Deep learning techniques to classify agricultural crops through UAV imagery: a review

Quantitative analysis and evaluation of winter and summer landscape colors in the Yangzhou ancient Canal utilizing deep learning

Color is an important index for human visual evaluation of landscape, and it is also a key factor affecting people's recognition and experience of heritage landscape. In this study, five important sites of the Yangzhou Grand Canal were selected for the color quantification analysis by using the Deep Learning(DL) scene parsing algorithm. The color characteristics of the winter and summer landscape of the five sites were evaluated as well as the Scenic Beauty Estimation (SBE) value. Furthermore, the correlation analysis between the color characteristics and the SBE value was established in order to study the relationship between color characteristics and the landscape beauty. The main results are as follows: ①.The dominant color of the five sites is blue and green, the building color is mainly orange and yellow in both winter and summer. The dominant plant color in five sites is green in summer, whereas in winter, changes to yellow(Site5:YZJGD) or cyan(Site1:DGGD, Site3:GZGD); ②.The overall color saturation is low in winter with the percentages of Very Low Saturation in almost each site(except site5:YZJGD)reach 80-98%. Summer has Medium Saturation colors, the percentage of Mid Saturation of sky in Site 2(GMS) in summer is 44.87%. ③. The landscapes have low brightness in winter and higher brightness in summer in all sites, sky is the only category whose High Brightness value exceeds 50% in both seasons.And in winter, landscapes are most prevalent in Low Brightness and Medium Brightness. In summer, the percentages of Medium Brightness and High Brightness increase.④.The color diversity of the sites in winter varies significantly, whereas the color diversity of the sites in summer varies slightly.The highest color diversity of plants is found in DGGD(Diversity > 1.5). ⑤.In winter, the highest SBE value is found in Site2:GMS(0.5956), and the lowest SBE value is found in Site5:YZJGD(- 0.8216),which is a large gap(1.4172).The highest average SBE value is in Site2:GMS(0.5062), followed by Site3:GZGD (0.2091), which both have average values greater than zero. ⑥.Correlation analysis revealed that there is no significant correlation between the saturation and SBE values(p > 0.05).However, the Pearson correlation coefficients which are - 0.625(winter) and 0.689(summer) indicate strong correlation.Meanwhile, there is no significant correlation between the color diversity and SBE values(p > 0.05). However, the Pearson correlation coefficients are 0.807(winter) and - 0.747(summer), indicating strong correlation.This study provides an in-depth examination of the Canal landscape color, it is hoped to promote the systematic and scientific study of landscape colors and provide a theoretical basis for the scientific design of heritage landscape color.

Enhanced object detection in remote sensing images by applying metaheuristic and hybrid metaheuristic optimizers to YOLOv7 and YOLOv8

Developments in object detection algorithms are critical for urban planning, environmental monitoring, surveillance, and many other applications. The primary objective of the article was to improve detection precision and model efficiency. The paper compared the performance of six different metaheuristic optimization algorithms including Gray Wolf Optimizer (GWO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Remora Optimization Algorithm (ROA), Aquila Optimizer (AO), and Hybrid PSO-GWO (HPSGWO) combined with YOLOv7 and YOLOv8. The study included two distinct remote sensing datasets, RSOD and VHR-10. Many performance measures as precision, recall, and mean average precision (mAP) were used during the training, validation, and testing processes, as well as the fit score. The results show significant improvements in both YOLO variants following optimization using these strategies. The GWO-optimized YOLOv7 with 0.96 mAP 50, and 0.69 mAP 50:95, and the HPSGWO-optimized YOLOv8 with 0.97 mAP 50, and 0.72 mAP 50:95 had the best performance in the RSOD dataset. Similarly, the GWO-optimized versions of YOLOv7 and YOLOv8 had the best performance on the VHR-10 dataset with 0.87 mAP 50, and 0.58 mAP 50:95 for YOLOv7 and with 0.99 mAP 50, and 0.69 mAP 50:95 for YOLOv8, indicating greater performance. The findings supported the usefulness of metaheuristic optimization in increasing the precision and recall rates of YOLO algorithms and demonstrated major significance in improving object recognition tasks in remote sensing imaging, opening up a viable route for applications in a variety of disciplines.

