Person Re-Identification Based on Significant Color With the Spatial Correspondence
Video surveillance has played a key role to find an individual just in case of a criminal offense. More studies were done to make the surveillance process autonomous. In this, the person re-identification technique helps to identify people. The surveillance cameras are normally mounted at a height above the head of a person. With such a position of camera, it is difficult to identify the person. Therefore, video surveillance is an application in real time. The images of the same individual may vary appreciably based on different camera field of view. Color content in an image remains an important cue to identify a person. Under the assumption that the clothing color remains unchanged over the period of surveillance, a method based on significant colors with its spatial correspondence in image is proposed. The method is applied on standard data sets like GRID, PRID450s and VIPER. The results are plotted as cumulative matching characteristic curve and compared with other methods. The approach is both computationally efficient and delivers better performance.