Tracking Object Using Object-strips Color Feature

Abstract

The paper presents a new tracking scheme based on the object-strips color (OSC) feature. Firstly, the images captured by the camera are transformed into a format which is suitable for object tracking. Secondly, background subtraction method is used to detect the moving object. Then the OSC feature is represented by dividing the detected object into several strips and integrating the mean hue of each strip into a one-dimensional vector. Finally, the detected object is tracked by matching the OSC features using correlation coefficient criteria. Since the OSC feature includes both color and spatial distribution information of the detected object, the proposed method is more reliable than traditional color-based tracking algorithms. Furthermore, the OSC feature, which is a one-dimensional vector, is so simple that can satisfy the real-time requirement in video surveillance easily. The experimental results show that the proposed method has a good performance for tracking objects.