基于残差收缩网络的遥感图像目标检测算法

doi:10.3778/j.issn.1002-8331.2109-0290

摘要/Abstract

摘要： 针对于遥感图像中背景复杂噪声多、小目标多且排布密集、目标尺度差异大等问题，提出了一种改进通道注意力与残差收缩网络的遥感图像目标检测算法。该算法借助卷积神经网络，以YOLOV3模型作为基础网络，选择Mosaic图像增强的方式进行数据预处理，采用深度残差收缩模块重构了特征提取网络，并结合通道注意力机制与组合池化构建空间金字塔池化融合层，采用CIOU进行定位损失计算，最终实现遥感图像目标检测。实验结果表明：改进算法相比于原算法的总体mAP由89.2%提升至92.2%，获得了更好的性能表现。

关键词: 通道注意力, 特征融合, 遥感图像, 残差收缩网络

Abstract: Aiming at the problems of complex background，more noise，dense arrangement of small targets and large difference of target scale in remote sensing images，a remote sensing image target detection algorithm based on improved channel attention and residual shrinkage network is proposed in this paper. The algorithm uses convolutional neural network，takes YOLOV3 model as the basic network，selects mosaic image enhancement for data preprocessing，reconstructs the feature extraction network by using the depth residual shrinkage module，constructs the spatial pyramid pooling fusion layer by combining the channel attention mechanism and combination pooling，calculates the positioning loss by using CIOU，and finally realizes the target detection of remote sensing image. Experimental results show that compared with the original algorithm，the overall map of the improved algorithm is improved from 89.2% to 92.2%，and better performance is obtained.

Key words: channel attention, feature fusion, remote sensing image, residual shrinkage network

高晔, 郭松宜, 厍向阳. 基于残差收缩网络的遥感图像目标检测算法[J]. 计算机工程与应用, 2022, 58(17): 93-100.

GAO Ye, GUO Songyi, SHE Xiangyang. Remote Sensing Image Target Detection Algorithm Based on Residual Shrinkage Network[J]. Computer Engineering and Applications, 2022, 58(17): 93-100.

参考文献

[1] 祝文韬，谢宝蓉，王琰，等.光学遥感图像中的飞机目标检测技术研究综述[J].计算机科学，2020，47（11）：165-171.
ZHU W T，XIE B R，WANG Y，et al.Survey on aircraft detection in optical remote sensing images[J].Computer Science，2020，47（11）：165-171.
[2] KIM T，PARK S R，KIM M G，et al.Tracking road centerlines from high resolution remote sensing images by least squares correlation matching[J].Photogrammetric Engineering and Remote Sensing，2004，70：1417-1422.
[3] BAI X，ZHANG H，ZHOU J.VHR object detection based on structural feature extraction and query expansion[J].IEEE Transactions on Geoscience & Remote Sensing，2014，52：6508-6520.
[4] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Columbus，OH，2014：580-587.
[5] GIRSHICK R.Fast R-CNN[C]//IEEE International Conference on Computer Vision.Washington：IEEE Computer Society，2015：1440-1448.
[6] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems.Cambridge，Massachusetts：MIT Press，2015：91-99.
[7] HE K，GKOXRI G，DOLLAR P，et al.Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision，2017.
[8] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//Proc of European Conference on Computer Vision-ECCV2016，2016：21-37.
[9] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition，Honolulu，2017：6517-6525.
[10] REDMON J，FARHADI A.YOLOv3：an incremental improvement[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recongnition，Washington DC，USA，2018：1-6.
[11] 李玉峰，顾曼璇，赵亮.采用改进 Faster R-CNN的遥感图像目标检测方法[J].信号处理，2020，36（8）：1363-1373.
LI Y F，GU M X，ZHAO L.Remote sensing image target detection method using improved Faster R-CNN[J].Journal of Signal Processing，2020，36（8）：1363-1373.
[12] 郑哲，雷琳，孙浩，等.FAGNet：基于MAFPN和GVR的遥感图像多尺度目标检测算法[J].计算机辅助设计与图形学学报，2021，33（6）：1-12.
ZHENG Z，LEI L，SUN H，et al.FAGNet：multi-scale object detection method in remote sensing images by combining MAFPN and GVR[J].Journal of Computer-Aided Design and Computer Graphics，2021，33（6）：1-12.
[13] 李红艳，李春庚，安居白，等.注意力机制改进卷积神经网络的遥感图像目标检测[J].中国图象图形学报，2019，24（8）：1400-1408．
LI H Y，LI C G，AN J B，et al.Attention mechanism improves CNN remote sensing image object detection[J].Journal of Image and Graphics，2019，24（8）：1400-1408.
[14] WOO S，PARK J，LEE J，et al.CBAM：convolutional block attention module[C]//Proceedings of 2018 European Conference on Computer Vision.Munich：Springer，2018：3-19.
[15] 吴湘宁，贺鹏，邓中港，等.陈苗一种基于注意力机制的小目标检测深度学习模型[J].计算机工程与科学，2021，43（1）：95-104.
WU X N，HE P，DENG Z G，et al.A deep learning model of small object detection based on attention mechanism[J].Computer Engineering ＆ Science，2021，43（1）：95-104.
[16] LIN T Y，DOLLAE P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：936-944.
[17] 董彪，熊风光，韩燮，等.徐清宇基于改进Yolo v3算法的遥感建筑物检测研究[J].计算机工程与应用，2020，56（18）：209-213.
DONG B，XIONG F G，HAN X，et al.Research on remote sensing building detection based on improved Yolo v3 algorithm[J].Computer Engineering and Applications，2020，56（18）：209-213.
[18] 成喆，吕京国，白颖奇，等.结合RPN网络与SSD算法的遥感影像目标检测算法[J].测绘科学，2021，46（4）：75-82.
CHENG Z，LV J G，BAI Y Q，et al.High-resolution remote sensing image object detection algorithm combining RPN network and SSD algorithm[J].Science of Surveying and Mapping，2021，46（4）：75-82.
[19] VAN ETTEN A.You only look twice：rapid multi-scale object detection in satellite imagery[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018.
[20] ZHAO M，ZHONG S，FU X，et al.Deep residual shrinkage networks for fault diagnosis[J].IEEE Transactions on Industrial Informatics，2020，16（7）：4681-4690.
[21] ZHENG Z H，WANG P，LIU W，et al.DistanceIoU loss：faster and better learning for bounding box regression[C]//AAAI Conference on Artificial Intelligence，New York，USA，2020：12993-13000.
[22] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.