Crop yield prediction in agriculture: A comprehensive review of machine learning and deep learning approaches, with insights for future research and sustainability

The agriculture sector is confronted with numerous challenges in the quest for accurate crop yield estimation, which is essential for efficient resource management and mitigating food scarcity in a rapidly growing global population. This research paper delves into the application of advanced Artificial Intelligence (AI) techniques to enhance crop yield estimation in the context of diverse agricultural challenges. Through a systematic literature review and analysis of relevant studies, this paper explores the role of AI methods, such as Machine Learning (ML) and Deep Learning (DL), in addressing the complexities posed by geographical variations, crop diversity, and cultivation areas. The review identifies a wealth of AI-powered solutions employed in crop yield prediction, emphasizing the importance of precise environmental and agricultural data. Key factors contributing to accurate estimation include temperature, rainfall, soil type, humidity, and various vegetation indices, such as NDVI, EVI, LAI, and NDWI. The research paper also examines the algorithms frequently utilized in the machine learning domain, including Random Forest (RF), Artificial Neural Networks (ANN), and Support Vector Machine (SVM). In the realm of deep learning, Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM), and Deep Neural Networks (DNN) emerge as promising candidates. The findings of this study shed light on the transformative potential of advanced AI techniques in improving crop yield estimation accuracy, ultimately enhancing agricultural planning and resource management. By addressing the challenges posed by geographical diversity, crop heterogeneity, and changing environmental conditions, AI-driven models offer new avenues for sustainable agriculture in an ever-evolving world. This research paper provides valuable insights and directions for future studies, highlighting the critical role of AI in ensuring food security and sustainability in agriculture.

The implementation of robotic dogs in automatic detection and surveillance of red imported fire ant nests

BACKGROUND

The Red Imported Fire Ant (RIFA), scientifically known as Solenopsis invicta, is a destructive invasive species causing considerable harm to ecosystems and generating substantial economic costs globally. Traditional methods for RIFA nests detection are labor-intensive and may not be scalable to larger field areas. This study aimed to develop an innovative surveillance system that leverages artificial intelligence (AI) and robotic dogs to automate the detection and geolocation of RIFA nests, thereby improving monitoring and control strategies.

RESULTS

The designed surveillance system, through integrating the CyberDog robotic platform with a YOLOX AI model, demonstrated RIFA nest detection precision rates of >90%. The YOLOX model was trained on a dataset containing 1118 images and achieved a final precision rate of 0.95, with an inference time of 20.16 ms per image, indicating real-time operational suitability. Field tests revealed that the CyberDog system identified three times more nests than trained human inspectors, with significantly lower rates of missed detections and false positives.

CONCLUSION

The findings underscore the potential of AI-driven robotic systems in advancing pest management. The CyberDog/YOLOX system not only matched human inspectors in speed, but also exceeded them in accuracy and efficiency. This study's results are significant as they highlight how technology can be harnessed to address biological invasions, offering a more effective, ecologically friendly, and scalable solution for RIFA detection. The successful implementation of this system could pave the way for broader applications in environmental monitoring and pest control, ultimately contributing to the preservation of biodiversity and economic stability. © 2024 Society of Chemical Industry.

Harnessing UAVs and deep learning for accurate grass weed detection in wheat fields: a study on biomass and yield implications

Weeds are undesired plants competing with crops for light, nutrients, and water, negatively impacting crop growth. Identifying weeds in wheat fields accurately is important for precise pesticide spraying and targeted weed control. Grass weeds in their early growth stages look very similar to wheat seedlings, making them difficult to identify. In this study, we focused on wheat fields with varying levels of grass weed infestation and used unmanned aerial vehicles (UAVs) to obtain images. By utilizing deep learning algorithms and spectral analysis technology, the weeds were identified and extracted accurately from wheat fields. Our results showed that the precision of weed detection in scattered wheat fields was 91.27% and 87.51% in drilled wheat fields. Compared to areas without weeds, the increase in weed density led to a decrease in wheat biomass, with the maximum biomass decreasing by 71%. The effect of weed density on yield was similar, with the maximum yield decreasing by 4320 kg·ha- 1, a drop of 60%. In this study, a method for monitoring weed occurrence in wheat fields was established, and the effects of weeds on wheat growth in different growth periods and weed densities were studied by accurately extracting weeds from wheat fields. The results can provide a reference for weed control and hazard assessment research.

