Title :
A stereo matching algorithm using line segment features
Author :
Kweon, Jung Jang ; Dae Kab Jang ; Kim, Seong Dae
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul, South Korea
Abstract :
A binocular-stereo-matching algorithm, based on a line matching method, which does not require the horizontal epipolar line constraint is presented. The method makes use of the line searching window determined by the epipolar lines of the extreme pixels of a given line segment and two circles whose radius is equal to the maximum possible disparity. The proposed algorithm was implemented on the KAISION-I system, designed for real-time image processing, and has been tested with various types of real scenes. The experimental results show that the proposed algorithm can be a useful tool for solving the correspondence problem in 3D computer vision
Keywords :
computer vision; computerised pattern recognition; computerised picture processing; 3D computer vision; KAISION-I system; binocular-stereo-matching algorithm; correspondence problem; epipolar lines; extreme pixels; line matching method; line searching window; maximum possible disparity; real scenes; real-time image processing; Algorithm design and analysis; Calibration; Cameras; Feature extraction; Image edge detection; Image processing; Image segmentation; Linear approximation; Real time systems; Stereo vision;
Conference_Titel :
TENCON '89. Fourth IEEE Region 10 International Conference
Conference_Location :
Bombay
DOI :
10.1109/TENCON.1989.177009
