改进YOLOv3的遥感影像小目标检测方法

doi:10.3778/j.issn.1002-8331.2203-0065

摘要/Abstract

摘要： 针对当前目标检测任务中对小目标检测识别率低，漏检率高的问题，提出一种基于门控通道注意力机制（EGCA）和自适应上采样模块的改进YOLOv3算法。该算法采用DarkNet-53作为主干网络进行图片基础特征提取；引入自适应上采样模块对低分辨率卷积特征图进行扩张，有效增强了不同尺度卷积特征图的融合效果；在三个尺度通道输出预测结果之前分别加入EGCA注意力机制以提高网络对小目标的特征表达和检测能力。将改进的算法在公开数据集RSOD（remote sensing object detection）上进行实验，小目标检测精度提升了8.2个百分点，最为显著，平均精度AP值达到56.3%，较原算法提升了7.9个百分点。实验结果表明，改进的算法相比于传统YOLOv3算法和其他算法拥有更好的小目标检测能力。

关键词: 小目标检测, YOLOv3算法, 注意力机制, 上采样

Abstract: To solve the problems of low recognition rate and high miss rate of small object detection in the current target detection task, an improved YOLOv3 algorithm based on gated channel attention mechanism（EGCA） and adaptive upsampling module is proposed. Firstly, darknet-53 is used as the backbone network for image basic feature extraction. Secondly, the adaptive upsampling module is introduced to expand the low-resolution convolution feature map, which effectively enhances the fusion effect of different scale convolution feature map. Finally, EGCA attention mechanism is added before the three scale channels output the prediction results to improve the feature expression and detection ability of the network to small objects. The improved algorithm is tested on the public data set RSOD（remote sensing object detection）, the accuracy of small object detection is improved by 8.2 percentage points, which is the most significant. The average accuracy AP value reaches 56.3%, which is 7.9 percentage points higher than the original algorithm. Experimental results show that the improved algorithm has better small object detection ability than the traditional YOLOv3 algorithm and other algorithms.

Key words: small object detection, YOLOv3 algorithm, channel attention mechanism, upsampling

牛浩青, 欧鸥, 饶姗姗, 马万民. 改进YOLOv3的遥感影像小目标检测方法[J]. 计算机工程与应用, 2022, 58(13): 241-248.

NIU Haoqing, OU Ou, RAO Shanshan, MA Wanmin. Small Object Detection Method Based on Improved YOLOv3 in Remote Sensing Image[J]. Computer Engineering and Applications, 2022, 58(13): 241-248.

参考文献

[1] XUE Z，CHEN W，LI J.Enhancement and fusion of multi-scale feature maps for small object detection[C]//Proceedings of the 39th Chinese Control Conference，2020：7212-7217.
[2] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：Unified，real-time object detection[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington DC：IEEE Computer Society，2016：779-788.
[3] REDMON J，FARHADI A.YOLO9000：Better，faster，stronger[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington DC：IEEE Computer Society，2017：7263-7271.
[4] REDMON J，FARHADI A.YOLOv3：An incremental improvement[EB/OL].（2018-04-08）[2021-12-06].https：//arxiv.org/pdf/1804.02767.pdf.
[5] LIU W，ANGUELOV D，ERHAN，D，et al.SSD：Single shot multibox detector[C]//Proceedings of 14th European Conference on Computer Vision.Cham：Springer，2016：21-37.
[6] GIRSHICK R.Fast R-CNN[EB/OL].（2015-09-27）[2021-12-06].https：//arxiv.org/pdf/1504.08083.pdf.
[7] REN S Q，HE K M，GRISHICK R，et al.Faster R-CNN：Towards real-time object detection with region proposal networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.Cambridge，MA：MIT Press，2015：21-37.
[8] 王建军，魏江，梅少辉，等.面向遥感图像小目标检测的改进YOLOv3算法[J].计算机工程与应用，2021，57（20）：133-141.
WANG J J，WEI J，MEI S H，et al.Improved YOLOv3 for small object detection in remote sensing images[J].Computer Engineering and Applications，2021，57（20）：133-141.
[9] FANG P C，SHI Y J.Small object detection using context information fusion in Faster R-CNN[C]//Proceedings of the 4th IEEE International Conference on Computer and Communications.Piscataway，NJ：IEEE Press，2018：1537-1540.
[10] 侯涛，蒋瑜.改进YOLOv4在遥感飞机目标检测中的应用研究[J].计算机工程与应用，2021，57（12）：224-230.
HOU T，JIANG Y.Application research of improved YOLOv4 in remote sensing aircraft target detection[J].Computer Engineering and Applications，2021，57（12）：224-230.
[11] 李成豪，张静，胡莉，等.基于多尺度感受野融合的小目标检测算法[J/OL].计算机工程与应用：1-9（2021-04-20）[2021-12-06].http：//kns.cnki.net/kcms/detail/11.2127.tp.
20210420.1358.074.html.
LI C H，ZHANG J，HU L，et al.Small object detection algorithm based on multiscale receptive field fusion[J/OL].Computer Engineering and Applications：1-9（2021-04-20）[2021-12-06].http：//kns.cnki.net/kcms/detail/11.2127.tp.
20210420.1358.074.html.
[12] 赵鹏飞，谢林柏，彭力.融合注意力机制的深层次小目标检测算法[J].计算机科学与探索，2022，16（4）：927-937.
ZHAO P F，XIE L B，PENG L.Deep small object detection algorithm integrating attention mechanism[J].Journal of Frontiers of Computer Science and Technology，2022，16（4）：927-937.
[13] LIN T Y，DOLLAR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[14] HU J，LI S，ALBANIE S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[15] WOO S，PARK J，LEE J Y，et al.Cbam：Convolutional block attention module[C]//Proceedings of the 16th European Conference on Computer Vision.Cham：Springer，2018：3-19.
[16] WANG Q L，WU B G，ZHU P F，et al.ECA-Net：Efficient channel attention for deep convolutional neural networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway，NJ：IEEE Press，2020.
[17] LIN M，CHEN Q，YAN S C.Network in network[EB/OL].（2013-12-16）[2021-12-06].https：//arxiv.org/abs/1312.4400.
[18] GAUTHIER J.Conditional generative adversarial nets for convolutional face generation[J].Class Project for Stanford CS231N：Convolutional Neural Networks for Visual Recognition，2014（5）：2.
[19] LONG Y，GONG Y P，XIAO Z F，et al.Accurate object localization in remote sensing images based on convolutional neural networks[J].IEEE Transactions on Geoscience and Remote Sensing，2017，55（5）：2486-2498.