Title :
Moving object area identification using the Radon transform in image sequences
Author :
Seyedin, Seyed Alireza
Author_Institution :
Sch. of Electr. Eng., New South Wales Univ., Sydney, NSW, Australia
Abstract :
A new moving object area identification method is described in this article. The Radon transform is used to take projections along parallel directions from two consecutive frames in a monocular image sequence while the camera is stationary. The method consists of two stages: motion detection; and identification of moving object areas in rectangular regions. Moving object area identification using this method is insensitive to sudden or gradual overall illumination changes in the sequence. The method has the capability to be implemented in real time by using pipeline architecture
Keywords :
Radon transforms; computer vision; image sequences; motion estimation; object recognition; pipeline processing; real-time systems; Radon transform; camera; illumination changes; image sequences; monocular image sequence; motion detection; moving object area identification; parallel directions; pipeline architecture; real time; rectangular regions; Australia; Cameras; Computer architecture; Computer vision; Image reconstruction; Image sequences; Motion detection; Object recognition; Pipelines; Real time systems;
Conference_Titel :
Electronic Technology Directions to the Year 2000, 1995. Proceedings.
Conference_Location :
Adelaide, SA
Print_ISBN :
0-8186-7085-1
DOI :
10.1109/ETD.1995.403471
