is later used for navigating the environment considering social distancing from individuals and groups of people. The main novelty is combining fast marching square for path planning and navigation with Gaussian models to represent people. This combination allows to create a continuous representation of the environment from which smooth paths can be extracted and modified according to dynamically captured data. Results prove the practical application of the method on an assistive robot for navigating indoor scenarios, including a behavior for crossing narrow passages. People are efficiently detected and modeled to assure their comfort when robots are around.

GCP-Based Automated Fine Alignment Method for Improving the Accuracy of Coordinate Information on UAV Point Cloud Data

3D point cloud data (PCD) can accurately and efficiently capture the 3D geometric information of a target and exhibits significant potential for construction applications. Although one of the most common approaches for generating PCD is the use of unmanned aerial vehicles (UAV), UAV photogrammetry-based point clouds are erroneous. This study proposes a novel framework for automatically improving the coordinate accuracy of PCD. Image-based deep learning and PCD analysis methods are integrated into a framework that includes the following four phases: GCP (Ground Control Point) detection, GCP global coordinate extraction, transformation matrix estimation, and fine alignment. Two different experiments, as follows, were performed in the case study to validate the proposed framework: (1) experiments on the fine alignment performance of the developed framework, and (2) performance and run time comparison between the fine alignment framework and common registration algorithms such as ICP (Iterative Closest Points). The framework achieved millimeter-level accuracy for each axis. The run time was less than 30 s, which indicated the feasibility of the proposed framework.

Fast and Non-Destructive Quail Egg Freshness Assessment Using a Thermal Camera and Deep Learning-Based Air Cell Detection Algorithms for the Revalidation of the Expiration Date of Eggs

Freshness is one of the most important parameters for assessing the quality of avian eggs. Available techniques to estimate the degradation of albumen and enlargement of the air cell are either destructive or not suitable for high-throughput applications. The aim of this research was to introduce a new approach to evaluate the air cell of quail eggs for freshness assessment as a fast, noninvasive, and nondestructive method. A new methodology was proposed by using a thermal microcamera and deep learning object detection algorithms. To evaluate the new method, we stored 174 quail eggs and collected thermal images 30, 50, and 60 days after the labeled expiration date. These data, 522 in total, were expanded to 3610 by image augmentation techniques and then split into training and validation samples to produce models of the deep learning algorithms, referred to as "You Only Look Once" version 4 and 5 (YOLOv4 and YOLOv5) and EfficientDet. We tested the models in a new dataset composed of 60 eggs that were kept for 15 days after the labeled expiration label date. The validation of our methodology was performed by measuring the air cell area highlighted in the thermal images at the pixel level; thus, we compared the difference in the weight of eggs between the first day of storage and after 10 days under accelerated aging conditions. The statistical significance showed that the two variables (air cell and weight) were negatively correlated (R² = 0.676). The deep learning models could predict freshness with F1 scores of 0.69, 0.89, and 0.86 for the YOLOv4, YOLOv5, and EfficientDet models, respectively. The new methodology for freshness assessment demonstrated that the best model reclassified 48.33% of our testing dataset. Therefore, those expired eggs could have their expiration date extended for another 2 weeks from the original label date.

HMM-Based Action Recognition System for Elderly Healthcare by Colorizing Depth Map

Addressing the problems facing the elderly, whether living independently or in managed care facilities, is considered one of the most important applications for action recognition research. However, existing systems are not ready for automation, or for effective use in continuous operation. Therefore, we have developed theoretical and practical foundations for a new real-time action recognition system. This system is based on Hidden Markov Model (HMM) along with colorizing depth maps. The use of depth cameras provides privacy protection. Colorizing depth images in the hue color space enables compressing and visualizing depth data, and detecting persons. The specific detector used for person detection is You Look Only Once (YOLOv5). Appearance and motion features are extracted from depth map sequences and are represented with a Histogram of Oriented Gradients (HOG). These HOG feature vectors are transformed as the observation sequences and then fed into the HMM. Finally, the Viterbi Algorithm is applied to recognize the sequential actions. This system has been tested on real-world data featuring three participants in a care center. We tried out three combinations of HMM with classification algorithms and found that a fusion with Support Vector Machine (SVM) had the best average results, achieving an accuracy rate (84.04%).

