Improvement of moving object segmentation accuracy in video sequences based on adaptive symmetrical difference and background subtraction

作者：Li, J.; Xu, J.; Sang, X.^*; Wang, Y.; Yan, B.; Yu, C.

来源：Optoelectronics and Advanced Materials-Rapid Communications, 2010, 4(12): 2172-2177.

• Moving object segmentation
• Symmetrical difference
• Background subtraction
• Adaptive threshold

The segmentation accuracy of moving object in video sequences is usually influenced by illumination variation, noise, shadow, and ghost after the initially static background objects were removed. A novel algorithm combining adaptive symmetrical difference with background subtraction is proposed. The moving object mask is detected through the adaptive symmetrical difference, and points between any pairs on the contour of the mask as motion region are determined. And then, the adaptive background subtraction is carried out in the acquired region and points as motion region are labeled to extract accurate moving object. Morphological operation and shadow cancellation are adopted to refine the result. Experimental results show that the algorithm is robust and effective in improving the segmentation accuracy.

• 出版日期2010-12
• 单位司法部司法鉴定科学技术研究所; 北京邮电大学