ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper 실환경에 강인한 dynamic programming기반의 스테레오 비전 알고리즘 개발
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
장지호, 정재찬, 임을균, 조재일
Issue Date
2011-06
Citation
대한전자공학회 종합 학술 대회 (하계) 2011, pp.956-959
Publisher
대한전자공학회
Language
Korean
Type
Conference Paper
Abstract
The stereo vision is becoming important increasingly in the field of virtual interface, gesture recognition, security, robotics, and entertainment. In this paper, we propose the stereo vision algorithm which is based on trellis dynamic programming structure using the Census Transform cost function that is robust for difference in brightness. And the algorithm use adaptive support weight for reducing steak noise and improvement of result. We optain the better result/image against only use trellis dynamic programming when we used middlebury test set and pratical image.
KSP Keywords
Adaptive support weight, Census Transform, Cost Function, Test Set, Virtual interface, Vision Algorithms, dynamic Programming, gesture recognition, stereo vision