Real time hand tracking based on active contour model

Abstract

This paper presents active contours based method for hand tracking using color information. The main problem in active contours based approach is that results are very sensitive to location of the initial curve. Initial curve far form the object induces more heavy computational cost, low accuracy of results, as well as missing the object that has a large movement. Therefore, this paper presents a hand tracking method using a mean shift algorithm and active contours. The proposed method consists of two steps: hand localization and hand extraction. In the first step, the hand location is estimated using mean shift. And the second step, at the location, evolves the initial curve using an active contour model. To assess the effectiveness of the proposed method, it is applied to real image sequences which include moving hand.