An Immersive Human-Robot Interactive Game Framework Based on Deep Learning for Children’s Concentration Training

In order to alleviate bottlenecks such as the lack of professional teachers, inattention during training processes, and low effectiveness in concentration training, we have proposed an immersive human–robot interactive (HRI) game framework based on deep learning for children’s concentration training and demonstrated its use through human–robot interactive games based on gesture recognition. The HRI game framework includes four functional modules: video data acquisition, image recognition modeling, a deep learning algorithm (YOLOv5), and information feedback. First, we built a gesture recognition model containing 10,000 pictures of children’s gestures, using the YOLOv5 algorithm. The average accuracy in recognition trainingwas 98.7%. Second, we recruited 120 children with attention deficits (aged from 9 to 12 years) to play the HRI games, including 60 girls and 60 boys. In the HRI game experiment, we obtained 8640 sample data, which were normalized and processed.According to the results, we found that the girls had better visual short-term memory and a shorter response time than boys. The research results showed that HRI games had a high efficacy, convenience, and full freedom, making them appropriate for children’s concentration training.

Literature Review on Ship Localization, Classification, and Detection Methods Based on Optical Sensors and Neural Networks

Object detection is a common application within the computer vision area. Its tasks include the classic challenges of object localization and classification. As a consequence, object detection is a challenging task. Furthermore, this technique is crucial for maritime applications since situational awareness can bring various benefits to surveillance systems. The literature presents various models to improve automatic target recognition and tracking capabilities that can be applied to and leverage maritime surveillance systems. Therefore, this paper reviews the available models focused on localization, classification, and detection. Moreover, it analyzes several works that apply the discussed models to the maritime surveillance scenario. Finally, it highlights the main opportunities and challenges, encouraging new research in this area.

Automatic recognition of parasitic products in stool examination using object detection approach

BACKGROUND

Object detection is a new artificial intelligence approach to morphological recognition and labeling parasitic pathogens. Due to the lack of equipment and trained personnel, artificial intelligence innovation for searching various parasitic products in stool examination will enable patients in remote areas of undeveloped countries to access diagnostic services. Because object detection is a developing approach that has been tested for its effectiveness in detecting intestinal parasitic objects such as protozoan cysts and helminthic eggs, it is suitable for use in rural areas where many factors supporting laboratory testing are still lacking. Based on the literatures, the YOLOv4-Tiny produces faster results and uses less memory with the support of low-end GPU devices. In comparison to the YOLOv3 and YOLOv3-Tiny models, this study aimed to propose an automated object detection approach, specifically the YOLOv4-Tiny model, for automatic recognition of intestinal parasitic products in stools.

METHODS

To identify protozoan cysts and helminthic eggs in human feces, the three YOLO approaches; YOLOv4-Tiny, YOLOv3, and YOLOv3-Tiny, were trained to recognize 34 intestinal parasitic classes using training of image dataset. Feces were processed using a modified direct smear method adapted from the simple direct smear and the modified Kato-Katz methods. The image dataset was collected from intestinal parasitic objects discovered during stool examination and the three YOLO models were trained to recognize the image datasets.

RESULTS

The non-maximum suppression technique and the threshold level were used to analyze the test dataset, yielding results of 96.25% precision and 95.08% sensitivity for YOLOv4-Tiny. Additionally, the YOLOv4-Tiny model had the best AUPRC performance of the three YOLO models, with a score of 0.963.

CONCLUSION

This study, to our knowledge, was the first to detect protozoan cysts and helminthic eggs in the 34 classes of intestinal parasitic objects in human stools.

Failure Detection in Quadcopter UAVs Using K-Means Clustering

We propose an unmanned aerial vehicle (UAV) failure detection system as the first step of a three-step autonomous emergency landing safety framework for UAVs. We showed the effectiveness and feasibility of using vibration data with the k-means clustering algorithm in detecting mid-flight UAV failures for that purpose. Specifically, we measured vibration signals for different faulty propeller cases during several test flights, utilizing a custom-made hardware system. After we made the vibration graphs and extracted the data, we investigated to determine the combination of acceleration and gyroscope parameters that results in the best accuracy of failure detection in quadcopter UAVs. Our investigations show that considering the gyroscope parameter in the vertical direction (gZ) along with the accelerometer parameter in the same direction (aZ) results in the highest accuracy of failure detection for the purpose of emergency landing of faulty UAVs, while ensuring a quick detection and timely engagement of the safety framework. Based on the parameter set (gZ-aZ), we then created scatter plots and confusion matrices, and applied the k-means clustering algorithm to the vibration dataset to classify the data into three health state clusters-normal, faulty, and failure. We confirm the effectiveness of the proposed system with flight experiments, in which we were able to detect faults and failures utilizing the aforementioned clusters in real time.

