[2] [2] REDMON JDIVVALA SGIRSHICK Ret al.You only look once:unifiedreal-time object detection ［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2016:779-788.

[3] [3] REDMON JFARHADI A.YOLO9000:betterfaster stronger［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2017:7263-7271.

[4] [4] REDMON JFARHADI A.YOLOv3:an incremental improvement［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2018:1-6.

[5] [5] BOCHKOVSKIY AWANG C YLIAO H Y M.YOLOv4:optimal speed and accuracy of object detection［J］.arXiv:2004.109342020.

[7] [7] LIU S THUANG DWANG Y H.Learning spatial fusion for single-shot object detection［J］.arXiv:1911.09516 2019.

[9] [9] LONG XDENG K PWANG G Zet al.PP-YOLO:an effective and efficient implementation of object detector［J］.arXiv:2007.120992020.

[17] [17] WANG C YLIAO H Y MWU Y Het al.CSPNet:a new backbone that can enhance learning capability of CNN［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops 2020:390-391.

[18] [18] WOO SPARK JLEE J Yet al.CBAM:convolutional block attention module［C］//European Conference on Computer Vision2018:3-19.

[19] [19] LIN T YDOLLR PGIRSHICK Ret al.Feature pyramid networks for object detection［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2017:2117-2125.

[20] [20] LIU SQI LQIN H Fet al.Path aggregation network for instance segmentation［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2018:8759-8768.

[21] [21] LIN T YGOYAL PGIRSHICK Ret al.Focal loss for dense object detection［C］//Proceedings of the IEEE International Conference on Computer Vision2017:2980-2988.