人体运动检测的光流与肤色融合方法

Detection of Human Motion Using a Fusion Method Based on Optical Flow and Skin Color

针对复杂背景环境中光流法难以检测出完整的人体目标区域的问题,提出了一种融合光流和肤色信息的人体运动检测方法.对视频序列进行光流分析,确定目标的运动区域;同时基于马氏距离检测出肤色区域;并对光流和肤色信息进行数据融合,分割出人体运动区域.实验结果表明,该方法能够有效地检测出完整的人体目标.

Optical flow algorithm has its difficultly in detecting the whole human region in the complex environment. An integrated method of detecting human motion based on optical flow and skin color is proposed. The motion region is detected by optical flow computation. Skin detection then concurred by computing the Mahalanobis distance. A whole object is detected by a fusion method based on optical flow and skin color. Experimental results showed that the method permits the detection of the whole human object.