基于改进YOLOv3的空间非合作目标部件识别算法

doi:10.11896/jsjkx.210700048

摘要/Abstract

摘要： 在使用深度学习方法进行空间非合作目标部件识别时,由于神经网络参数量大且嵌入式设备计算能力不足,难以将神经网络有效地部署在嵌入式平台上。针对该问题,文中提出了一种改进的轻量化目标检测网络,在保证检测精度的同时,有效降低网络参数量,提升了网络检测速度。所提网络模型在YOLOv3的基础上借鉴深度可分离卷积的思想,引入Bottleneck模块降低了模型参数量,提升了检测速度,同时引入Res2Net残差模块来增加模型的感受野尺度丰富性和结构深度,提高了网络对于小目标的检测能力。设计了一个新的轻量化特征提取主干网络Res2-MobileNet,并结合多尺度检测方法进行空间非合作目标部件识别。实验结果表明,相比YOLOv3,所提模型在参数量上降低了55.5%,检测速度由34fps提高到65 fps,同时对于小目标的检测效果也有显著提升。

关键词: YOLOv3, 空间非合作目标, 目标识别, 轻量化

Abstract: Due to the large amount of neural network parameters and insufficient computing power of embedded devices,it is difficult to effectively deploy neural networks on embedded platforms when using deep learning methods to identify spatial non-cooperative target components.Aiming at this problem,an improved lightweight target detection network is proposed in this paper.On the basis of YOLOv3,a new lightweight feature extraction backbone network Res2-MobileNet is designed,drawing on the ideaof Depth Separable Convolution,introducing the Bottleneck module to reduce the amount of model parameters to improve the detection speed,and introducing the Res2Net residual module to increase the sensitivity of network to small targets by increasing the modeĹs receptive field scale richness and structural depth,and combines multi-scale detection methods to recognize spatial non-cooperative target components.The experimental results show that compared with the YOLOv3 model,the size of this model is reduced by 55.5%,the detection speed is increased from 34fps to 65 fps,and the detection effect for small targets is also significantly improved.

Key words: Lightweight, Spatial non-cooperative target, Target recognition, YOLOv3

中图分类号:

TP391

郝强, 李杰, 张曼, 王路. 基于改进YOLOv3的空间非合作目标部件识别算法[J]. 计算机科学, 2022, 49(6A): 358-362. https://doi.org/10.11896/jsjkx.210700048

HAO Qiang, LI Jie, ZHANG Man, WANG Lu. Spatial Non-cooperative Target Components Recognition Algorithm Based on Improved YOLOv3[J]. Computer Science, 2022, 49(6A): 358-362. https://doi.org/10.11896/jsjkx.210700048

参考文献

[1] WANG L.Research on spatial multi-target recognition method based on deep learning[J].Unmanned System Technology,2019,2(3):49-55.
[2] YANG M D.Research on space non-cooperative area targettracking technology [D].Shanghai:Shanghai Institute of Technical Physics,2015.
[3] LIU L C,ZHOU R H,ZHANG L M,et al.Spacecraft feature recognition algorithm based on vision[C]//The Second China Aerospace Security Conference.2017.
[4] HUA Y R,ZHANG Z,LONG S,et al.Remote sensing imagetarget detection based on improved YOLO algorithm[J].Electronic Measurement Technology,2020,43(24):87-92.
[5] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc.of the Computer Vision and Pattern Recognition,Columbus.2014:580-587.
[6] GIRSHICK R.Fast R-CNN[C]//Proc. of the InternationalConference on Computer Vision.2015:1440-1448.
[7] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towardsreal-time object detection with region proposal networks[J].IEEE Trans.on Pattern Analysis & Machine Intelligence,2017,39(6):1137-1149.
[8] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shotMultiBox detector[C]//Proc.of the European Conference on Computer Vision.Amsterdam,2016:21-37.
[9] LI Z,ZHOU F.FSSD:Feature fusion single shot multibox detector[J].Computer Vision and Pattern Recognition,2018,36(7):356-366.
[10] FU C,LIU W,RANGA A,et al.DSSD:deconvolutional single shot detector [EB/OL].http://arxiv.org/abs/1701.06659,2020-07-16.
[11] REDMON J,DIVVALA S K,GIRSHICK R,et al.You onlylook once:unified,real-time object detection[C]//Proc.of the Computer Vision and Pattern Recognition.2016:779-788.
[12] REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C]//Proc.o f the Computer Vision and Pattern Recognition.2017:6517-6525.
[13] REDMON J,FARHADI A.YOLOv3:An incremental improvement [EB/OL].http://arxiv.org/abs/1804.02767,2020-07-16.
[14] CHOLLET F.Xception:deep learning with depthwise separableconvolutions[C]//IEEE conference on computer vision and pattern recognition.Honolulu,HI:IEEE,2017:1800-1807.
[15] KONG Y H,ZHU C C,CHE B B.Flower recognition and model pruning based on MobileNets under complex background[J].Science Technology and Engineering,2018,18(19):84-88.
[16] ZHANG X,ZHOU X,LIN M,et al.ShuffleNet:an extremely efficient convolutional neural network for mobile devices[C]//IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:IEEE,2018:6848-6856.

