HE Yi, SANG Nong, GAO Changxin, HAN Jun. Online Unsupervised Learning Classification of Pedestrian and Vehicle for Video Surveillance[J]. Chinese Journal of Electronics, 2017, 26(1): 145-151. doi: 10.1049/cje.2016.08.011
Citation: HE Yi, SANG Nong, GAO Changxin, HAN Jun. Online Unsupervised Learning Classification of Pedestrian and Vehicle for Video Surveillance[J]. Chinese Journal of Electronics, 2017, 26(1): 145-151. doi: 10.1049/cje.2016.08.011

Online Unsupervised Learning Classification of Pedestrian and Vehicle for Video Surveillance

doi: 10.1049/cje.2016.08.011
Funds:  This work is supported by the National Natural Science Foundation of China (No.61371047), and Research Fund for the Doctoral Program of Higher Education of China (No.20110185110014).
More Information
  • Corresponding author: HAN Jun (corresponding author) received the Ph.D. degree in Air Force Radar Academy, Wuhan, China in 2010. Now he is a lecturer in Air Force Early Warning Academy. His interests include radar signal processing, electronic countermeasures. (Email:duj81@163.com)
  • Received Date: 2014-09-02
  • Rev Recd Date: 2015-05-05
  • Publish Date: 2017-01-10
  • This paper presents an online unsupervised learning classification of pedestrians and vehicles for video surveillance. Different from traditional methods depending on offline training, our method adopts the online label strategy based on temporal and morphological features, which saves time and labor to a large extent. It extract the moving objects with their features from the original video. An online filtering procedure is adopted to label the moving objects according to certain threshold of speed and area feature. The labeled objects are sent into a SVM classifier to generate the pedestrian & vehicle classifier. Experimental results illustrate that our unsupervised learning algorithm is adapted to polymorphism of the pedestrians and diversity of the vehicles with high classification accuracy.
  • loading
  • Zhi Kai Ku, "Shape-based recognition and classification for common objects-An application in video scene analysis", International Conference on Computer Engineering and Technology, Chengdu, China, pp.16-18, 2010.
    Mohamed Elhoseiny, "MultiClass object classication in video surveillance systems experimental study", IEEE Conference on Computer Vision and Pattern Recognition Workshops, Oregon, Portland, pp.788-793, 2013.
    R. Collins, et al., "A system for video surveillance and monitoring", Technical Report, VSAM final report Carnegie Mellon University, CMU-RI-TR-00-12, 2000.
    L. Zhang, S. Li, X. Yuan, et al., "Real-time object classification in video surveillance based on appearance learning", Proc. of IEEE. Int. Workshop Visual Surveillance in Conjunction with CVPR, Hawaii, USA, pp.17-22, 2007.
    P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features", IEEE Conference on Computer Vision and Pattern Recognition Workshops, Minnesota, USA, pp.511-518, 2001.
    A. Blum and T. Mitchell, "Combining labeled and unlabeled data with cotraining", Proc. of 11th Annu. Conf. Computational Learning Theory, Madison, USA, pp.92-100, 1998.
    X. Fan, Z. Guo, and H. Ma,"An improved em-based semi-supervised learning method", International Conference on Systems Biology and Intelligent Computing, Shanghai, China, pp.529-532, 2009.
    Xin Zhao, "Global and local training for moving object classification in surveillance-oriented scene", Asian Conference on Pattern Recognition, Beijing, China, pp.681-685, 2011.
    A. Levin, P. Viola, and Y. Freund, "Unsupervised improvement of visual detectors using co-training", IEEE Conference on Computer Vision, Beijing, China, pp.626-633, 2003.
    Z. Zhou and M. Li, "Semisupervised regression with cotrainingstyle algorithms", TKDE, Vol.19, No.11, pp.1479-1493, 2007.
    T.Z. Zhang, "Mining semantic context information for intelligent video surveillance of traffic scenes", IEEE Transactions on Industrial Informatics, Vol.9, No.1, pp.149-151, 2013.
    R.N. Hota, V. Venkoparao, A. Rajagopal, "Shape based object classification for automated video surveillance with feature selection", International Conference on Information Technology, Roukela, India, pp.97-99, 2007.
    Navneet Dalal, Bill Triggs, "Histograms of oriented gradients for human detection", IEEE Conference on Computer Vision and Pattern Recognition Workshops, San Diego, CA, USA, pp.886-893, 2005.
    J. Xu, M.H. He and J. Han, "A comprehensive estimation method for kernel function of radar signal classifier," Chinese Journal of Electronics, Vol.24, No.1, pp.218-220, 2015.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (121) PDF downloads(822) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return