Object Tracking Using Joint Color-Texture Histogram

Pallavi C. Hingane, S. A. Shirsat

Abstract: Object tracking is active research topic in field of computer vision. It is widely used in many applications such as security, surveillance, traffic monitoring. Mean shift object tracking algorithm is presented in this paper by using the joint color-texture histogram to represent a target object. The objective of this work is to track moving object with help of mean shift tracking algorithm. Mean shift algorithm is implemented to increase tracking accuracy. Many tracking algorithms have been proposed to overcome difficulties arising from noise, changes in background environment. This algorithm is more suitable due to simplicity. Using only color histogram in mean shift tracking has some problems. First spatial information is lost. Second, when target has similar appearance to the background, color histogram will become invalid to distinguish them. To overcome this drawback local binary pattern method is used. The performance of this algorithm improves tracking accuracy with fewer mean shift iterations.

Keywords: Object tracking, color histogram, local binary pattern, feature extraction