计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200101-6.doi: 10.11896/jsjkx.230200101
姜珂, 石建强, 陈光武
JIANG Ke, SHI Jianqiang, CHEN Guangwu
摘要： 轨道线检测有助于提高列车的行驶安全,但检测效果易受列车行驶环境的影响。针对这种情况,提出了基于图像预处理并使用改进后的YOLOv5s网络进行轨道线检测的方法。首先,对图像预处理,使用HSV分离出图像的多余信息后,基于Otsu阈值处理,提高了图像检测目标的显著度,降低了目标识别的复杂程度;其次,考虑到列车车载系统轻量化的要求,对YOLOv5s目标识别网络进行了改进,通过添加 CBAM注意力机制模块改进主干网络,来加强有效的特征信息,可以在确保检测结果的基础上提高检测速度,并使得检测算法模型易于部署到移动端设备中。使用公开的列车行驶图像构建数据集进行实验,实验结果表明提出的检测算法在数据集测试中的mAP达到了94.1%,具备一定的实时性和鲁棒性。
中图分类号:
| [1]XIAO Y,SU L Y.Research on the Integrated Technology of the Automatic Driving System for Rail Transit[J].China Railway,2015,5(5):109-113. [2]LIU D W,GUO J,WANG X M,et al.Intelligent MonitoringTechnologies forRailway Signaling Systems in China[J].Journal of Southwest Jiaotong University,2014,49(9):904-912. [3]APKING A.Worldwide Market for Railway Industries Study:Market Volumes for OEM Business and After-Sales Service as Well as Prospects for Market Developments of Infrastructure and Rolling Stock[J].SCI Verkehr GmbH:Köln,Germany,2018:7. [4]XIAO J S,CHENG X,LI B J,et al.Lane detection algorithmbased on Beamlet transformation and K-means clustering[J].Journal of Sichuan University(Engineering Science Edition),2015,47(4):98-103. [5]ETXEBERRIA-GARCIA M,LABAYEN M,ZAMALLOA M,et al.Application of computer vision and deep learning in the railway domain for autonomous train stop operation[C]//2020 IEEE/SICE International Symposium on System Integration(SII).IEEE,2020:943-948. [6]KAPOOR R,GOEL R,SHARMA A.Deep learning based object and railway track recognition using train mounted thermal imaging system[J].Journal of Computational and Theoretical Nanoscience,2020,17(11):5062-5071. [7]DENG Y W,PU H T,HUA X B.Research on Lane Detection Based On RC-DBSCAN[J].Journal of Hunan University(Natural Sciences),2021,48(10):85-92. [8]MUTHALAGU R,BOLIMERA A,KALAIC V.Lane detection technique based on perspective transformation and histogram analysis for self-driving cars[J].Computers & Electrical Engineering,2020,85:106653. [9]WEI X,YANG Z,LIU Y,et al.Railway track fastener defect detection based on image processsing and deep learning techniques:A comparative study[J].Engineering Applications of Artificial Intelligence,2019,80:66-81. [10]HE H,LIU A,QIU J.Lane Line Detection Method Based on MFD-MCN[J].Journal of Hunan Institute of Engineering(Na-tural Science Edition),2022,32(2):48-53. [11]QIN N,HU X,DAI H.Deep fusion of multi-view and multimodal representation of ALS point cloud for 3D terrain scene re-cognition[J].ISPRS Journal of Photogrametry and Remote Sensing,2018,143:205-212. [12]WANG J T,HONG W,GONG L.Lane detection algorithmbased ondensity clustering and RANSAC[C]//2018 Chinese Control And Decision Conference(CCDC).Shenyang,China:IEEE,2018:919-924. [13]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. [14]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19. [15]WEI X K,SUO D,WEI D H.A Survey of The Application of Machine Vision In Rail Transit System Inspection[J].Control and Decision,2021,36(2):257-282. [16]WANG S,LIU F,LIU B.Research on application of deep convolutional network in high-speed railway track inspection based on distributed fiber acoustic sensing[J].Optics Communications,2021,492:126-141. [17]WANG G,CHEN X C,HAN D Y.Research on threshold segmentation algorithm of coal CT images based on improved Otsu[J].Coal Science and Technology,2021,49(1):264-271. [18]YUE X X,JIA J X,CHEN X D,et al.Road small target detection algorithm based on improved YOLO V3[J].Computer Engineering and Applications,2020,56(21):218-223. [19]LU D,MA W Q.Gesture Recognition Based on ImprovedYOLOv4-tiny Algorithm[J].Journal of Electronics & Information Technology,2021:1-9. [20]LYU Z,ZHANG D,LUO J.A GPU-free real-time object detection method for apron surveillance video based on quantized MobileNet-SSD[J].IET Image Processing,2022. |
|
||
首页