一种基于特征融合的点特征目标跟踪算法

Object tracking algorithm based on the feature fusion points

联合目标的颜色和纹理特征,构造了由目标的颜色和纹理特征联合表示的特征点目标表示模型,利用Mahalanobis距离构造特征点匹配函数,利用自适应kalman滤波(AKF)算法预测特征点在下一帧图像中的位置,通过特征点匹配准确定位目标,达到实时、准确跟踪的目的。实验表明,该方法对于光线变化,目标形状相似以及目标被部分遮挡时的跟踪是有效和稳健的。

Through combining the color feature and the texture feature of the target, a target model represented by both the color and the texture of the target is constructed. A feature point matching function is built by Mahalanobis distance. Position of the feature point in the next frame of the image is predicted using Adaptive Kalman Filter（AKF）. The purpose of tracking targets in a real-time and accurate way can be realized by positioning the target accurately with feature point. Experiments show that our method is effective and robust for illumination variation, shape similarity as well as the partial-block tracking.