The mean- shift algorithm is generally used in trac king system,which is based on non - parametric density estimation method and produces less computational loads.The traditional mean - shift algorithm cannot effectively handle inadequate representation of target′s color distribution,invariable target model an d occlusion.Aiming to resolve these problems,an adaptive multi -feature mean - shift algorithm is proposed.In this algorithm,an improved kernel function is obtained by combining the silhouette of the target.This method could eliminate the influence of the background,various illuminations and other related limitations.Furthermore ,the color- texture histogram is extracted to achieve target model effectively.A selective update strategy is proposed to adaptively update the target model.The update sche me c ould not only eliminate the accumulated error,but also avo id drifting away.At last,extend Kalman filter (EKF) is used to estimate the pers on′s motion between consecutive frames.Compared with the traditional algorithm, the presented algorithm could track the target succe ssfully when the background has similar color and texture. In addition, t he average tracking time is 140ms/frame , which satisfie d the requirements of real - time target tracking .Experimental results show that the proposed algorithm is robust against s imilarity distraction and occlusion.