Person Re-identification Based on Color Histogram and Spatial Configuration of Dominant Color Regions
This addresses the problem of identifying individuals across different cameras for surveillance, but it appears incremental as it builds on existing appearance-based approaches.
The paper tackles person re-identification in video surveillance by proposing a method based on dominant color histogram and spatial configuration of color regions, which is evaluated on benchmark datasets using CMC curves to show effectiveness.
There is a requirement to determine whether a given person of interest has already been observed over a network of cameras in video surveillance systems. A human appearance obtained in one camera is usually different from the ones obtained in another camera due to difference in illumination, pose and viewpoint, camera parameters. Being related to appearance-based approaches for person re-identification, we propose a novel method based on the dominant color histogram and spatial configuration of dominant color regions on human body parts. Dominant color histogram and spatial configuration of the dominant color regions based on dominant color descriptor(DCD) can be considered to be robust to illumination and pose, viewpoint changes. The proposed method is evaluated using benchmark video datasets. Experimental results using the cumulative matching characteristic(CMC) curve demonstrate the effectiveness of our approach for person re-identification.