Exploiting Feature Correlations by Brownian Statistics for People Detection and Recognition

被引:12
作者
Bak, Slawomir [1 ]
Biagio, Marco San [2 ]
Kumar, Ratnesh [3 ]
Murino, Vittorio [2 ,4 ]
Bremond, Francois [5 ]
机构
[1] Disney Res Pittsburgh, Pittsburgh, PA 15213 USA
[2] Ist Italiano Tecnol, Dept Pattern Anal & Comp Vis, I-16163 Genoa, Italy
[3] Placemeter, New York, NY USA
[4] Univ Verona, Dipartimento Informat, I-37134 Verona, Italy
[5] INRIA Sophia Antipolis Mediterranean, STARS Lab, F-06902 Valbonne, France
来源
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS | 2017年 / 47卷 / 09期
关键词
Brownian descriptor; covariance descriptor; pedestrian detection; reidentification; CLASSIFICATION; APPEARANCE; HISTOGRAMS;
D O I
10.1109/TSMC.2016.2531658
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Characterizing an image region by its feature intercorrelations is a modern trend in computer vision. In this paper, we introduce a new image descriptor that can be seen as a natural extension of a standard covariance descriptor with the advantage of capturing nonlinear and nonmonotone dependencies. Inspired from the recent advances in mathematical statistics of Brownian motion, we can express highly complex structural information in a compact and computationally efficient manner. We show that our Brownian covariance descriptor can capture richer image characteristics than the covariance descriptor. Additionally, a detailed analysis of the Brownian manifold reveals that opposite to the classical covariance descriptor, the proposed descriptor lies in a relatively flat manifold, which can be treated as a Euclidean. This brings significant boost in the efficiency of the descriptor. The effectiveness and the generality of our approach is validated on two challenging vision tasks, pedestrian classification, and person reidentification. The experiments are carried out on multiple datasets achieving promising results.
引用
收藏
页码:2538 / 2549
页数:12
相关论文
共 50 条
  • [1] Face description with local binary patterns:: Application to face recognition
    Ahonen, Timo
    Hadid, Abdenour
    Pietikainen, Matti
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) : 2037 - 2041
  • [2] [Anonymous], P COMP VIS PATT REC
  • [3] [Anonymous], 2008, 2008 IEEE C COMP VIS
  • [4] [Anonymous], 2008, COMPUT VIS IMAGE UND, DOI DOI 10.1016/j.cviu.2007.09.014
  • [5] [Anonymous], 2012 INT C DIGITAL I, DOI [DOI 10.1109/DICTA.2012.6411689, 10.1109/DICTA.2012.6411689]
  • [6] Bak S., 2011, Proceedings of the 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2011), P179, DOI 10.1109/AVSS.2011.6027316
  • [7] Bak S, 2014, IEEE WINT CONF APPL, P363, DOI 10.1109/WACV.2014.6836077
  • [8] Bak S, 2012, LECT NOTES COMPUT SC, V7574, P806, DOI 10.1007/978-3-642-33712-3_58
  • [9] Boosted human re-identification using Riemannian manifolds
    Bak, Slawomir
    Corvee, Etienne
    Bremond, Francois
    Thonnat, Monique
    [J]. IMAGE AND VISION COMPUTING, 2012, 30 (6-7) : 443 - 452
  • [10] BROWNIAN COVARIANCE AND CENTRAL LIMIT THEOREM FOR STATIONARY SEQUENCES
    Bakirov, N. K.
    Szekely, G. J.
    [J]. THEORY OF PROBABILITY AND ITS APPLICATIONS, 2011, 55 (03) : 371 - 394