An Improved Instance Segmentation Method for Complex Elements of Farm UAV Aerial Survey Images

Farm aerial survey layers can assist in unmanned farm operations, such as planning paths and early warnings. To address the inefficiencies and high costs associated with traditional layer construction, this study proposes a high-precision instance segmentation algorithm based on SparseInst. Considering the structural characteristics of farm elements, this study introduces a multi-scale attention module (MSA) that leverages the properties of atrous convolution to expand the sensory field. It enhances spatial and channel feature weights, effectively improving segmentation accuracy for large-scale and complex targets in the farm through three parallel dense connections. A bottom-up aggregation path is added to the feature pyramid fusion network, enhancing the model's ability to perceive complex targets such as mechanized trails in farms. Coordinate attention blocks (CAs) are incorporated into the neck to capture richer contextual semantic information, enhancing farm aerial imagery scene recognition accuracy. To assess the proposed method, we compare it against existing mainstream object segmentation models, including the Mask R-CNN, Cascade-Mask, SOLOv2, and Condinst algorithms. The experimental results show that the improved model proposed in this study can be adapted to segment various complex targets in farms. The accuracy of the improved SparseInst model greatly exceeds that of Mask R-CNN and Cascade-Mask and is 10.8 and 12.8 percentage points better than the average accuracy of SOLOv2 and Condinst, respectively, with the smallest number of model parameters. The results show that the model can be used for real-time segmentation of targets under complex farm conditions.

Enhancing two-stage object detection models via data-driven anchor box optimization in UAV-based maritime SAR

The high-altitude imaging capabilities of Unmanned Aerial Vehicles (UAVs) offer an effective solution for maritime Search and Rescue (SAR) operations. In such missions, the accurate identification of boats, personnel, and objects within images is crucial. While object detection models trained on general image datasets can be directly applied to these tasks, their effectiveness is limited due to the unique challenges posed by the specific characteristics of maritime SAR scenarios. Addressing this challenge, our study leverages the large-scale benchmark dataset SeaDronesSee, specific to UAV-based maritime SAR, to analyze and explore the unique attributes of image data in this scenario. We identify the need for optimization in detecting specific categories of difficult-to-detect objects within this context. Building on this, an anchor box optimization strategy is proposed based on clustering analysis, aimed at enhancing the performance of the renowned two-stage object detection models in this specialized task. Experiments were conducted to validate the proposed anchor box optimization method and to explore the underlying reasons for its effectiveness. The experimental results show our optimization method achieved a 45.8% and a 10% increase in average precision over the default anchor box configurations of torchvision and the SeaDronesSee official sample code configuration respectively. This enhancement was particularly evident in the model's significantly improved ability to detect swimmers, floaters, and life jackets on boats within the SeaDronesSee dataset's SAR scenarios. The methods and findings of this study are anticipated to provide the UAV-based maritime SAR research community with valuable insights into data characteristics and model optimization, offering a meaningful reference for future research.

Machine learning based recommendation of agricultural and horticultural crop farming in India under the regime of NPK, soil pH and three climatic variables

Machine learning (ML) can make use of agricultural data related to crop yield under varying soil nutrient levels, and climatic fluctuations to suggest appropriate crops or supplementary nutrients to achieve the highest possible production. The aim of this study was to evaluate the efficacy of five distinct ML models for a dataset sourced from the Kaggle repository to generate practical recommendations for crop selection or determination of required nutrient(s) in a given site. The datasets contain information on NPK, soil pH, and three climatic variables: temperature, rainfall, and humidity. The models namely Support vector machine, XGBoost, Random forest, KNN, and Decision Tree were trained using yields of individual data sets of 11 agricultural and 10 horticultural crops, as well as combined yield of both agri-horticultural crops. The results strongly suggest to evaluate individual data sets separately for each crop category rather than using combined the data sets of both categories for better predictions. Comparing the five ML models, the XGBoost demonstrated the highest level of accuracy. The precision rates of XGBoost for recommending agricultural crops, horticultural crops, and a combination of both were 99.09 % (AUC 1.0), 99.3 % (AUC 1.0), and 98.51 % (AUC 0.99), respectively. This non-intrusive method for generating crop recommendations in diverse environmental conditions holds the potential to provide valuable insights for the development of a user-friendly AI cloud-based interface. Such an interface would enable rapid decision-making for optimal fertilizer applications and the selection of suitable crops for cultivation at specific sites.

