Abstract: Aimed at the problems of classical mean-shift algorithm, which are caused by background similarities and scale change and target occlusion in the process of target tracking, a scale and orientation adaptive mean shift tracking with corrected background-weighted histogram is proposed to solve them. Combined with background-weighted histogram to extract the color histogram enhances the features of target area and reduces the track drift problems caused by background similarities and clutters. For ensuring tracking accuracy, the scale and orientation adaptive covariance matrix estimation is used to satisfy the real-time scale and orientation changes of the target. Compared with other classic mean shift algorithm, by experiments, the algorithm in this paper has improved significantly in precision and efficiency.

Key words: mean shift, background-weighted histogram, color histogram, scale and orientation adaptive

摘要： 针对经典的均值漂移算法在跟踪过程中由背景相似度、尺寸变化以及遮挡等引起的跟踪漂移问题，提出了一种基于背景加权的尺度方向自适应均值漂移跟踪算法。结合背景加权来提取目标颜色特征，充分利用了视频图像序列的空间信息，突出了目标区域的信息特征，抑制了由背景相似度和背景模糊引起的跟踪漂移现象。采用尺寸方向自适应的协方差矩阵估计方法，以适应运动目标尺寸方向的实时变化，保证了跟踪的准确性。经实验验证提出的运动目标跟踪算法较之其他经典均值漂移算法在精度和效率上都有显著提高。

关键词: 均值漂移, 背景加权, 颜色特征, 尺寸方向自适应