Automatic Vehicle Identification and Classification Model Using the YOLOv3 Algorithm for a Toll Management System

Vehicle identification and classification are some of the major tasks in the areas of toll management and traffic management, where these smart transportation systems are implemented by integrating various information communication technologies and multiple types of hardware. The currently shifting era toward artificial intelligence has also motivated the implementation of vehicle identification and classification using AI-based techniques, such as machine learning, artificial neural network and deep learning. In this research, we used the deep learning YOLOv3 algorithm and trained it on a custom dataset of vehicles that included different vehicle classes as per the Indian Government’s recommendation to implement the automatic vehicle identification and classification for use in the toll management system deployed at toll plazas. For faster processing of the test videos, the frames were saved at a certain interval and then the saved frames were passed through the algorithm. Apart from toll plazas, we also tested the algorithm for vehicle identification and classification on highways and urban areas. Implementing automatic vehicle identification and classification using traditional techniques is a highly proprietary endeavor. Since YOLOv3 is an open-standard-based algorithm, it paves the way to developing sustainable solutions in the area of smart transportation.

Optimisation of Deep Learning Small-Object Detectors with Novel Explainable Verification

In this paper, we present a novel methodology based on machine learning for identifying the most appropriate from a set of available state-of-the-art object detectors for a given application. Our particular interest is to develop a road map for identifying verifiably optimal selections, especially for challenging applications such as detecting small objects in a mixed-size object dataset. State-of-the-art object detection systems often find the localisation of small-size objects challenging since most are usually trained on large-size objects. These contain abundant information as they occupy a large number of pixels relative to the total image size. This fact is normally exploited by the model during training and inference processes. To dissect and understand this process, our approach systematically examines detectors’ performances using two very distinct deep convolutional networks. The first is the single-stage YOLO V3 and the second is the double-stage Faster R-CNN. Specifically, our proposed method explores and visually illustrates the impact of feature extraction layers, number of anchor boxes, data augmentation, etc., utilising ideas from the field of explainable Artificial Intelligence (XAI). Our results, for example, show that multi-head YOLO V3 detectors trained using augmented data produce better performance even with a fewer number of anchor boxes. Moreover, robustness regarding the detector’s ability to explain how a specific decision was reached is investigated using different explanation techniques. Finally, two new visualisation techniques are proposed, WS-Grad and Concat-Grad, for identifying explanation cues of different detectors. These are applied to specific object detection tasks to illustrate their reliability and transparency with respect to the decision process. It is shown that the proposed techniques can result in high resolution and comprehensive heatmaps of the image areas, significantly affecting detector decisions as compared to the state-of-the-art techniques tested.

Evaluating the Forest Ecosystem through a Semi-Autonomous Quadruped Robot and a Hexacopter UAV

Accurate and timely monitoring is imperative to the resilience of forests for economic growth and climate regulation. In the UK, forest management depends on citizen science to perform tedious and time-consuming data collection tasks. In this study, an unmanned aerial vehicle (UAV) equipped with a light sensor and positioning capabilities is deployed to perform aerial surveying and to observe a series of forest health indicators (FHIs) which are inaccessible from the ground. However, many FHIs such as burrows and deadwood can only be observed from under the tree canopy. Hence, we take the initiative of employing a quadruped robot with an integrated camera as well as an external sensing platform (ESP) equipped with light and infrared cameras, computing, communication and power modules to observe these FHIs from the ground. The forest-monitoring time can be extended by reducing computation and conserving energy. Therefore, we analysed different versions of the YOLO object-detection algorithm in terms of accuracy, deployment and usability by the EXP to accomplish an extensive low-latency detection. In addition, we constructed a series of new datasets to train the YOLOv5x and YOLOv5s for recognising FHIs. Our results reveal that YOLOv5s is lightweight and easy to train for FHI detection while performing close to real-time, cost-effective and autonomous forest monitoring.

