Abstract
Person re-identification is to match pedestrian targets observed from different camera views of multi-camera surveillance systems. Aiming at the issues that the color similarity pedestrian affect the recognition result, a person re-identification method based on multi-feature fusion in perceptual uniform color space is proposed, which is according to the characteristics of human vision system. Firstly, the color space which is suitable for similar pedestrian recognition is selected from five color spaces CIELAB, S-CIELAB, IPT, LAB2000HL and CAM02-SCD. Secondly, three kinds of pedestrian appearance features are extracted including spatial weighted histogram, local color and shape feature and global texture feature. Different distance measure methods are used to calculate the similarity of three different features. Finally, the linear fusion is performed by the adaptive weights. The experimental results based on VIPeR database and ETHZ database show that the proposed method is effective and can be used for the recognition of pedestrians with visual similarity.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bedagkar-Gala A, Shah S K (2014). A survey of approaches and trends in person re-identification. Image and Vision Computing, 32(4): 270–286.
Farenzena M, Bazzani L, Perina A (2010). Person re-identification by symmetry-driven accumulation of local features. CVPR: 2360–2367.
Fan Caixia, Zhu Hong (2013). Person re-identification based on multi-features. Journal of Image and Graphics, 18(6):711–717.
Liu X, Wang H, Wu Y (2015). An ensemble color model for human re-identification. WACV: 868–875.
Ahmed E, Jones M, Marks T K (2015). An improved deep learning architecture for person re-identification. CVPR.
Du Yu-Ning, Ai Hai-Zhou (2014). A statistical inference approach for person re-identification. Journal of Electronics and Information Technology, 36(7): 1612–1618.
Qi Meibin, Tan Shengshun (2016). Multi-feature subspace and kernel learning for person re-identification. ACTA AUTOMATICA SINICA, 42(2):299–308.
LUO M R, CUI G, RIGG B (2001). The development of the CIE 2000 colour‐difference formula: CIEDE2000. Color Research & Application, 26(5): 340–350.
LUO M R, CUI G, LI C (2006). Uniform colour spaces based on CIECAM02 colour appearance model. Color Research & Application, 31(4): 320–330.
ZHANG X, WANDELL B A (1997). A spatial extension of CIELAB for digital color‐image reproduction. Journal of the Society for Information Display, 5(1): 61–63.
EBNER F, FAIRCHILD M D(1998). Development and testing of a color space (IPT) with improved hue uniformity. In proceedings of the 6th Color Imaging Conference, 11. 17–20.
LISSNER I, URBAN P (2012). Toward a unified color space for perception-based image processing. IEEE Transactions on Image Processing, 21(3): 1153–1168.
Fan Caixia,Chen Yajun (2016). Evaluation of perceptual uniform color spaces and application in image processing. Journal of Xi’an university of technology, 32(2):191–198.
Xu Y, Lin L, Zheng W S, et al (2013). Human re-identification by matching compositional template with cluster sampling. In proceedings of the IEEE International Conference on Computer Vision: 3152–3159.
Pele O, Werman M(2008). A linear time histogram metric for improved sift matching. ECCV: 495–508.
Gray D, Tao H (2008). Viewpoint invariant pedestrian recognition with an ensemble of localized features. ECCV:262–275.
Schwartz W R, Davis L S(2009). Learning discriminative appearance-based models using partial least squares. In Proceeding of Tutorials of the XXII Brazilian Symposium on Computer Graphics and Image Processing: 322–329.
Acknowledgements
This study is funded by the Doctoral scientific research start-up fund (108-451115001) and School science research program (2015CX021).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Fan, C., Chen, Y., Cao, L. (2017). Person Re-identification Based on Fusing Appearance Features in Perceptual Color Space. In: Zhao, P., Ouyang, Y., Xu, M., Yang, L., Ouyang, Y. (eds) Advanced Graphic Communications and Media Technologies . PPMT 2016. Lecture Notes in Electrical Engineering, vol 417. Springer, Singapore. https://doi.org/10.1007/978-981-10-3530-2_34
Download citation
DOI: https://doi.org/10.1007/978-981-10-3530-2_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3529-6
Online ISBN: 978-981-10-3530-2
eBook Packages: EngineeringEngineering (R0)