基于DSM-YOLO v5的无人机航拍图像目标检测

doi:10.3778/j.issn.1002-8331.2302-0324

摘要/Abstract

摘要： 针对传统无人机航拍图像目标检测算法存在漏检率高、检测成功率低、模型体积大等问题，提出一种新的基于深度可分离多头网络结构的目标检测方法DSM-YOLO v5（depthwise separable multiplex YOLO v5）。通过在YOLO v5网络结构上增加一个尺寸为160×160的小目标检测头，并将其与高层网络进行残差连接，以提升小目标检测能力，同时在Conv模块中引入深度可分离卷积算法，将其中的普通卷积替换为深度可分离卷积，能有效减少网络的参数量，降低模型体积。实验结果表明，基于DSM-YOLO v5网络结构的目标检测的mAP@0.5为36.8%，较YOLO v5s提高3.6个百分点，参数量和模型体积较YOLO v5s整体下降21.1%和19.7%，能够有效地应用于无人机航拍图像目标检测任务。

关键词: DSM-YOLO v5, 目标检测, 深度可分离, YOLO v5, 无人机图像

Abstract: Aiming at the problems of high missed detection rate, low detection success rate and large model size in traditional UAV（unmanned aerial vehicle） aerial image target detection algorithms, a new target detection method based on depthwise separable multiplex networks structure, DSM-YOLO v5（depthwise separable multiplex YOLO v5） is proposed. By adding a small target detection head with a size of 160×160 to the YOLO v5 network structure and performing residual connections with the high-level network to improve the detection ability of small objects. At the same time, the depthwise separable convolution algorithm is introduced in the Conv module, replacing ordinary convolution with depthwise separable convolution, which can effectively reduce the number of network parameters and reduce the model size. The experimental results show that the mAP@0.5 of target detection based on DSM-YOLO v5 network structure is 36.8%, which is 3.6 percentage points higher than that of YOLO v5s. The parameter volume and model volume are reduced by 21.1% and 19.7% respectively compared with YOLO v5s, which can be effectively applied to UAV aerial image target detection tasks.

Key words: DSM-YOLO v5, target detection, depthwise separable, YOLO v5, unmanned aerial vehicle（UAV） image

陈卫彪, 贾小军, 朱响斌, 冉二飞, 谢昊. 基于DSM-YOLO v5的无人机航拍图像目标检测[J]. 计算机工程与应用, 2023, 59(18): 226-233.

CHEN Weibiao, JIA Xiaojun, ZHU Xiangbin, RAN Erfei, XIE Hao. Target Detection for UAV Image Based on DSM-YOLO v5[J]. Computer Engineering and Applications, 2023, 59(18): 226-233.

