Learning Invariant Color Features for Person Reidentification
Authors:
- 18 February 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 25 (7) , 3395-3410
Abstract
Matching people across multiple camera views known as person reidentification is a challenging problem due to the change in visual appearance caused by varying lighting conditions. The perceived color of the subject appears to be different under different illuminations. Previous works use color as it is or address these challenges by designing color spaces focusing on a specific cue. In this paper, we propose an approach for learning color patterns from pixels sampled from images across two camera views. The intuition behind this work is that, even though varying lighting conditions across views affect the pixel values of the same color, the final representation of a particular color should be stable and invariant to these variations, i.e., they should be encoded with the same values. We model color feature generation as a learning problem by jointly learning a linear transformation and a dictionary to encode pixel values. We also analyze different photometric invariant color spaces as well as popular color constancy algorithm for person reidentification. Using color as the only cue, we compare our approach with all the photometric invariant color spaces and show superior performance over all of them. Combining with other learned low-level and high-level features, we obtain promising results in VIPeR, Person Re-ID 2011, and CAVIAR4REID data sets.Keywords
All Related Versions
Funding Information
- Rapid-Rich Object Search Laboratory within the Interactive Digital Media Strategic Research Programme through the National Research Foundation, Singapore
- Singapore Ministry of Education Tier 2 (ARC28/14)
- Agency for Science, Technology and Research, Singapore, within the Science and Engineering Research Council (PSF1321202099)
This publication has 61 references indexed in Scilit:
- Color Models and Weighted Covariance Estimation for Person Re-identification2014
- Semi-supervised Coupled Dictionary Learning for Person Re-identification2014
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition2014
- Learning Discriminative Hierarchical Features for Object RecognitionIEEE Signal Processing Letters, 2014
- Salient Color Names for Person Re-identification2014
- Person Re-identification by Salience Matching2013
- Domain transfer for person re-identification2013
- Unsupervised Salience Learning for Person Re-identification2013
- Local Fisher Discriminant Analysis for Pedestrian Re-identification2013
- Multiple-shot person re-identification by chromatic and epitomic analysesPattern Recognition Letters, 2012