TAN Feigang, LIU Weiming, HUANG Ling, ZHAI Cong, SHI Wei, LI Yanshan. Person Re-identification Across Multiple Non-overlapping Cameras by Grouping Similarity Comparison Model[J]. Chinese Journal of Electronics, 2017, 26(5): 905-911. doi: 10.1049/cje.2016.08.007
Citation: TAN Feigang, LIU Weiming, HUANG Ling, ZHAI Cong, SHI Wei, LI Yanshan. Person Re-identification Across Multiple Non-overlapping Cameras by Grouping Similarity Comparison Model[J]. Chinese Journal of Electronics, 2017, 26(5): 905-911. doi: 10.1049/cje.2016.08.007

Person Re-identification Across Multiple Non-overlapping Cameras by Grouping Similarity Comparison Model

doi: 10.1049/cje.2016.08.007
Funds:  This work is supported by the National Natural Science Foundation of China (No.6140128, No.51408237), Foundation for Distinguished Young Talents in Higher Education of Guangdong (No.2014KQNCX132), National Defense Preliminary Research Project (No.9140C800502150C80341), the scientific research fund of the Hunan provincial Education Department of China (No.13B132), Natural Science Foundation of SZU (No.201415), and Natural Science Foundation of Hubei Province (No.2015CFA025).
More Information
  • Corresponding author: LI Yanshan (corresponding author) was born in 1979, he received the Ph.D. degree in South China University of Technology. He is currently an associate professor at College of Information Engineering, Shenzhen University. His research interests include computer vision, machine learning and image analysis. (Email:lys@szu.edu.cn)
  • Received Date: 2015-09-06
  • Rev Recd Date: 2015-11-06
  • Publish Date: 2017-09-10
  • We propose a novel algorithm to solve the problem of person re-identification across multiple nonoverlapping cameras by grouping similarity comparison model. We use an image sequence instead of an image as a probe, and divide image sequence into groups by the method of systematic sampling. Then we design the rule which uses full-connection in a group and non-connection between groups to calculate similarities between images. We take the similarities as features, and train an AdaBoost classifier to match the persons across disjoint views. To enhance Euclidean distance discriminative ability, we propose a novel measure of similarity which is called Significant difference distance (SDD). Extensive experiments are conducted on two public datasets. Our proposed person re-identification method can achieve better performance compared with the state-of-the-art.
  • loading
  • H.X. Liu, X.W. LYU, T.H. Zhu, et al., "An adaptive featurefusion method for object matching over non-overlapped scenes", Journal of Signal Processing Systems, Vol.76, No.1, pp.77-89, 2014.
    N. Martinel and C. Micheloni, "Classification of local eigendissimilarities for person re-identification", IEEE Signal Processing Letters, Vol.22, No.4, pp.455-459, 2015.
    R. Mazzon, S.F. Tahir and A. Cavallaro, "Person reidentification in crowd", Pattern Recognition Letters, Vol.33, No.14, pp.1828-1837, 2012.
    Y.S. Li, W.M. Liu, X.T. Li, et al., "GA-SIFT:A new scale invariant feature transform for multispectral image using geometric algebra", Information Sciences, Vol.281, No.10, pp.559-572, 2014.
    Y.S. Li, Q.H. Huang, W.X. Xie, et al., "A novel visual codebook model based on fuzzy geometry for large-scale image classification", Pattern Recognition, Vol.48, No.10, pp.3125-3134, 2015.
    X.T. Chen, K.Q. Huang and T.N. Tan, "Object tracking across non-overlapping cameras using adaptive models", Proc. of Asian Conference on Computer Vision, Daejeon, Korea, pp.464-477, 2012.
    Y.S. Li, W.M. Liu, Q.H. Huang, et al., "Fuzzy bag of words for social image description", Multimedia Tools and Applications, Doi:10.1007/s11042-014-2138-4, 2014.
    Y.S. Li, W.M. Liu, Q.H. Huang, "Traffic anomaly detection based on image descriptor in videos", Multimedia Tools and Applications, Doi:10.1007/s11042-015-2637-y, 2015.
    Y.W. Fu, J.Q. Long and W. Yang, "Maneuvering multi-target tracking using the multi-model cardinalized probability hypothesis density filter", Chinese Journal of Electronics, Vol.22, No.3, pp.634-640, 2013.
    X. Liu, M.L. Song, D.C. Tao, et al., "Semi-supervised coupled dictionary learning for person re-identification", Proc. of IEEE Computer Vision and Pattern Recognition, Columbus, OH, USA, pp.3550-3557, 2014.
    S.F. Tahir and A. Cavallaro, "Cost-effective features for reidentification in camera networks", IEEE Transactions on Circuits & Systems for Video Technology, Vol.24, No.8, pp.1362-1374, 2014.
    R. Satta, G. Fumera and F. Roli, "Fast person re-identification based on dissimilarity representations", Pattern Recognition Letters, Vol.33, No.14, pp.1838-1848, 2012.
    R. Zhao, W. Ouyang and X.G. Wang, "Unsupervised salience learning for person re-identification", Proc. of IEEE Computer Vision and Pattern Recognition, Portland, OR, USA, pp. 3586-3593, 2013.
    C.X. Liu, S.G. Gong and C.C. Loy, "On-the-fly feature importance mining for person re-identification", Pattern Recognition, Vol.47, No.4, pp.1602-1615, 2014.
    W.S. Zheng, S.G. Gong and T. Xiang, "Person re-identification by probabilistic relative distance comparison", Proc. of IEEE Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, pp.649-656, 2011.
    Z. Li, S.Y. Chang, F. Liang, et al., "Learning locally-adaptive decision functions for person verification", Proc. of IEEE Com-puter Vision and Pattern Recognition, Portland, OR, USA, pp.3610-3617, 2013.
    X.J. Zhang, C. Xu, M. Li, et al., "Study of visual saliency detection via nonlocal anisotropic diffusion equation", Pattern Recognition, Vol.48, No.4, pp.1315-1327, 2015.
    L. Lamberti and F. Camastra, "Handy:A real-time three color glove-based gesture recognizer with learning vector quantization", Expert Systems with Applications, Vol.39, No.12, pp.10489-10494, 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 (172) PDF downloads(337) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return