Person re-identification based on visual saliency
- 1 November 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2012 12th International Conference on Intelligent Systems Design and Applications (ISDA)
Abstract
Person re-identification has long been a significant research direction in intelligent network surveillance. The challenging issues in person re-identification consist in pose, viewpoint and illumination changes and occlusions. In this paper, we propose a saliency based approach, which simulates the recognition process of the human brain, to tackle these issues. When people see a picture, they tend to focus on the salient areas and information in those areas is more determinant in the further matching and identification process. This so-called visual attention mechanism has long been studied and used in image segmentation, tracking, detection and recognition. To simulate this distinctive mechanism, we first calculate the saliency map which indicates the conspicuity of each pixel, and then we extract the saliency map weighted HSV histograms by giving each pixel a weight according to its saliency. We also design another feature, the salient colors, to address the occlusion problem. By opportunely combining these two features, our approach achieved state of the art performances.Keywords
This publication has 15 references indexed in Scilit:
- Person re-identification by probabilistic relative distance comparisonPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- A Multiple Component Matching Framework for Person Re-identificationLecture Notes in Computer Science, 2011
- Person re-identification by symmetry-driven accumulation of local featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Stel component analysis: Modeling spatial correlations in image class structurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A fast MPEG-7 dominant color extraction with new similarity measure for image retrievalJournal of Visual Communication and Image Representation, 2008
- Continuously Tracking Objects Across Multiple Widely Separated CamerasPublished by Springer Science and Business Media LLC ,2007
- Similarity templates for detection and recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A saliency-based search mechanism for overt and covert shifts of visual attentionVision Research, 2000
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Is complexity theory appropriate for analyzing biological systems?Behavioral and Brain Sciences, 1991