Title :
Object motion detection based on perceptual edge tracking
Author :
Gao, Q. ; Tan, Min
Author_Institution :
Fac. of Comput. Sci., Dalhousie Univ., Halifax, NS
Abstract :
This paper presents a method for detecting moving objects in image sequences produced by a stationary camera. The method is based on perceptual organisation. An edge tracker is developed to extract edge traces on the fly. It is both robust and fast; the method executes in real-time. Moving objects are detected and tracked within the image sequence by computing the difference between the edge-trace flows in consecutive frames. Experimental results are provided
Keywords :
edge detection; image motion analysis; image sequences; object detection; tracking; visual perception; edge trace extraction; edge tracker; edge-trace flows; image sequences; moving object tracking; object motion detection; perceptual edge tracking; perceptual organisation; real-time execution; stationary camera; Computer vision; Feature extraction; Humans; Image edge detection; Image sequences; Motion detection; Object detection; Robustness; Shape; Tracking;
Conference_Titel :
Digital and Computational Video, 2001. Proceedings. Second International Workshop on
Conference_Location :
Tampa, FL
Print_ISBN :
0-7695-1110-4
DOI :
10.1109/DCV.2001.929945
