Title :
Fast multiple motion video segmentation
Author :
Xu, Dong ; Li, Xuelong
Author_Institution :
Dept. of Electron. Eng. & Inf. Sci., Univ. of Sci. & Technol. of China, Anhui, China
Abstract :
This paper proposes a novel fast scheme to deal with multiple motion video, which contains more than one different motion objects. Change detection methods are employed under some essential prior knowledge, and the computing complexity is low. Experimental results show that the presented algorithm performs well for the multiple motion video, efficiently and effectively.
Keywords :
image motion analysis; image segmentation; object detection; change detection methods; computational complexity; motion objects; multiple motion video segmentation; Cameras; Change detection algorithms; Image motion analysis; Image segmentation; Information science; Layout; Merging; Object detection; Optical filters; Video sequences;
Conference_Titel :
Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
0-7803-7702-8
DOI :
10.1109/ICNNSP.2003.1281214
