计算机科学 ›› 2022, Vol. 49 ›› Issue (6A): 358-362.doi: 10.11896/jsjkx.210700048
郝强, 李杰, 张曼, 王路
HAO Qiang, LI Jie, ZHANG Man, WANG Lu
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。
中图分类号:
[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. |
[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. |
|