改进YOLOv5的遥感影像目标检测算法

doi:10.3778/j.issn.1002-8331.2301-0220

摘要/Abstract

摘要： 针对遥感影像目标检测中复杂背景的干扰，小目标检测效果差等问题，提出一种改进YOLOv5（you only look once v5）的遥感影像目标检测模型。针对卷积神经网络下采样导致的特征图中包含的小目标信息较少或消失的问题，引入特征复用以增加特征图中的小目标特征信息；在特征融合阶段时使用EMFFN（efficient multi-scale feature fusion network）的特征融合网络代替原有的PANet（path aggregation network），通过添加跳跃连接以及跨层连接高效融合不同尺度的特征图信息；为了应对复杂背景带来的检测效果变差的问题，提出了一种包含通道与像素的双向特征注意力机制（bidirectional feature attention mechanism，BFAM），以提高模型在复杂背景下的检测效果。实验结果表明，改进后的YOLOv5模型在DIOR数据集与RSOD数据集中分别取得了87.8%和96.6%的检测精度，相较原算法分别提高5.2和1.6个百分点，有效提高了复杂背景下的小目标检测精度。

关键词: 遥感影像, 深度学习, 目标检测, YOLOv5, 注意力机制, 多尺度特征融合, DenseDarkNet模型

Abstract: An improved YOLOv5 is proposed to address complex backgrounds and small objects missing detection in remote sensing images. Firstly, considering that the high-level feature map contains little small object information caused by down-sampling of convolutional neural networks, low-level feature is reused to increase the small target feature information. The EMFFN（efficient multi-scale feature fusion network） is used in the feature fusion stage instead of the original PANet（path aggregation network） to efficiently fuse the feature map information at different scales by adding jump connections and skip connections. Finally, a bidirectional feature attention mechanism（BFAM） including channels attention and pixel attention is designed to improve detection in complex background. To evaluate the proposed model, this paper uses two remote sensing image datasets, DIOR and RSOD. The experimental results show that the improved YOLOv5 model achieves 87.8% and 96.6% detection accuracy in the DIOR and RSOD datasets respectively, which is 5.2 and 1.6?percentage points better than the original YOLOv5 algorithm, effectively improving the detection accuracy of small targets in complex backgrounds.

Key words: remote sensing images, deep learning, object detection, YOLOv5, attention mechanism, multi-scale feature fusion, DenseDarkNet model

杨晨, 佘璐, 杨璐, 冯自贤. 改进YOLOv5的遥感影像目标检测算法[J]. 计算机工程与应用, 2023, 59(15): 76-86.

YANG Chen, SHE Lu, YANG Lu, FENG Zixian. Improved YOLOv5 Object Detection Algorithm for Remote Sensing Images[J]. Computer Engineering and Applications, 2023, 59(15): 76-86.

