基于分块变化检测的人体肢体运动跟踪

Human Limbs Motion Tracking Based on Blocking and Change Detection

人体运动跟踪是基于视频的人体运动分析的关键技术之一.提出了一种新的人体肢体运动的跟踪方法,通过基于分块的帧间变化检测和二维人体块模型检测出人体运动区域,利用背景统计的技术从累积的帧差信息中构建出完整的背景区域,进而从运动区域中提取出头部和四肢的区域,通过区域形状分析确定各肢体区域的位置信息,从而判断出关节点的位置.实验证明,该方法可以对人体肢体的大幅度运动进行跟踪.

The human motion tracking is a key technique of video based on human motion analysis. A new method to track human limbs motion is brought forward in this paper. Firstly, detect the human moving region with the change detection between frames based on blocking and 2D human block model, and construct complete background region from the accumulated frame difference information by using background statistical technology. Then pick up the head and limbs region from the moving region, define the location information of the limbs region with the analysis of region shape, and judge the location of the joints. The experimental results show that the method can track large human limbs motion.