一种自学习阴影检测方法

Self-learning method for shadow detection

提出一种实时学习的阴影检测方法,该方法无须用户提供监控场景信息或设定任何阈值,而是根据统计的技巧来自我学习该场景的阴影特性,进而达到阴影检测的目的。仿真结果表明,该方法可有效地实现阴影检测,并具有较强的自适应性和实时性。

This paper presented an unsupervised self-learning method to detect shadows without any priori scene information or threshold parameters.According to the statistical techniques,the method learned scene shadow characteristics actively,so as to achieve the purpose of shadow detection.Experimental results reveal the flexibility and adaptability of the proposed learning method on real surveillance scenarios.