Title :
Remaining edges linking method of motion segmentation based on edge detection
Author :
Xiang, Long ; Xiaoqing, Wu ; Xiong, Yang
Author_Institution :
Coll. of Inf. Sci. & Technol., Hainan Univ., Haikou, China
Abstract :
In our previous work, we proposed a new motion segmentation method based on edge detection. In order to solve the problem of the disconnection of edges of the object in the segmentation result, we proposed a new edge linking method in this paper. In order to reduce the influence of noise, a double threshold segmentation method is used here. From the experimental result, we found that our edge linking method is satisfaction.
Keywords :
edge detection; image motion analysis; image segmentation; double threshold segmentation method; edge detection; motion segmentation method; object edge disconnection; remaining edges linking method; Computer vision; Image edge detection; Image segmentation; Joining processes; Monitoring; Motion segmentation; Noise; Gravitation; double threshold; edge linking; motion parameter vector; motion segmentation;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on
Conference_Location :
Sichuan
Print_ISBN :
978-1-4673-0025-4
DOI :
10.1109/FSKD.2012.6233808
