Abstract To address the problems such as misdetection and omission of low-altitude UAV targets, the algorithmic model ASSM-YOLO for improving YOLOv8n is proposed. Firstly, a small target detection head is added and the original Neck structure is replaced using asymptotic feature pyramid network (AFPN), which asymptotically fuses low-level and high-level features. Second, the shuffle attention (SA) mechanism is introduced to enhance the perception of UAV targets. Again, the backbone network convolutional layer is replaced with space to depth convolution (SPD-Conv) to improve the feature loss problem in the convolution process. Finally, the loss function MPDIoU Loss is replaced to optimise the regression loss calculation. Experiments on the DUT-UAV dataset show that the ASSM-YOLO algorithm results in 92.5%, 72.2%, and 62.9% on the RmAP@0.5、RmAP@0.75 and RmAP@0.5:0.95 metrics, which are 5.9%, 8.3%, and 6.5% respectively compared to YOLOv8n, so significantly improves the detection accuracy of the UAV targets.
ZHANG Liguo,YUAN Yulin,JIN Mei, et al. Research on UAV Target Detection Algorithm Based on Improved YOLOv8n[J]. Acta Metrologica Sinica, 2024, 45(10): 1487-1493.
LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector ［C］//Proceedings of the European Conference on Computer Vision. Amsterdam: Springer, 2016: 21-37.
［17］
ZHANG H, ZHANG S. Shape-IoU: more accurate metric considering bounding box shape and scale ［J］. arXiv e-prints, 2023. DOI: 10.48550/arXiv. 2312.17663.
［3］
BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speed and accuracy of object detection ［C］ // Proceedings of European Conference on Computer Vision (ECCV). Glasgow, UK, 2020,10934.
［5］
WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors ［C］ // 2023 IEEE/ CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, BC, Canada, 2023, 7464-7475.
［7］
REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149.
WU F H, CUI J X, ZHANG N, et al. Detection of wheel surface defects based on improved YOLOv4 algorithm ［J］. Acta Metrologica Sinica, 2022, 43(11): 1404-1411.
［11］
TAN M, PANG R, Le Q V. EfficientDet: scalable and efficient object detection［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
［13］
HU J, SHEN L, SUN G. Squeeze-and-excitation networks ［C］ //2018 IEEE/CVF Conference on Com -puter Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018, 7132-7141.
［15］
HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design［C］// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021.
［6］
GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation ［J］. IEEE Computer Society, 2014,81.
REDMON J, FARHADI A. YOLOv3: an incremental improvement ［C］ // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Salt Lake, USA, 2018:1804.0276.
［4］
ZHU X, LYU S, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios ［C］ // 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada, 2021, 2778-2788.
［10］
YANG R, LI W, SHANG X, et al. KPE-YOLOv5: an improved small target detection algorithm based on YOLOv5 ［J］. Electronics, 2023, 12(4): 817-830.
［12］
YANG G, LEI J, ZHU Z, et al. AFPN: asymptotic feature pyramid network for object detection［C］// 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 2023.
［14］
WANG Q, WU B, ZHU P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks［C］// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
［16］
OUYANG D, HE S, ZHANG G, et al. Efficient multi-scale attention module with cross-spatial learning ［C］//ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).IEEE, 2023.
［18］
ZHAO J, ZHANG J, LI D, et al. Vision-based anti-uav detection and tracking ［J］. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(12): 25323-25334.
ZHANG L G, JIANG Y X, TIAN G J. Research on uav-to-ground vehicle target detection algorithm based on multi-scale fusion method ［J］. Acta Metrologica Sinica, 2021, 42(11): 1436-1442.
2024, Vol. 45 