G, Rajendran S. Dipper throated optimization with deep convolutional neural network-based crop classification for remote sensing image analysis

Problem

With the rapid advancement of remote sensing technology is that the need for efficient and accurate crop classification methods has become increasingly important. This is due to the ever-growing demand for food security and environmental monitoring. Traditional crop classification methods have limitations in terms of accuracy and scalability, especially when dealing with large datasets of high-resolution remote sensing images. This study aims to develop a novel crop classification technique, named Dipper Throated Optimization with Deep Convolutional Neural Networks based Crop Classification (DTODCNN-CC) for analyzing remote sensing images. The objective is to achieve high classification accuracy for various food crops.

Methods

The proposed DTODCNN-CC approach consists of the following key components. Deep convolutional neural network (DCNN) a GoogleNet architecture is employed to extract robust feature vectors from the remote sensing images. The Dipper throated optimization (DTO) optimizer is used for hyper parameter tuning of the GoogleNet model to achieve optimal feature extraction performance. Extreme Learning Machine (ELM): This machine learning algorithm is utilized for the classification of different food crops based on the extracted features. The modified sine cosine algorithm (MSCA) optimization technique is used to fine-tune the parameters of ELM for improved classification accuracy.

Results

Extensive experimental analyses are conducted to evaluate the performance of the proposed DTODCNN-CC approach. The results demonstrate that DTODCNN-CC can achieve significantly higher crop classification accuracy compared to other state-of-the-art deep learning methods.

Conclusion

The proposed DTODCNN-CC technique provides a promising solution for efficient and accurate crop classification using remote sensing images. This approach has the potential to be a valuable tool for various applications in agriculture, food security, and environmental monitoring.

DPXception: a lightweight CNN for image-based date palm species classification

Introduction

Date palm species classification is important for various agricultural and economic purposes, but it is challenging to perform based on images of date palms alone. Existing methods rely on fruit characteristics, which may not be always visible or present. In this study, we introduce a new dataset and a new model for image-based date palm species classification.

Methods

Our dataset consists of 2358 images of four common and valuable date palm species (Barhi, Sukkari, Ikhlas, and Saqi), which we collected ourselves. We also applied data augmentation techniques to increase the size and diversity of our dataset. Our model, called DPXception (Date Palm Xception), is a lightweight and efficient CNN architecture that we trained and fine-tuned on our dataset. Unlike the original Xception model, our DPXception model utilizes only the first 100 layers of the Xception model for feature extraction (Adapted Xception), making it more lightweight and efficient. We also applied normalization prior to adapted Xception and reduced the model dimensionality by adding an extra global average pooling layer after feature extraction by adapted Xception.

Results and discussion

We compared the performance of our model with seven well-known models: Xception, ResNet50, ResNet50V2, InceptionV3, DenseNet201, EfficientNetB4, and EfficientNetV2-S. Our model achieved the highest accuracy (92.9%) and F1-score (93%) among the models, as well as the lowest inference time (0.0513 seconds). We also developed an Android smartphone application that uses our model to classify date palm species from images captured by the smartphone's camera in real time. To the best of our knowledge, this is the first work to provide a public dataset of date palm images and to demonstrate a robust and practical image-based date palm species classification method. This work will open new research directions for more advanced date palm analysis tasks such as gender classification and age estimation.

Remote Sensing Imagery Data Analysis Using Marine Predators Algorithm with Deep Learning for Food Crop Classification

Recently, the usage of remote sensing (RS) data attained from unmanned aerial vehicles (UAV) or satellite imagery has become increasingly popular for crop classification processes, namely soil classification, crop mapping, or yield prediction. Food crop classification using RS images (RSI) is a significant application of RS technology in agriculture. It involves the use of satellite or aerial imagery to identify and classify different types of food crops grown in a specific area. This information can be valuable for crop monitoring, yield estimation, and land management. Meeting the criteria for analyzing these data requires increasingly sophisticated methods and artificial intelligence (AI) technologies provide the necessary support. Due to the heterogeneity and fragmentation of crop planting, typical classification approaches have a lower classification performance. However, the DL technique can detect and categorize crop types effectively and has a stronger feature extraction capability. In this aspect, this study designed a new remote sensing imagery data analysis using the marine predators algorithm with deep learning for food crop classification (RSMPA-DLFCC) technique. The RSMPA-DLFCC technique mainly investigates the RS data and determines the variety of food crops. In the RSMPA-DLFCC technique, the SimAM-EfficientNet model is utilized for the feature extraction process. The MPA is applied for the optimal hyperparameter selection process in order to optimize the accuracy of SimAM-EfficientNet architecture. MPA, inspired by the foraging behaviors of marine predators, perceptively explores hyperparameter configurations to optimize the hyperparameters, thereby improving the classification accuracy and generalization capabilities. For crop type detection and classification, an extreme learning machine (ELM) model can be used. The simulation analysis of the RSMPA-DLFCC technique is performed on two benchmark datasets. The extensive analysis of the results portrayed the higher performance of the RSMPA-DLFCC approach over existing DL techniques.