相关文章 15

[1]	袁磊, 刘紫燕, 朱明成, 马珊珊, 陈霖周廷. 融合改进密集连接和分布排序损失的遥感图像检测 Improved YOLOv3 Remote Sensing Target Detection Based on Improved Dense Connection and Distributional Ranking Loss 计算机科学, 2021, 48(9): 168-173. https://doi.org/10.11896/jsjkx.200800001
[2]	余晗青, 杨贞, 殷志坚. 基于区域激活策略的Tiny YOLOv3目标检测算法 Tiny YOLOv3 Target Detection Algorithm Based on Region Activation Strategy 计算机科学, 2021, 48(6A): 118-121. https://doi.org/10.11896/jsjkx.200700122
[3]	袁晓磊, 岳晓峰, 方博, 马国元. 基于点对特征及分层全连接聚类的三维目标识别方法 Three-dimensional Target Recognition Method Based on Pair Point Feature and HierarchicalComplete-linkage Clustering 计算机科学, 2021, 48(6A): 127-131. https://doi.org/10.11896/jsjkx.200800035
[4]	李杉, 许新征. 基于双角度并行剪枝的VGG16优化方法 Parallel Pruning from Two Aspects for VGG16 Optimization 计算机科学, 2021, 48(6): 227-233. https://doi.org/10.11896/jsjkx.200800016
[5]	龚航, 刘培顺. 夜间行驶车辆远光灯检测方法 Detection Method of High Beam in Night Driving Vehicle 计算机科学, 2021, 48(12): 256-263. https://doi.org/10.11896/jsjkx.200700026
[6]	刘彦, 秦品乐, 曾建朝. 基于YOLOv3与分层数据关联的多目标跟踪算法 Multi-object Tracking Algorithm Based on YOLOv3 and Hierarchical Data Association 计算机科学, 2021, 48(11A): 370-375. https://doi.org/10.11896/jsjkx.201000115
[7]	徐守坤, 倪楚涵, 吉晨晨, 李宁. 基于YOLOv3的施工场景安全帽佩戴的图像描述 Image Caption of Safety Helmets Wearing in Construction Scene Based on YOLOv3 计算机科学, 2020, 47(8): 233-240. https://doi.org/10.11896/jsjkx.190600109
[8]	乔梦雨, 王鹏, 吴娇, 张宽. 面向陆战场目标识别的轻量级卷积神经网络 Lightweight Convolutional Neural Networks for Land Battle Target Recognition 计算机科学, 2020, 47(5): 161-165. https://doi.org/10.11896/jsjkx.190300062
[9]	刘舒康, 唐鹏, 金炜东. 基于智能数据增强和改进YOLOv3算法的接触网吊弦及支架检测研究 Study on Catenary Dropper and Support Detection Based on Intelligent Data Augmentation and Improved YOLOv3 计算机科学, 2020, 47(11A): 178-182. https://doi.org/10.11896/jsjkx.200200053
[10]	黄同愿, 杨雪姣, 向国徽, 陈辽. 基于单目视觉的小目标行人检测与测距研究 Study on Small Target Pedestrian Detection and Ranging Based on Monocular Vision 计算机科学, 2020, 47(11): 205-211. https://doi.org/10.11896/jsjkx.190900078
[11]	吴刚,徐利敏. 目标形状表达算法综述 Review of Shape Representation for Objects 计算机科学, 2019, 46(7): 30-37. https://doi.org/10.11896/j.issn.1002-137X.2019.07.005
[12]	程栋,王卫红. OpenMP多核计算技术在SAR图像处理中的应用 Application of OpenMP in SAR Image Processing 计算机科学, 2017, 44(Z6): 161-163. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.037
[13]	刘涛,吴泽民,姜青竹,曾明勇,彭韬频. 基于似物性的快速视觉目标识别算法 Fast Object Recognition Method Based on Objectness 计算机科学, 2016, 43(7): 73-76. https://doi.org/10.11896/j.issn.1002-137X.2016.07.012
[14]	皮嘉立,巫正中,陈卓. 基于Adaboost-CSHG的特定类目标跟踪识别 Specific Target Tracking and Recognition Based on Adaboost-CSHG 计算机科学, 2016, 43(4): 318-321. https://doi.org/10.11896/j.issn.1002-137X.2016.04.065
[15]	薛爱军,王晓丹,宋亚飞,雷蕾. 基于移动散射点模型的雷达回波仿真及分析 Simulation and Analysis of Radar Echo Based on Moving Scattering Center Model 计算机科学, 2013, 40(9): 201-203.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed