[1] [1] LIN T YMAIRE MBELONGIE Set al.Microsoft COCO:common objects in context［C］//European Conference on Computer Vision.Cham:Springer2014:740755.

[3] [3] HE K MGKIOXARI GDOLLR Pet al.Mask RCNN［C］//International Conference on Computer Vision.Venice:IEEE2017:29802988.

[4] [4] GIRSHICK R.Fast RCNN［C］//International Conference on Computer Vision.Santiago:IEEE2015:14401448.

[5] [5] REDMON JDIVVALA SGIRSHICK Ret al.You only look once:unifiedrealtime object detection［C］//Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE2016:779788.

[6] [6] LIU WANGUELOV DERHAN Det al.SSD:single shot MultiBox detector［C］//European Conference on Computer Vision.Amsterdam:Springer2016:2137.

[10] [10] KISANTAL MWOJNA ZMURAWSKI Jet al.Augmentation for small object detection［EB/OL］.(20190219)［20231120］.https://arxiv.org/abs/1902.07296.

[11] [11] ZHU X KLYU S CWANG Xet al.TPHYOLOv5:improved YOLOv5 based on Transformer prediction head for object detection on dronecaptured scenarios［C］// IEEE/CVF International Conference on Computer Vision Workshops.Montreal:IEEE2021:27782788.

[12] [12] VASWANI ASHAZEER NPARMAR Net al.Attention is all you need［J］.The 31st International Conference on Neural Information Processing Systems.Long Beach:ACM2017:60006010.

[13] [13] WOO SPARK JLEE J Yet al.CBAM:convolutional block attention module［C］//European Conference on Computer Vision.Cham:Springer2018:319.

[14] [14] HAN KWANG Y HTIAN Qet al.GhostNet:more features from cheap operations［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle:IEEE2020:15771586.

[17] [17] SUNKARA RLUO T.No more strided convolutions or pooling:a new CNN building block for lowresolution images and small objects［C］//European Conference on Machine Learning and Knowledge Discovery in Databases.Cham:Springer2022:443459.

[18] [18] HOU Q BZHOU D QFENG J S.Coordinate attention for efficient mobile network design［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville:IEEE2021:1370813717.

[19] [19] LIU Y CSHAO Z RTENG Y Yet al.NAM:normalizationbased attention module［EB/OL］.(20211124)［20231120］.https://arxiv.org/abs/2111.12419.

[20] [20] ZHANG X YZHOU X YLIN M Xet al.ShuffleNet:an extremely efficient convolutional neural network for mobile devices［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE 2018:68486856.

[21] [21] LI Y HYAO TPAN Y Wet al.Contextual Transformer networks for visual recognition［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence202245(2):14891500.

[22] [22] HE K MZHANG X YREN S Qet al.Deep residual learning for image recognition［C］//Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE 2016:770778.

[24] [24] ZHU P FWEN L YDU D Qet al.Vision meets drones:pastpresent and future［EB/OL］.(20200716)［20231120］.https://arxiv.org/pdf/2001.06303v2.

[25] [25] REDMON JFARHADI A.YOLOv3:an incremental improvement［EB/OL］.(20180408)［20231120］.https://arxiv.org/abs/1804.02767.

[26] [26] 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］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE2023:74647475.

[27] [27] LI C YLI L LJIANG H Let al.YOLOv6:a singlestage object detection framework for industrial applications［EB/OL］.(20220907)［20231120］.https://arxiv.org/abs/2209.02976.