Adaptive image segmentation based on color clustering for person re-identification
Person re-identification refers to identifying a particular person who has occurred in the monitoring network automatically by computer in the surveillance video, which is significantly important for the improvement of intelligence of video monitoring. But the research of person re-identification is not mature and facing many challenges. The following factors may lead to a certain difference for the same person in different monitoring video images; for example: the illumination changing in the monitoring environment, the shooting angle difference, and the posture difference. These may lead to low recognition accuracy. In this paper, a new appearance-based person re-identification method was proposed and an investigation was launched on the following topics for the improvement of recognition accuracy. First, a simple and feasible method for color invariants was proposed, so that the affection of color by change of illumination and shooting angle could be eliminated. Then, a highly adaptive image segmentation method based on color clustering and a color feature representation scheme for specific color characteristics were designed, which could help to extract color features in more reasonable points. Finally, an effective similarity measure criterion was obtained through QSF measure learning, which could ensure that the different pedestrians can be distinguished and was better able to capture the visual change of the same person. In addition, the traditional evolutionary algorithm was improved and applied to the process of iterative computation for QSF. The experimental results show that our method is an effective way for the person re-identification problem.
KeywordsPerson re-identification Adaptive image segmentation Color invariants Color clustering Evolutionary algorithm
This work was jointly supported by the Natural Science Foundation of Guangdong Province of China (#2015A030313408), and Natural Science Foundation of China (#61573157).
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Bak S, Corvee E, Bremond F, Thonnat M (2010) Person re-identification using spatial covariance regions of human body parts. In: IEEE Int’l conf. advanced video and signal based surveillance, pp 435–440Google Scholar
- Baltieri D, Vezzani R, Cucchiara R (2014) Mapping appearance descriptors on 3d body models for people re-identification. Int J Comput Vis 111(3):345–364Google Scholar
- Bezdek JC, Ehrlich R, Full W (1984) Fcm: the fuzzy c-means clustering algorithm. In: Intl. Conf. on image analysis and recognition, vol 10, pp 191–203Google Scholar
- Cheng DS, Cristani M, Stoppa M (2011) Custom pictorial structures for re-identification. In: BMVC2011, vol 2, pp 1–6Google Scholar
- Du YN, Ai HZ (2014) A statistical inference approach for person re-identification. J Electron Inf Technol 36(7):1612–1618Google Scholar
- Fan CX, Zhu H, Lin GF, Luo L (2013) Person re-identification based on multi-features. J Image Graph 18:711–717Google Scholar
- Farenzena M, Bazzani L, Perina A, Murino M, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: IEEE conference computer vision and pattern recognition, pp 2360–2367Google Scholar
- Funt BV, Finlayson GD (1995) Color constancy color indexing. In: IEEE trans on pattern analysis and machine intelligence, vol 17, pp 522–529Google Scholar
- Graham DF, Bernt S, James LC (1998) Comprehensive colour image normalization. In: Proceedings of the 5th European conference on computer vision, vol 1, pp 475–490Google Scholar
- Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensamble of localized features. In: ECCV2008, pp 262–275Google Scholar
- Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: IEEE International workshop on performance evaluation for tracking and surveillance, vol 3Google Scholar
- Hahnel M, Klunder D, Kraiss KF (2004) Color and texture features for person recognition. In: Neural networks 2004 proceedings, vol 1Google Scholar
- Harandi M, Salzmann M, Porikli F (2014) Regman divergences for infinite dimensional covariance matrice. In: IEEE conference on computer vision and pattern recognitionGoogle Scholar
- Hartigan JA, Wong MA (1979) Algorithm as 136: a k-means clustering algorithm. Appl Stat, pp 100–108Google Scholar
- Holland JH (1992) Adaptation in natural and artificial systems: an introductory analysis with application to biology. In: Control and arterial intelligenceGoogle Scholar
- Joachims T (2002) Optimizing search engines using click through data. In: Proceedings of the eighth ACM SIGKDD international conference, pp 133–142Google Scholar
- Prosser B, Zheng WS, Gong S, Xiang T (2010) Person re-identification by support vector ranking. In: Proc. British machine vision conf. vol 1, pp 1–5Google Scholar
- Venkatesan S, Madane SR (2012) Face recognition system with genetic algorithm and ant colony optimization. Int J Innov Manag Technol 1:469–471Google Scholar
- Wang X, Doretto G, SebastianT, Rittscher J, Tu P (2007) Shape and appearance context modeling. In: Proc. IEEE Int’l Conf. computer vision, pp 1–8Google Scholar
- Weijer J, Sehlnid C (2006) Blur robust and color constant image description. In: Proc. of Int. Conf. on image processing, pp 993–996Google Scholar
- Zheng WS, Gong S, Xiang T (2013) Reidentification by relative distance comparision. In: IEEE tansaction on pattern analysis and machine intelligenceGoogle Scholar
- Zhu W, Liang S, Wei Y (2014) Saliency optimization from robust background detection. In: IEEE conference on computer vision and pattern recognition, pp 2814–2821Google Scholar