Integrating Deep Learning-Based IoT and Fog Computing with Software-Defined Networking for Detecting Weapons in Video Surveillance Systems

Due to the widespread proliferation of multimedia traffic resulting from Internet of Things (IoT) applications and the increased use of remote multimedia-based applications, as a consequence of COVID-19, there is an urgent need to develop intelligent adaptive techniques that improve the Quality of Service (QoS) perceived by end-users. In this work, we investigate the integration of deep learning techniques with Software-Defined Network (SDN) architecture to support delay-sensitive applications in IoT environments. Weapon detection in real-time video surveillance applications is deployed as our case study upon which multiple deep learning-based models are trained and evaluated for detection using precision, recall, and mean absolute precision. The deep learning model with the highest performance is then deployed within a proposed artificial intelligence model at the edge to extract the first detected video frames containing weapons for quick transmission to authorities, thus helping in the early detection and prevention of different kinds of crimes, and at the same time decreasing the bandwidth requirements by offloading the communication network from massive traffic transmission. Performance improvement is achieved in terms of delay, throughput, and bandwidth requirements by dynamically programming the network to provide different QoS based on the type of offered traffic and current traffic load, and based on the destination of the traffic. Performance evaluation of the proposed model was carried out using the mininet emulator, which revealed improvement of up to 75.0% in terms of average throughput, up to 14.7% in terms of mean jitter, and up to 32.5% in terms of packet loss.

Detection of River Plastic Using UAV Sensor Data and Deep Learning

Plastic pollution is a critical global issue. Increases in plastic consumption have triggered increased production, which in turn has led to increased plastic disposal. In situ observation of plastic litter is tedious and cumbersome, especially in rural areas and around transboundary rivers. We therefore propose automatic mapping of plastic in rivers using unmanned aerial vehicles (UAVs) and deep learning (DL) models that require modest compute resources. We evaluate the method at two different sites: the Houay Mak Hiao River, a tributary of the Mekong River in Vientiane, Laos, and Khlong Nueng canal in Talad Thai, Khlong Luang, Pathum Thani, Thailand. Detection models in the You Only Look Once (YOLO) family are evaluated in terms of runtime resources and mean average Precision (mAP) at an Intersection over Union (IoU) threshold of 0.5. YOLOv5s is found to be the most effective model, with low computational cost and a very high mAP of 0.81 without transfer learning for the Houay Mak Hiao dataset. The performance of all models is improved by transfer learning from Talad Thai to Houay Mak Hiao. Pre-trained YOLOv4 with transfer learning obtains the overall highest accuracy, with a 3.0% increase in mAP to 0.83, compared to the marginal increase of 2% in mAP for pre-trained YOLOv5s. YOLOv3, when trained from scratch, shows the greatest benefit from transfer learning, with an increase in mAP from 0.59 to 0.81 after transfer learning from Talad Thai to Houay Mak Hiao. The pre-trained YOLOv5s model using the Houay Mak Hiao dataset is found to provide the best tradeoff between accuracy and computational complexity, requiring model resources yet providing reliable plastic detection with or without transfer learning. Various stakeholders in the effort to monitor and reduce plastic waste in our waterways can utilize the resulting deep learning approach irrespective of location.

YOLOv5-Ytiny: A Miniature Aggregate Detection and Classification Model

Aggregate classification is the prerequisite for making concrete. Traditional aggregate identification methods have the disadvantages of low accuracy and a slow speed. To solve these problems, a miniature aggregate detection and classification model, based on the improved You Only Look Once (YOLO) algorithm, named YOLOv5-ytiny is proposed in this study. Firstly, the C3 structure in YOLOv5 is replaced with our proposed CI structure. Then, the redundant part of the Neck structure is pruned by us. Finally, the bounding box regression loss function GIoU is changed to the CIoU function. The proposed YOLOv5-ytiny model was compared with other object detection algorithms such as YOLOv4, YOLOv4-tiny, and SSD. The experimental results demonstrate that the YOLOv5-ytiny model reaches 9.17 FPS, 60% higher than the original YOLOv5 algorithm, and reaches 99.6% mAP (the mean average precision). Moreover, the YOLOv5-ytiny model has significant speed advantages over CPU-only computer devices. This method can not only accurately identify the aggregate but can also obtain the relative position of the aggregate, which can be effectively used for aggregate detection.

Deep Neural Network Recognition of Rivet Joint Defects in Aircraft Products

The mathematical statement of the problem of recognizing rivet joint defects in aircraft products is given. A computational method for the recognition of rivet joint defects in aircraft equipment based on video images of aircraft joints has been proposed with the use of neural networks YOLO-V5 for detecting and MobileNet V3 Large for classifying rivet joint states. A novel dataset based on a real physical model of rivet joints has been created for machine learning. The accuracy of the result obtained during modeling was 100% in both binary and multiclass classification.

