Unmanned aerial vehicle (UAV) image detection algorithms are critical in performing military countermeasures and disaster search and rescue. The state-of-the-art object detection algorithm known as you only look once (YOLO) is widely used for detecting UAV images. However, it faces challenges such as high floating-point operations (FLOPs), redundant parameters, slow inference speed, and poor performance in detecting small objects. To address the above issues, an improved, lightweight, real-time detection algorithm was proposed based on the edge computing platform for UAV images. In the presented method, MobileNetV3 was used as the YOLOv5 backbone network to reduce the numbers of parameters and FLOPs. To enhance the feature extraction ability of MobileNetV3, the efficient channel attention (ECA) attention mechanism was introduced into MobileNetV3. Furthermore, in order to improve the detection ability for small objects, an extra prediction head was introduced into the neck structure, and two kinds of neck structures with different parameter scales were designed to meet the requirements of different embedded devices. Finally, the FocalEIoU loss function was introduced into YOLOv5 to accelerate bounding box regression and improve the localization accuracy of the algorithm. To validate the performance of the proposed improved algorithm, we compared our algorithm with other algorithms in the VisDrone-Det2021 dataset. The results showed that compared with YOLOv5s, MELF-YOLOv5-S achieved a 51.4% reduction in the number of parameters and a 38.6% decrease in the number of FLOPs. MELF-YOLOv5-L had 87.4% and 47.4% fewer parameters and FLOPs, respectively, and achieved higher detection accuracy than YOLOv5l.

A lightweight target detection algorithm, MobileNetv3 extended neck YOLOv5 (MEN-YOLOv5) is proposed in this paper to simplify the complex structure of the YOLOv5 target detection network, reduce the number of model parameters, and improve detection accuracy of small targets. Firstly, to reduce the number of parameters, the backbone network YOLOv5 is re-constructed using the MobileNetv3 depthwise separable convolution. Secondly, in accordance with the characteristics of the air-to-ground detected targets and the YOLOv5 algorithm, the layers are extended to the shallow-layer on the basis of the Neck network structure and more shallow feature information are fused, which makes the developed algorithm have a smaller receptive field and improves accuracy of detection of small targets. Finally, channel parameters are re-designed and the Neck network structure is rebuilt to avoid the dramatic increase in the number of parameters. As a result, the number of parameters in the entire network structure are compressed to the maximum extent possible to produce lightweight target detection models. The effectiveness of the proposed algorithm is verified by experiments with the VisDrone-DET2019 dataset and the experimental results show that, compared with YOLOv5l and YOLOv5x, the numbers of parameters of MEN-YOLOv5-L reduce by 86.8% and 92.98%, and floating point operations (FLOPs) decrease by 46.18% and 71.58%, and mAP50 values increase by 7.18% and 5.78%, respectively. MEN-YOLOv5-S has 52.9% and 30.8% lower number of parameters and FLOPs, respectively, and 2.5% higher mAP50 than YOLOv5s.