Abstract
Person re-identification across multiple cameras is difficult due to viewpoint and illumination variations. Most traditional research focuses on developing invariant features that are unaffected by these variations. However, thus far, there has been no feature developed that is completely invariant, and it is possible that a fully invariant feature may not exist. Therefore, we do not seek to develop these ideal features in this paper. We instead propose a framework for learning a gallery of persons who appear in the camera network frequently. The gallery contains appearance models of these persons from each camera and viewpoint. Given the camera identity, viewpoint identity, person identity, the model is decided. Since these appearance models are specific to each camera and viewpoint, the problems of viewpoint variations and illumination variations between cameras are explicitly solved, and re-identification becomes a ranking problem. Experiments demonstrate that our framework provides significant improvement in addressing the re-identification problem.
Similar content being viewed by others
References
Alahi A, Vandergheynst P, Bierlaire M, Kunt M (2010) Cascade of descriptors to detect and track objects across any network of cameras. Comput Vis Image Underst 114:624–640
Bay H, Ess A, Tuytelaars T, Gool LV (2008) SURF: speeded up robust features. Comput Vis Image Underst 110(3):346–359
Chen KW, Lai CC, Hung YP, Chen CS (2008) An adaptive learning method for target tracking across multiple cameras. IEEE Conf Comput Vis Pattern Recognit
D’Angelo A, Dugelay J (2011) People re-identification in camera networks based on probabilistic color histograms. Proc Electron Imaging 2011
Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. IEEE Conf Comput Vis Pattern Recognit
Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. IEEE Int Work Perform Eval Track Surveill
Hamdoun O, Moutarde F, Stanciulescu B, Steux B (2008) Person re-identification in multi-camera system by signature based on interest point descriptors collected on short video sequences. ACM/IEEE Int Conf Distrib Smart Cameras
Havasi L, Szlavik Z, Sziranyi T (2005) Eigenwalks: walk detection and biometrics from symmetry patterns. IEEE Int Conf Image Process
Huang J, Kumar S, Mitra M, Zhu W, Zabih R (1999) Spatial color indexing and applications. Int J Comput Vis 35:245–268
Javed O, Shafique K, Shah M (2005) Appearance modeling for tracking in multiple non-overlapping cameras. IEEE Conf Comput Vis Pattern Recognit
Loy C, Xiang T, Gong S (2010) Time-delayed correlation analysis for multi-camera activity understanding. Int J Comput Vis 90:106–129
Makris D, Ellis T (2003) Automatic learning of an activity-based semantic scene model. IEEE Int Conf Adv Video Sig Based Surveill
Makris D, Ellis T, Black T (2004) Bridging the gaps between cameras. IEEE Conf Comput Vis Pattern Recognit
Oliveira I, Pio J (2009) People reidentification in a camera network. IEEE Int Conf Depend Auton Secure Comput
Perona P, Zelnik-Manor L (2004) Self-tuning spectral clustering. Adv Neural Inf Process Syst 17:1601–1608
Wang L, Tan T, Ning H, Hu W (2003) Silhouette analysis-based gait recognition for human identification. IEEE Trans Pattern Anal Mach Intell 25:1505–1518
Zong Jie X, Qiren C, Yuncai L (2012) Person re-identification by fuzzy space color histogram. Multimed Tools Appl (accept)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work is supported by China NSFC Key Program Grant No. 60833009, China NSFC Program under Grant NO. 60975012, and China National 973 Program Grant No. 2011CB302203.
Electronic supplementary material
Below is the link to the electronic supplementary material.
ESM 1
(DOCX 1092 kb)
Rights and permissions
About this article
Cite this article
Xiang, Z.J., Chen, Q. & Liu, Y. Feature correspondence in a non-overlapping camera network. Multimed Tools Appl 73, 1129–1145 (2014). https://doi.org/10.1007/s11042-013-1600-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-013-1600-z