Person retrieval based on viewpoint saliency prior

被引：0

作者：

机构：

[1] National Engineering Research Center for Multimedia Software, School of Computer, Wuhan University

来源：

Hu, R. (hurm1964@gmail.com) | 1600年 / Binary Information Press, P.O. Box 162, Bethel, CT 06801-0162, United States卷 / 09期

关键词：

Body partitioning; Person retrieval; Viewpoint saliency prior;

D O I：

10.12733/jcis7104

中图分类号：

学科分类号：

摘要：

Matching people across disjoint cameras, known as person re-identification, is becoming an important and challenge task. However appearance of same person in different cameras may be obviously different due to various surveillance environments or individual motions, especially caused by variations in viewpoints and poses. To solve this problem, this paper presents a novel and simple method that retrievals specific person based on viewpoint saliency prior obtained from users knowledge. After body partitioning and viewpoint classification, we establish the fuzzy correspondence among all parts in different viewpoint. When query person is given, user is requested to designate some parts which will be influenced significantly by viewpoints change, and then weights of those parts are adjusted automatically. Introducing users prior is available when we try to find someone accurately, and it is simple and convenient compared to complicated learning way in various multi-cameras environments. Finally experiments prove the efficiency of our method. © 2013 Binary Information Press.

引用

页码：8235 / 8242

页数：7

共 15 条

[1]

Gong S.G., Loy C.C., Xiang T., Security and surveillance, VAH, Part 4, pp. 455-472, (2011)

[2]

Gheissari N., Sebastian T.B., Tu P.H., Rittscher J., Hartley R., Person re-identification using spatiotemporal appearance, CVPR, 2, pp. 1528-1535, (2006)

[3]

Farenzena M., Bazzani L., Perina A., Murino V., Cristani M., Person re-identification by symmetry-driven accumulation of local features, CVPR, pp. 2360-2367, (2010)

[4]

Cheng D.S., Cristani M., Stoppa M., Bazzani L., Murino V., Custom pictorial structures for re-identification, BMVC, (2011)

[5]

Gray D., Tao H., Viewpoint invariant pedestrian recognition with an ensemble of localized features, ECCV, pp. 262-275, (2008)

[6]

Prosser B., Zheng W.S., Gong S., Xiang T., Person re-identification by support vector ranking, BMVC, (2010)

[7]

Zheng W.S., Gong G.S., Tao X., Person re-identification by probabilistic relative distance comparison, CVPR, pp. 649-656, (2011)

[8]

Hirzer M., Roth P., Kstinger M., Bischof H., Relaxed pairwise learned metric for person re-identification, ECCV, pp. 780-793, (2012)

[9]

Chang C.-C., Lin C.-J., LIBSVM: A library for support vector machines, ACM Transactions on Intelligent Systems and Technology, 2, 3, (2011)

[10]

Liu X., Song M.L., Zhao Q., Tao D.C., Chen C., Bu J.J., Attribute-restricted latent topic model for person re-identification, PR, 45, pp. 4204-4213, (2012)

← 1 2 →