Tools, techniques, datasets and application areas for object detection in an image: a review

Object detection is one of the most fundamental and challenging tasks to locate objects in images and videos. Over the past, it has gained much attention to do more research on computer vision tasks such as object classification, counting of objects, and object monitoring. This study provides a detailed literature review focusing on object detection and discusses the object detection techniques. A systematic review has been followed to summarize the current research work's findings and discuss seven research questions related to object detection. Our contribution to the current research work is (i) analysis of traditional, two-stage, one-stage object detection techniques, (ii) Dataset preparation and available standard dataset, (iii) Annotation tools, and (iv) performance evaluation metrics. In addition, a comparative analysis has been performed and analyzed that the proposed techniques are different in their architecture, optimization function, and training strategies. With the remarkable success of deep neural networks in object detection, the performance of the detectors has improved. Various research challenges and future directions for object detection also has been discussed in this research paper.

A deep learning model to classify and detect brain abnormalities in portable microwave based imaging system

Automated classification and detection of brain abnormalities like a tumor(s) in reconstructed microwave (RMW) brain images are essential for medical application investigation and monitoring disease progression. This paper presents the automatic classification and detection of human brain abnormalities through the deep learning-based YOLOv5 object detection model in a portable microwave head imaging system (MWHI). Initially, four hundred RMW image samples, including non-tumor and tumor(s) in different locations are collected from the implemented MWHI system. The RMW image dimension is 640 × 640 pixels. After that, image pre-processing and augmentation techniques are applied to generate the training dataset, consisting of 4400 images. Later, 80% of images are used to train the models, and 20% are used for testing. Later, from the 80% training dataset, 20% are utilized to validate the models. The detection and classification performances are evaluated by three variations of the YOLOv5 model: YOLOv5s, YOLOv5m, and YOLOv5l. It is investigated that the YOLOv5l model performed better compared to YOLOv5s, YOLOv5m, and state-of-the-art object detection models. The achieved accuracy, precision, sensitivity, specificity, F1-score, mean average precision (mAP), and classification loss are 96.32%, 95.17%, 94.98%, 95.28%, 95.53%, 96.12%, and 0.0130, respectively for the YOLOv5l model. The YOLOv5l model automatically detected tumor(s) accurately with a predicted bounding box including objectness score in RMW images and classified the tumors into benign and malignant classes. So, the YOLOv5l object detection model can be reliable for automatic tumor(s) detection and classification in a portable microwave brain imaging system as a real-time application.

Runtime ML-DL Hybrid Inference Platform Based on Multiplexing Adaptive Space-Time Resolution for Fast Car Incident Prevention in Low-Power Embedded Systems

Forward vehicle detection is the key technique to preventing car incidents in front. Artificial intelligence (AI) techniques are used to more accurately detect vehicles, but AI-based vehicle detection takes a lot of processing time due to its high computational complexity. When there is a risk of collision with a vehicle in front, the slow detection speed of the vehicle may lead to an accident. To quickly detect a vehicle in real-time, a high-speed and lightweight vehicle detection technique with similar detection performance to that of an existing AI-based vehicle detection is required. In addition, to apply forward collision warning system (FCWS) technology to vehicles, it is important to provide high performance based on low-power embedded systems because the vehicle’s battery consumption must remain low. The vehicle detection algorithm occupies the most resources in FCWS. To reduce power consumption, it is important to reduce the computational complexity of an algorithm, that is, the amount of resources required to run it. This paper describes a method for fast, accurate forward vehicle detection using machine learning and deep learning. To detect a vehicle in consecutive images consistently, a Kalman filter is used to predict the bounding box based on the tracking algorithm and correct it based on the detection algorithm. As a result, its vehicle detection speed is about 25.85 times faster than deep-learning-based object detection is, and its detection accuracy is better than machine-learning-based object detection is.