参考文献

[1] 张朕通，单玉刚，袁杰.联合多尺度和注意力机制的遥感影像检测[J].计算机工程与应用，2021，57（9）：212-216.
ZHANG Z T，SHAN Y G，YUAN J.Remote sensing image detection algorithm combining multi-scale and attention mechanism[J].Computer Engineering and Applications，2021，57（9）：212-216.
[2] 高宇歌，杨海涛，王晋宇，等.联合知识与CNN的遥感影像目标检测研究综述[J].计算机工程与应用，2021，57（18）：65-74.
GAO Y G，YANG H T，WANG J Y，et al.Review of remote sensing image target detection research combining knowledge and CNN[J].Computer Engineering and Applications，2021，57（18）：65-74.
[3] SADGROVE E J，FALZON G，MIRON D，et al.Real-time object detection in agricultural/remote environments using the multiple-expert colour feature extreme learning machine（MEC-ELM）[J].Computers in Industy，2018，98：183-191.
[4] KUSSUL N，LAVRENIUK M，SKAKUN S，et al.Deep learning classification of land cover and crop types using remote sensing data[J].IEEE Geoscience and Remote Sensing Letters，2017：778-782.
[5] 张菁，吴鑫嘉，赵晓蕾，等.全局关系注意力引导场景约束的高分辨率遥感影像目标检测[J].电子与信息学报，2022，44（8）：2924-2931.
ZHANG J，WU X J，ZHAO X L，et al.Scene constrained object detection method in high-resolution remote sensing images by relation-aware global attention[J].Journal of Electronics & Information Technology，2022，44（8）：2924-2931.
[6] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[7] GIRSHICK R.Fast R-CNN[C]//Procceedings of the 2015 IEEE International Conference on Computer Vision，2015：1440-1448.
[8] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（6）：1137-1149.
[9] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision，2016：21-37.
[10] LIU Y，GOYAL P，GIRSHICK R.Focal loss for dense object detection[C]//Proceedings of IEEE International Conference on Computer Vision，2017：2980-2988.
[11] REDOMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[12] REDMON J，FARHADI A.Yolo9000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：6517-6525.
[13] JOSEPH R，ALI F.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[14] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.Yolov4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[15] 王一旭，肖小玲，王鹏飞，等.改进YOLOv5s的小目标烟雾火焰检测算法[J].计算机工程与应用，2023，59（1）：72-81.
   WANG Y X，XIAO X L，WANG P F，et al.Improved YOLOv5s small target smoke and fire detection algorithm[J].Computer Engineering and Applications，2023，59（1）：72-81.
[16] 刘春磊，陈天恩，王聪，等.小样本目标检测研究综述[J].计算机科学与探索，2023，17（1）：53-73.
   LIU C L，CHEN T N，WANG C，et al.Survey of few-shot object detection[J].Journal of Frontiers of Computer Science and Technology，2023，17（1）：53-73.
[17] 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 image[J].Computer Engineering and Applications，2021，   57（20）：133-141.
[18] 牛浩青，欧鸥，饶姗姗，等.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 H Q，OU O，RAO S S，et al.Small object detection method based on improved YOLOv3 in remote sensing image[J].Computer Engineering and Applications，2022，   58（13）：241-248.
[19] 李小军，邓月明，陈正浩，等.改进YOLOv5的机场跑道异物目标检测算法[J].计算机工程与应用，2023，59（2）：202-211.
   LI X J，DENG Y M，CHEN Z H，et al.Improved YOLOv5’s foreign object debris detection algorithm for airport runways[J].Computer Engineering and Applications，2023，59（2）：202-211.
[20] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：8759-8768.
[21] HUANG G，LIU Z，LAURENS V，et al.Densely connected convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：2261-2269.
[22] 宋谱怡，陈红，苟浩波.改进YOLOv5s的无人机目标检测算法[J].计算机工程与应用，2023，59（1）：108-116.
SONG P Y，CHEN H，GOU H B.Improving UAV object detection algorithm for YOLOv5s[J].Computer Engineering and Applications，2023，59（1）：108-116.
[23] 王剑哲，吴秦.坐标注意力特征金字塔的显著性目标检测算法[J].计算机科学与探索，2023，17（1）：154-165.
WANG J Z，WU Q.Salient object detection based on coordinate attention feature pyramid[J].Journal of Frontiers of Computer Science and Technology，2023，17（1）：154-165.
[24] WOO S，PARK J，LEE J，et al.CBAM：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision，2018.
[25] LIU Y，SHAO Z，HOFFMANN N.Global attention mechanism：retain information to enhance channel-spatial interactions[J].arXiv：2112.05561，2021.
[26] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision & Pattern Recognition.Piscataway：IEEE Computer Society，2016：770-778.
[27] 王林，张文卓.一种融合注意力机制与上下文信息的交通标志检测方法[J].计算机测量与控制，2022，30（3）：54-59.
   WANG L，ZHANG W Z.A traffic sign detection based on attentional mechanism and contextual information[J].Computer Measurement & Control，2022，30（3）：54-59.
[28] 陈欣，万敏杰，马超，等.采用多尺度特征融合SSD的遥感图像小目标检测[J].光学精密工程，2021（11）：29.
   CHEN X，WAN M J，MA C，et al.Recognition of small targets in remote sensing image using multi-scale feature fusion-based shot multi-box detector[J].Optics and Precision Engineering，2021（11）：29.
[29] HU J，SHEN L，ALBANIE S，et al.Squeeze and excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42，2011-2023.
[30] 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，2021.
[31] ZHOU L，ZHENG C，YAN H，et al.RepDarkNet：a multi-branched detector for small-target detection in remote sensing images[J].ISPRS International Journal of Geo-Information，2022，11（3）：158.