Road Surface State Recognition Based on SVM Optimization and Image Segmentation Processing

被引:18
|
作者
Zhao, Jiandong [1 ]
Wu, Hongqiang [1 ]
Chen, Liangliang [2 ]
机构
[1] Beijing Jiaotong Univ, Sch Mech & Elect Control Engn, Beijing 100044, Peoples R China
[2] Broadvis Engn Consultants, Nat Engn Lab Surface Transportat Weather Impacts, Kunming 650041, Peoples R China
关键词
D O I
10.1155/2017/6458495
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Adverse road condition is the main cause of traffic accidents. Road surface condition recognition based on video image has become a central issue. However, hybrid road surface and road surface under different lighting environments are two crucial problems. In this paper, the road surface states are categorized into 5 types including dry, wet, snow, ice, and water. Then, according to the original image size, images are segmented; 9-dimensional color eigenvectors and 4 texture eigenvectors are extracted to construct road surface state characteristics database. Next, a recognition method of road surface state based on SVM (Support Vector Machine) is proposed. In order to improve the recognition accuracy and the universality, a grid searching algorithm and PSO (Particle Swarm Optimization) algorithm are used to optimize the kernel function factor and penalty factor of SVM. Finally, a large number of actual road surface images in different environments are tested. The results show that the method based on SVM and image segmentation is feasible. The accuracy of PSO algorithm is more than 90%, which effectively solves the problem of road surface state recognition under the condition of hybrid or different video scenes.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Recognition of maize disease based on image processing and SVM
    College of Information and Electric Engineering, Shenyang Agricultural University, Shenyang 110161, China
    Yi Qi Yi Biao Xue Bao, 2006, SUPPL. (2123-2124):
  • [2] Road extraction using SVM and image segmentation
    Song, MJ
    Civco, D
    PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2004, 70 (12): : 1365 - 1371
  • [3] A Painting Artist Recognition System Based on Image Processing and Hierarchical SVM
    AlyanNezhadi, Mohammad M.
    Dabbaghan, Hossein
    Moghani, Samira
    Forghani, Majid
    2019 IEEE 5TH CONFERENCE ON KNOWLEDGE BASED ENGINEERING AND INNOVATION (KBEI 2019), 2019, : 537 - 541
  • [4] Recognition method of cement rotary kiln burning state based on Otsu-Kmeans flame image segmentation and SVM
    Zhang, Rongfeng
    Lu, Shizeng
    Yu, Hongliang
    Wang, Xiaohong
    OPTIK, 2021, 243
  • [5] Recognition method of cement rotary kiln burning state based on Otsu-Kmeans flame image segmentation and SVM
    Zhang, Rongfeng
    Lu, Shizeng
    Yu, Hongliang
    Wang, Xiaohong
    Optik, 2021, 243
  • [6] State Recognition of Switch Matrix Based on Image Processing
    Zhang, Shigang
    Yang, Yongmin
    Li, Yangyang
    Luo, Xu
    2018 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE (PHM-CHONGQING 2018), 2018, : 614 - 618
  • [7] Segmentation algorithm for overlap recognition of seedling lettuce and weeds based on SVM and image blocking
    Zhang, Lei
    Zhang, Zhien
    Wu, Chuanyu
    Sun, Liang
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 201
  • [8] Road markings recognition using image processing
    Charbonnier, P
    Diebolt, F
    Guillard, Y
    Peyret, F
    IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, 1997, : 912 - 917
  • [9] Image segmentation and pattern recognition for road marking analysis
    Rebut, J
    Bensrhair, A
    Toulminet, G
    Proceedings of the IEEE-ISIE 2004, Vols 1 and 2, 2004, : 727 - 732
  • [10] IMAGE SEGMENTATION ALGORITHM RESEARCH BASED ON SVM
    Kun, Luo
    2011 3RD INTERNATIONAL CONFERENCE ON COMPUTER TECHNOLOGY AND DEVELOPMENT (ICCTD 2011), VOL 2, 2012, : 1 - 5