Foxtail Millet Ear Detection Method Based on Attention Mechanism and Improved YOLOv5

A lightweight network for improving wheat ears detection and counting based on YOLOv5s

Introduction

Recognizing wheat ears plays a crucial role in predicting wheat yield. Employing deep learning methods for wheat ears identification is the mainstream method in current research and applications. However, such methods still face challenges, such as high computational parameter volume, large model weights, and slow processing speeds, making it difficult to apply them for real-time identification tasks on limited hardware resources in the wheat field. Therefore, exploring lightweight wheat ears detection methods for real-time recognition holds significant importance.

Methods

This study proposes a lightweight method for detecting and counting wheat ears based on YOLOv5s. It utilizes the ShuffleNetV2 lightweight convolutional neural network to optimize the YOLOv5s model by reducing the number of parameters and simplifying the complexity of the calculation processes. In addition, a lightweight upsampling operator content-aware reassembly of features is introduced in the feature pyramid structure to eliminate the impact of the lightweight process on the model detection performance. This approach aims to improve the spatial resolution of the feature images, enhance the effectiveness of the perceptual field, and reduce information loss. Finally, by introducing the dynamic target detection head, the shape of the detection head and the feature extraction strategy can be dynamically adjusted, and the detection accuracy can be improved when encountering wheat ears with large-scale changes, diverse shapes, or significant orientation variations.

Results and discussion

This study uses the global wheat head detection dataset and incorporates the local experimental dataset to improve the robustness and generalization of the proposed model. The weight, FLOPs and mAP of this model are 2.9 MB, 2.5 * 109 and 94.8%, respectively. The linear fitting determination coefficients R2 for the model test result and actual value of global wheat head detection dataset and local experimental Site are 0.94 and 0.97, respectively. The improved lightweight model can better meet the requirements of precision wheat ears counting and play an important role in embedded systems, mobile devices, or other hardware systems with limited computing resources.

YOLOv5s-DSD: An Improved Aerial Image Detection Algorithm Based on YOLOv5s

Due to the challenges of small detection targets, dense target distribution, and complex backgrounds in aerial images, existing object detection algorithms perform poorly in aerial image detection tasks. To address these issues, this paper proposes an improved algorithm called YOLOv5s-DSD based on YOLOv5s. Specifically, the SPDA-C3 structure is proposed and used to reduce information loss while focusing on useful features, effectively tackling the challenges of small detection targets and complex backgrounds. The novel decoupled head structure, Res-DHead, is introduced, along with an additional small object detection head, further improving the network's performance in detecting small objects. The original NMS is replaced by Soft-NMS-CIOU to address the issue of neighboring box suppression caused by dense object distribution. Finally, extensive ablation experiments and comparative tests are conducted on the VisDrone2019 dataset, and the results demonstrate that YOLOv5s-DSD outperforms current state-of-the-art object detection models in aerial image detection tasks. The proposed improved algorithm achieves a significant improvement compared with the original algorithm, with an increase of 17.4% in mAP@0.5 and 16.4% in mAP@0.5:0.95, validating the superiority of the proposed improvements.

YOLOv5s-Fog: An Improved Model Based on YOLOv5s for Object Detection in Foggy Weather Scenarios

In foggy weather scenarios, the scattering and absorption of light by water droplets and particulate matter cause object features in images to become blurred or lost, presenting a significant challenge for target detection in autonomous driving vehicles. To address this issue, this study proposes a foggy weather detection method based on the YOLOv5s framework, named YOLOv5s-Fog. The model enhances the feature extraction and expression capabilities of YOLOv5s by introducing a novel target detection layer called SwinFocus. Additionally, the decoupled head is incorporated into the model, and the conventional non-maximum suppression method is replaced with Soft-NMS. The experimental results demonstrate that these improvements effectively enhance the detection performance for blurry objects and small targets in foggy weather conditions. Compared to the baseline model, YOLOv5s, YOLOv5s-Fog achieves a 5.4% increase in mAP on the RTTS dataset, reaching 73.4%. This method provides technical support for rapid and accurate target detection in adverse weather conditions, such as foggy weather, for autonomous driving vehicles.

Blind Detection of Broadband Signal Based on Weighted Bi-Directional Feature Pyramid Network

With the development of wireless technology, signals propagating in space are easy to mix, so blind detection of communication signals has become a very practical and challenging problem. In this paper, we propose a blind detection method for broadband signals based on a weighted bi-directional feature pyramid network (BiFPN). The method can quickly perform detection and automatic modulation identification (AMC) on time-domain aliased signals in broadband data. Firstly, the method performs a time-frequency analysis on the received signals and extracts the normalized time-frequency images and the corresponding labels by short-time Fourier transform (STFT). Secondly, we build a target detection model based on YOLOv5 for time-domain mixed signals in broadband data and learn the features of the time-frequency distribution image dataset of broadband signals, which achieves the purpose of training the model. The main improvements of the algorithm are as follows: (1) a weighted bi-directional feature pyramid network is used to achieve a simple and fast multi-scale feature fusion approach to improve the detection probability; (2) the Efficient-Intersection over Union (EIOU) loss function is introduced to achieve high accuracy signal detection in a low Signal-Noise Ratio (SNR) environment. Finally, the time-frequency images are detected by an improved deep network model to complete the blind detection of time-domain mixed signals. The simulation results show that the method can effectively detect the continuous and burst signals in the broadband communication signal data and identify their modulation types.

A Lightweight Algorithm for Insulator Target Detection and Defect Identification

The accuracy of insulators and their defect identification by UAVs (unmanned aerial vehicles) in transmission-line inspection needs to be further improved, and the model size of the detection algorithm is significantly reduced to make it more suitable for edge-end deployment. In this paper, the algorithm uses a lightweight GhostNet module to reconstruct the backbone feature extraction network of the YOLOv4 model and employs depthwise separable convolution in the feature fusion layer. The model is lighter on the premise of ensuring the effect of image information extraction. Meanwhile, the ECA-Net channel attention mechanism is embedded into the feature extraction layer and PANet (Path Aggregation Network) to improve the recognition accuracy of the model for small targets. The experimental results show that the size of the improved model is reduced from 244 MB to 42 MB, which is only 17.3% of the original model. At the same time, the mAp of the improved model is 0.77% higher than that of the original model, reaching 95.4%. Moreover, the mAP compared with YOLOv5-s and YOLOX-s, respectively, is improved by 1.98% and 1.29%. Finally, the improved model is deployed into Jetson Xavier NX and run at a speed of 8.8 FPS, which is 4.3 FPS faster than the original model.