Alleviating cavity problems in moving object detection based on hysteresis thresholding and multi-models

Traditional background modeling methods often require complicated computations and suffer from cavity problems in foreground objects. In this paper, we propose a block-based background modeling method combining multiple detection results derived from color and texture characteristics. This method can significantly alleviate the cavity problem and resist certain shadow interference. Since the proposed scheme only requires low complexity, it is suitable for real-time applications.