Moving object segmentation algorithm based on cellular neural networks in the H.264 compressed domain

作者：Feng Jie^*; Chen Yaowu; Tian Xiang

来源：Optical Engineering, 2009, 48(7): 077001.

DOI：10.1117/1.3158987

• object segmentation
• adaptive motion vector filter
• cellular neural network
• H.264

A cellular neural network (CNN)-based moving object segmentation algorithm in the H. 264 compressed domain is proposed. This algorithm mainly utilizes motion vectors directly extracted from H.264 bitstreams. To improve the robustness of the motion vector information, the intramodes in I-frames are used for smooth and nonsmooth region classification, and the residual coefficient energy of P-frames is used to update the classification results first. Then, an adaptive motion vector filter is used according to interpartition modes. Finally, many CNN models are applied to implement moving object segmentation based on motion vector fields. Experiment results are presented to verify the efficiency and the robustness of this algorithm.

• 出版日期2009-7
• 单位浙江大学