参考文献

[1] YALCIN H，HEBERT M，COLLINS R，et al.A flow-based approach to vehicle detection and background mosaicking in airborne video[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition（CVPR’05），2005：1202.
[2] MEI X，LING H B.Robust visual tracking and vehicle classification via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2011，33（11）：2259-2272.
[3] REDMON 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.
[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，2014：580-587.
[5] GIRSHICK R.Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago：IEEE，2015：1440-1448.
[6] REN S，HE K，GIRSHICK R，et al.Faster RCNN：towards real-time object detection with region proposal networks[C]//Proceedings of Advances in Neural Information Processing Systems，2015：91-99.
[7] DAI J，LI Y，HE K，et al.R-FCN：object detection via region-based fully convolutional networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems，2016：379-387.
[8] 张瑞倩，邵振峰，Aleksei Portnov，等.多尺度空洞卷积的无人机影像目标检测方法[J].武汉大学学报（信息科学版），2020，45（6）：895-903.
ZHANG R Q，SHAO Z F，ALEKSEI P，et al.Multi-scale dilated convolutional neural network for object detection in UAV images[J].Geomatics and Information Science of Wuhan University，2020，45（6）：895-903.
[9] 陈旭，彭冬亮，谷雨.基于改进YOLOv5s无人机图像实时目标检测[J].光电工程，2022，49（3）：69-81.
CHEN X，PENG D L，GU Y.Real-time object detection for UAV images based on improved YOLOv5s[J].Opto-Electronic Engineering，2022，49（3）：69-81.
[10] 韩玉洁，曹杰，刘琨，等.基于改进YOLO的无人机对地多目标检测[J].电子测量技术，2020，43（21）：19-24.
HAN Y J，CAO J，LIU K，et al.UAV ground multi-target detection based on improved YOLO[J].Electronic Measurement Technology，2020，43（21）：19-24.
[11] 刘鑫，黄进，杨涛，等.改进CenterNet的无人机小目标捕获检测方法[J].计算机工程与应用，2022，58（14）：96-104.
LIU X，HUANG J，YANG T，et al.Improved small object detection for UAV acquisition based on CenterNet[J].Computer Engineering and Applications，2022，58（14）：96-104.
[12] 王浩雪，曹杰，邱诚，等.基于改进YOLOv4的航拍图像多目标检测方法[J].电光与控制，2022，29（5）：23-27.
WANG H X，CAO J，QIU C，et al.Multi-target detection method of aerial images based on improved YOLOv4 algorithm[J].Electronics Optics & Control，2022，29（5）：23-27.
[13] 王胜科，任鹏飞，吕昕，等.基于中心点和双重注意力机制的无人机高分辨率图像小目标检测算法[J].应用科学学报，2021，39（4）：650-659.
WANG S K，REN P F，Lü X，et al.Small target detection algorithm of UAV high resolution image based on center point and dual attention mechanism[J].Journal of Applied Sciences，2021，39（4）：650-659.
[14] ZHU X，LYU S C，WANG X，et al.TPH-YOLOv5：improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2021：2778-2788.
[15] LIU M J，WANG X H，ZHOU A J，et al.UAV-YOLO：small object detection on unmanned aerial vehicle perspective[J].Sensors，2020，20（8）：2238.
[16] LIN H，ZHOU J K，GAN Y F，et al.Novel up-scale feature aggregation for object detection in aerial images[J].Neurocomputing，2020，411：364-374.
[17] ZHANG X Q，FENG Y，ZHANG S，et al.Finding nonrigid tiny person with densely cropped and local attention object detector networks in low-altitude aerial images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2022，15：4371-4385.
[18] LUO X D，WU Y Q，WANG F Y.Target detection method of UAV aerial imagery based on improved YOLOv5[J].Remote Sensing，2022，14（19）：5063.
[19] ZHANG T Y，ZHAO Z Q，TIAN D W，et al.Improved YOLOv5 network with attention and context for small object detection[C]//18th International Conference on Intelligent Computing Methodologies，Xi’an，China，August 7-11，2022.Cham：Springer International Publishing，2022：341-352.
[20] YANG R J，LI W F，SHANG X N，et al.KPE-YOLOv5：an improved small target detection algorithm based on YOLOv5[J].Electronics，2023，12（4）：817.
[21] 李壮飞，杨风暴，郝岳强.一种基于残差网络优化的航拍小目标检测算法[J].国外电子测量技术，2022，41（8）：27-33.
LI Z F，YANG F B，HAO Y Q.Small target detection algorithm for aerial photography based on residual network optimization[J].Foreign Electronic Measurement Technology，2022，41（8）：27-33.
[22] 苏凯第，赵巧娥.基于YOLOv5算法的无人机电力巡检快速图像识别[J].电力科学与工程，2022，38（4）：43-48.
SU K D，ZHAO Q E.Fast image recognition of UAV power inspection based on YOLOv5 algorithm[J].Electric Power Science and Engineering，2022，38（4）：43-48.
[23] 许德刚，王露，李凡.深度学习的典型目标检测算法研究综述[J].计算机工程与应用，2021，57（8）：10-25.
XU D G，WANG L，LI F.Review of typical object detection algorithms for deep learning[J].Computer Engineering and Applications，2021，57（8）：10-25.
[24] HOWARD A，ZHU M L，CHEN B，et al.Mobilenets：efficient convolutional neural networks for mobile vision applications[J].arXiv：1704.04861，2017.
[25] ZHOU Y，LIU Y Y，HAN G J，et al.Face recognition based on the improved MobileNet[C]//2019 IEEE Symposium Series on Computational Intelligence（SSCI），2019：2776-2781.
[26] DU D W，ZHU P F，WEN L Y，et al.VisDrone-DET2019：the vision meets drone object detection in image challenge results[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop（ICCVW），2019：213-226.
[27] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.Yolov4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[28] 刘展威，陈慈发，董方敏.基于YOLOv5s的航拍小目标检测改进算法研究[J/OL].无线电工程：1-10[2023-02-23].https：//kns.cnki.net/kcms/detail/13.1097.TN.20230411.1645.
026.html.
LIU Z W，CHEN C F，DONG F M.Improved aerial small object detection algorithm based on YOLOv5s[J/OL].Radio Eegineering：1-10[2023-02-23].https：//kns.cnki.net/kcms/detail/13.1097.TN.20230411.1645.026.html.
[29] YU W P，YANG T J N，CHEN C.Towards resolving the challenge of long-tail distribution in UAV images for object detection[C]//2021 IEEE Winter Conference on Applications of Computer Vision.Waikoloa：IEEE，2021：3258-3267.
[30] ZHOU X，WANG D，KRHENBUHL P.Objects as points[J].arXiv：1904.07850，2019.
[31] ZHAO H P，ZHOU Y，ZHANG L，et al.Mixed YOLOv3-LITE：a lightweight real-time object detection method[J].Sensors，2020，20（7）：1861-1878.