Synergetic Stereo Matching Algorithm for Occlusion and Reversal Position
Author(s) -
Tohru Irie,
Hiroshi Maeda,
Norikazu Ikoma
Publication year - 2003
Publication title -
journal of advanced computational intelligence and intelligent informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.172
H-Index - 20
eISSN - 1343-0130
pISSN - 1883-8014
DOI - 10.20965/jaciii.2003.p0178
Subject(s) - computer science , matching (statistics) , position (finance) , artificial intelligence , algorithm , blossom algorithm , computer vision , pattern recognition (psychology) , mathematics , statistics , finance , economics
We propose a stereo matching algorithm based on a pattern recognition algorithm using synergetics. Matching between left and right images is represented by the differential equations with order parameter and attention parameter. This algorithm gives us a free hand designing the two parameters. This paper presents parameter design and experiment results confirming that the proposed algorithm has high matching precision compared to the conventional template matching and DP matching.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom