[2] [2] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］∥Proceedings of 2014 IEEE International Conferenceon Computer Vision and Pattern Recognition.Columbus,OH:IEEE,2014:580-587．

[3] [3] Girshick R. Fast R-CNN［C］∥Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago:IEEE,2015:1440-1448.

[7] [7] Fariborz Ghorbani, Hamid Ebadi, Amin Sedaghat. Geospatial target detection from high-resolution remote-sensing images based on PIIFD descriptor and salient regions［J］. Journal of the Indian Society of Remote Sensing,2019,47(5):879-891.

[8] [8] Changqing Cao, Jin Wu, Xiaodong Zeng, et al. Rseearch on airplane and ship detection of aerial remote sensing images based on convolutional neural network［J］. Sensors,2020,20(17):4696.

[9] [9] Yuelei Xu, Mingming Zhu, Peng Xin, et al. Rapid airplane detection in remote sensing images based on multilayers feature fusion in fully convolutional neural networks［J］. Sensors,2018,18(7):2335.

[10] [10] Redmon J, Farhadi A. YOLO9000:better,faster,stronger［EB/OL］. arXiv: 1612.08242v1［cs.CV］.(2016-12)/［2020-12］. https:∥pjreddie.com/yolo9000/.

[11] [11] Bochkovskiy A, Wang C Y, Liao H Y. YOLOv4:optimal speed and accuracy of object detection［EB/OL］. arXiv: 2004.10934v1［cs.CV］. (2020-04)/［2020-12］. https:∥arxiv.org/abs/2004.10934.

[12] [12] Rrdmon J, Farhadi A. YOLO v3: an incremental improvement［EB/OL］ (2018-11)/［2020-12］. http:∥arxiv.org/pdf/1804.02767v1.pdf.

[13] [13] He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916．

[14] [14] Diganta M. Mish: A self regularized nonmonotonic neural activation function［EB/OL］.arXiv:1908.08681.(2019-04)/［2020-12］. https:∥arxiv.org/pdf/1908.08681.pdf.