Maize Production under Drought Stress: Nutrient Supply, Yield Prediction

Maize yield forecasting is important for the organisation of harvesting and storage, for the estimation of the commodity base and for the provision of the country's feed and food demand (export-import). To this end, a field experiment was conducted in dry (2021) and extreme dry (2022) years to track the development of the crop to determine the evolution of the relative chlorophyll content (SPAD) and leaf area index (LAI) for better yield estimation. The obtained results showed that SPAD and LAI decreased significantly under drought stress, and leaf senescence had already started in the early vegetative stage. The amount of top dressing applied at V6 and V12 phenophases did not increase yield due to the low amount of rainfall. The 120 kg N ha-1 base fertiliser proved to be optimal. The suitability of SPAD and LAI for maize yield estimation was modelled by regression analysis. Results showed that the combined SPAD-LAI was suitable for yield prediction, and the correlation was strongest at the VT stage (R2 = 0.762).

Plant and Disease Recognition Based on PMF Pipeline Domain Adaptation Method: Using Bark Images as Meta-Dataset

Efficient image recognition is important in crop and forest management. However, it faces many challenges, such as the large number of plant species and diseases, the variability of plant appearance, and the scarcity of labeled data for training. To address this issue, we modified a SOTA Cross-Domain Few-shot Learning (CDFSL) method based on prototypical networks and attention mechanisms. We employed attention mechanisms to perform feature extraction and prototype generation by focusing on the most relevant parts of the images, then used prototypical networks to learn the prototype of each category and classify new instances. Finally, we demonstrated the effectiveness of the modified CDFSL method on several plant and disease recognition datasets. The results showed that the modified pipeline was able to recognize several cross-domain datasets using generic representations, and achieved up to 96.95% and 94.07% classification accuracy on datasets with the same and different domains, respectively. In addition, we visualized the experimental results, demonstrating the model's stable transfer capability between datasets and the model's high visual correlation with plant and disease biological characteristics. Moreover, by extending the classes of different semantics within the training dataset, our model can be generalized to other domains, which implies broad applicability.

Growth Monitoring and Yield Estimation of Maize Plant Using Unmanned Aerial Vehicle (UAV) in a Hilly Region

More than 66% of the Nepalese population has been actively dependent on agriculture for their day-to-day living. Maize is the largest cereal crop in Nepal, both in terms of production and cultivated area in the hilly and mountainous regions of Nepal. The traditional ground-based method for growth monitoring and yield estimation of maize plant is time consuming, especially when measuring large areas, and may not provide a comprehensive view of the entire crop. Estimation of yield can be performed using remote sensing technology such as Unmanned Aerial Vehicles (UAVs), which is a rapid method for large area examination, providing detailed data on plant growth and yield estimation. This research paper aims to explore the capability of UAVs for plant growth monitoring and yield estimation in mountainous terrain. A multi-rotor UAV with a multi-spectral camera was used to obtain canopy spectral information of maize in five different stages of the maize plant life cycle. The images taken from the UAV were processed to obtain the result of the orthomosaic and the Digital Surface Model (DSM). The crop yield was estimated using different parameters such as Plant Height, Vegetation Indices, and biomass. A relationship was established in each sub-plot which was further used to calculate the yield of an individual plot. The estimated yield obtained from the model was validated against the ground-measured yield through statistical tests. A comparison of the Normalized Difference Vegetation Index (NDVI) and the Green-Red Vegetation Index (GRVI) indicators of a Sentinel image was performed. GRVI was found to be the most important parameter and NDVI was found to be the least important parameter for yield determination besides their spatial resolution in a hilly region.

