Abstract: Traditional method of remote sensing image obJect detection has the disadvantages of high time complexity and low precision.How to detect specific targets in remote sensing images quickly and accurately has become a hot research topic.In order to solve this problem,this paper improves the YOLO-V2 obJect detection algorithm,reduces the convolution layers and dimension,and combined with the ideal of feature pyramid to increase the detection features’ scale,so as to achieve the purpose of improving detection accuracy.At the same time,a general processing framework of remote sensing image obJect detection algorithm based on deep learning is presented to solve the problem that large remote sensing images cannot be directly processed.Comparison experiments on the DOTA dataset show that the improved YOLO-V2 algorithm has better accuracy and recall rate in 15 categories than the YOLO-V2 algorithm,and the mAP value is increased by 0.12.In terms of time complexity,it is slightly lower than the YOLO-V2 algorithm.Specifically,on 416×416 image patches,the detection time of the improved YOLO-V2 algorithm is reduced by 0.1 ms compared to the YOLO-V2 algorithm.

Key words: Deep learning, Feature pyramid, Multiscale, ObJect detection, Remote sensing image, YOLO-V2