An Object Detection Model for Paint Surface Detection Based on Improved YOLOv3

To solve the problem of poor performance of the target detection algorithm and false detection in the detection of paint surface defects of office chairs five-star feet, we propose a defect detection method based on the improved YOLOv3 algorithm. Firstly, a new feature fusion structure is designed to reduce the missed detection rate of small targets. Then we used the CIOU loss function to improve the positioning accuracy. At the same time, a parallel version of the k-means++ initialization algorithm (K-means||) is used to optimize and determine the parameters of the a priori anchor so as to improve the matching degree between the a priori anchor and the feature layer. We constructed a dataset of paint surface defects on the five-star feet of office chairs and performed optimization training, and used multiple algorithms and different datasets to conduct comparative experiments to validate the algorithm. The experimental results show that the improved YOLOv3 algorithm is effective in that the average precision on the self-made dataset reaches 88.3%, which is 5.8% higher than the original algorithm. At the same time, it has also been verified based on the Aliyun Tianchi competition aluminum dataset, and the average precision has reached 89.2%. This method realizes the real-time detection of the paint surface defects of the five-star feet of the office chair very well.

A Comparative Study of Autonomous Object Detection Algorithms in the Maritime Environment Using a UAV Platform

Maritime operations rely heavily on surveillance and require reliable and timely data that can inform decisions and planning. Critical information in such cases includes the exact location of objects in the water, such as vessels, persons, and others. Due to the unique characteristics of the maritime environment, the location of even inert objects changes through time, depending on the weather conditions, water currents, etc. Unmanned aerial vehicles (UAVs) can be used to support maritime operations by providing live video streams and images from the area of operations. Machine learning algorithms can be developed, trained, and used to automatically detect and track objects of specific types and characteristics. EFFECTOR is an EU-funded project, developing an Interoperability Framework for maritime surveillance. Within the project, we developed an embedded system that employs machine learning algorithms, allowing a UAV to autonomously detect objects in the water and keep track of their changing position through time. Using the on-board computation unit of the UAV, we ran and present the results of a series of comparative tests among possible architecture sizes and training datasets for the detection and tracking of objects in the maritime environment. We tested architectures based on their efficiency, accuracy, and speed. A combined solution for training the datasets is suggested, providing optimal efficiency and accuracy.

A Video Analytics System for Person Detection Combined with Edge Computing

Ensuring citizens’ safety and security has been identified as the number one priority for city authorities when it comes to the use of smart city technologies. Automatic understanding of the scene, and the associated provision of situational awareness for emergency situations, are able to efficiently contribute to such domains. In this study, a Video Analytics Edge Computing (VAEC) system is presented that performs real-time enhanced situation awareness for person detection in a video surveillance manner that is also able to share geolocated person detection alerts and other accompanied crucial information. The VAEC system adopts state-of-the-art object detection and tracking algorithms, and it is integrated with the proposed Distribute Edge Computing Internet of Things (DECIoT) platform. The aforementioned alerts and information are able to be shared, though the DECIoT, to smart city platforms utilizing proper middleware. To verify the utility and functionality of the VAEC system, extended experiments were performed (i) in several light conditions, (ii) using several camera sensors, and (iii) in several use cases, such as installed in fixed position of a building or mounted to a car. The results highlight the potential of VAEC system to be exploited by decision-makers or city authorities, providing enhanced situational awareness.

Fast identification and quantification of c-Fos protein using you-only-look-once-v5

In neuroscience, protein activity characterizes neuronal excitability in response to a diverse array of external stimuli and represents the cell state throughout the development of brain diseases. Importantly, it is necessary to characterize the proteins involved in disease progression, nuclear function determination, stimulation method effect, and other aspects. Therefore, the quantification of protein activity is indispensable in neuroscience. Currently, ImageJ software and manual counting are two of the most commonly used methods to quantify proteins. To improve the efficiency of quantitative protein statistics, the you-only-look-once-v5 (YOLOv5) model was proposed. In this study, c-Fos immunofluorescence images data set as an example to verify the efficacy of the system using protein quantitative statistics. The results indicate that YOLOv5 was less time-consuming or obtained higher accuracy than other methods (time: ImageJ software: 80.12 ± 1.67 s, manual counting: 3.41 ± 0.25 s, YOLOv5: 0.0251 ± 0.0003 s, p < 0.0001, n = 83; simple linear regression equation: ImageJ software: Y = 1.013 × X + 0.776, R ² = 0.837; manual counting: Y = 1.0*X + 0, R ² = 1; YOLOv5: Y = 0.9730*X + 0.3821, R ² = 0.933, n = 130). The findings suggest that the YOLOv5 algorithm provides feasible methods for quantitative statistical analysis of proteins and has good potential for application in detecting target proteins in neuroscience.