BotanicX-AI: Identification of Tomato Leaf Diseases Using an Explanation-Driven Deep-Learning Model

Early and accurate tomato disease detection using easily available leaf photos is essential for farmers and stakeholders as it help reduce yield loss due to possible disease epidemics. This paper aims to visually identify nine different infectious diseases (bacterial spot, early blight, Septoria leaf spot, late blight, leaf mold, two-spotted spider mite, mosaic virus, target spot, and yellow leaf curl virus) in tomato leaves in addition to healthy leaves. We implemented EfficientNetB5 with a tomato leaf disease (TLD) dataset without any segmentation, and the model achieved an average training accuracy of 99.84% ± 0.10%, average validation accuracy of 98.28% ± 0.20%, and average test accuracy of 99.07% ± 0.38% over 10 cross folds.The use of gradient-weighted class activation mapping (GradCAM) and local interpretable model-agnostic explanations are proposed to provide model interpretability, which is essential to predictive performance, helpful in building trust, and required for integration into agricultural practice.

Advantages in Using Colour Calibration for Orthophoto Reconstruction

UAVs are sensor platforms increasingly used in precision agriculture, especially for crop and environmental monitoring using photogrammetry. In this work, light drone flights were performed on three consecutive days (with different weather conditions) on an experimental agricultural field to evaluate the photogrammetric performances due to colour calibration. Thirty random reconstructions from the three days and six different areas of the field were performed. The results showed that calibrated orthophotos appeared greener and brighter than the uncalibrated ones, better representing the actual colours of the scene. Parameter reporting errors were always lower in the calibrated reconstructions and the other quantitative parameters were always lower in the non-calibrated ones, in particular, significant differences were observed in the percentage of camera stations on the total number of images and the reprojection error. The results obtained showed that it is possible to obtain better orthophotos, by means of a calibration algorithm, to rectify the atmospheric conditions that affect the image obtained. This proposed colour calibration protocol could be useful when integrated into robotic platforms and sensors for the exploration and monitoring of different environments.

Intelligent Classification of Japonica Rice Growth Duration (GD) Based on CapsNets

Rice cultivation in cold regions of China is mainly distributed in Heilongjiang Province, where the growing season of rice is susceptible to low temperature and cold damage. Choosing and planting rice varieties with suitable GD according to the accumulated temperate zone is an important measure to prevent low temperature and cold damage. However, the traditional identification method of rice GD requires lots of field investigations, which are time consuming and susceptible to environmental interference. Therefore, an efficient, accurate, and intelligent identification method is urgently needed. In response to this problem, we took seven rice varieties suitable for three accumulated temperature zones in Heilongjiang Province as the research objects, and we carried out research on the identification of japonica rice GD based on Raman spectroscopy and capsule neural networks (CapsNets). The data preprocessing stage used a variety of methods (signal.filtfilt, difference, segmentation, and superposition) to process Raman spectral data to complete the fusion of local features and global features and data dimension transformation. A CapsNets containing three neuron layers (one convolutional layer and two capsule layers) and a dynamic routing protocol was constructed and implemented in Python. After training 160 epochs on the CapsNets, the model achieved 89% and 93% accuracy on the training and test datasets, respectively. The results showed that Raman spectroscopy combined with CapsNets can provide an efficient and accurate intelligent identification method for the classification and identification of rice GD in Heilongjiang Province.

Accuracy Analysis of Three-Dimensional Modeling of a Multi-Level UAV without Control Points

Unmanned Aerial Vehicle (UAV) oblique photography technology has been applied more and more widely for the 3D reconstruction of real-scene models due to its high efficiency and low cost. However, there are many kinds of UAVs with different positioning methods, camera models, and resolutions. To evaluate the performance levels of different types of UAVs in terms of their application to 3D reconstruction, this study took a primary school as the research area and obtained image information through oblique photography of four UAVs of different levels at different flight altitudes. We then conducted a comparative analysis of the accuracy of their 3D reconstruction models. The results show that the 3D reconstruction model of M300RTK has the highest dimensional accuracy, with an error of about 1.1–1.4 m per kilometer, followed by M600Pro (1.5–3.6 m), Inspire2 (1.8–4.2 m), and Phantom4Pro (2.4–5.6 m), but the accuracy of the 3D reconstruction model was found to have no relationship with the flight altitude. At the same time, the resolution of the 3D reconstruction model improved as the flight altitude decreased and the image resolution of the PTZ camera increased. The 3D reconstruction model resolution of the M300RTK + P1 camera was the highest. For every 10 m decrease in flight altitude, the clarity of the 3D reconstruction model improved by 16.81%. The UAV flight time decreased as the UAV flying altitude increased, and the time required for 3D reconstruction of the model increased obviously as the number and resolution of photos increased.