ZHU Suguo, DU Junping, REN Nan, “A Novel Simple Visual Tracking Algorithm Based on Hashing and Deep Learning,” Chinese Journal of Electronics, vol. 26, no. 5, pp. 1073-1078, 2017, doi: 10.1049/cje.2016.06.026
Citation: ZHU Suguo, DU Junping, REN Nan, “A Novel Simple Visual Tracking Algorithm Based on Hashing and Deep Learning,” Chinese Journal of Electronics, vol. 26, no. 5, pp. 1073-1078, 2017, doi: 10.1049/cje.2016.06.026

A Novel Simple Visual Tracking Algorithm Based on Hashing and Deep Learning

doi: 10.1049/cje.2016.06.026
Funds:  This work was supported by the National Basic Research Program of China (973 Program) (No.2012CB821200, No.2012CB821206), and the National Natural Science Foundation of China (No.61320106006, No.61532006, No.61502042).
More Information
  • Corresponding author: DU Junping (corresponding author) was born in 1963. She is now a professor and Ph.D. supervisor in School of Computer Science and Technology, Beijing University of Posts and Telecommunications. Her research interests include artificial intelligence, image processing and pattern recognition. (Email:junpingdu@126.com)
  • Received Date: 2015-08-04
  • Rev Recd Date: 2015-09-08
  • Publish Date: 2017-09-10
  • Deep network has been proven efficient and robust to capture object features in some conditions. It still remains in the stage of classifying or detecting objects. In the field of visual tracking, deep network has not been applied widely. One of the reasons is that its time consuming made the strong method could not meet the speed need of visual tracking. A novel simple tracker is proposed to complete tracking task. A simple six-layer feed-forward backpropagation neural network is applied to capture object features. Nevertheless, this representation is not robust enough when illumination changes or drastic scale changes in dynamic condition. To improve the performance and not to increase much time spent, image perceptual hashing method is employed, which extracts low frequency information of object as its fingerprint to recognize the object from its structure. 64-bit characters are calculated by it, and they are utilized to be the bias terms of the neutral network. This leads more significant improvement for performance of extracting sufficient object features. Then we take particle filter to complete the tracking process with the proposed representation. The experimental results demonstrate that the proposed algorithm is efficient and robust compared with the state-of-the-art tracking methods.
  • loading
  • K. Zhang, L. Zhang, and M.-H. Yang, "Real-time compressive tracking", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Firenze Italy, pp.864-877, 2012.
    T. Zhang, B. Ghanem, S. Liu, et al., "Robust visual tracking via multi-task sparse learning", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, pp.2042-2049, 2012.
    J. Xu, H. Lu and M.-H. Yang, "Visual tracking via adaptive structural local sparse appearance model", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, pp. 1822-1829, 2012.
    J.F. Henriques, R. Caseiro, P. Martins, et al., "Exploiting the circulant structure of tracking-by-detection with kernels", Proc. of 12th European Conference Computer Vision, Firenze, Italy, pp.702-715. 2012.
    S.-L. Laura and L.-M. Erik, "Distribution fields for tracking", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, pp.1910-1917, 2012.
    G. Yuan and M. Xue, "Robust visual tracking via principal component pursuit", Chinese Journal of Electronics, Vol.43, No.3, pp.417-423, 2015.
    N. Wang and D. Yeung, "Learning a deep compact image representation for visual tracking", Advances in Neural Information Processing Systems, pp.809-817. 2013.
    X, Zhou, L. Xie, P. Zhang, et al., "An ensemble of deep neural networks for object tracking", Proc. of IEEE International Conference on Image Processing, Paris, France, pp.843-847, 2014.
    K. Jason, K.M. Lim and C.P. Lee, "Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle", Pattern Recognition, Vol.48, No.10, pp.2964-2982, 2015.
    K. Zhang, Q. Liu, Y. Wu, et al., "Robust tracking via convolutional networks without learning", arXiv preprint arXiv:1501.04505, 2015.
    Z. Jie, "A novel block-DCT and PCA based image perceptual hashing algorithm", International Journal of Computer Science Issues, Vol.10, No.3, 2013.
    M. Fei, J. Li and H. Liu, "Visual tracking based on improved foreground detection and perceptual hashing", Neurocomputing, Vol.152, pp.413-428, 2014.
    T.M. Mitchell, Machine Learning, The McGraw-Hill Companies, 1997.
    J. Segers, "Perceptual image hashes", http://jenssegers.be/index.php/blog/61/perceptual-image-hashes,2014-12-14.
    P. Sarkar, "Sequential Monte Carlo methods in practice", Technometrics, Vol.45, No.1, pp.1-106, 2003.
    PASCAL VOC, "Pattern analysis, analysis modelling and computational learning visual object classes", http://pascallin.ecs.soton.ac.uk/challenges/VOC/, 2012.
  • 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 (575) PDF downloads(526) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return