Open AccessLocal stereo matching algorithm using modified dynamic cost computation
Author(s) -
Ahmad Fauzan Kadmin,
Rostam Affendi Hamzah,
M. N. Abd Manap,
M. Saad Hamid,
T. F. Tg. Wook
Publication year - 2021
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v22.i3.pp1312-1319
Subject(s) - computation , benchmark (surveying) , matching (statistics) , computer science , histogram , algorithm , artificial intelligence , computer vision , enhanced data rates for gsm evolution , stereopsis , image (mathematics) , mathematics , statistics , geodesy , geography
Stereo matching is an essential subject in stereo vision architecture. Traditional framework composition consists of several constraints in stereo correspondences such as illumination variations in images and inadequate or non-uniform light due to uncontrollable environments. This work improves the local method stereo matching algorithm based on the dynamic cost computation method for depth measurement. This approach utilised modified dynamic cost computation in the matching cost. A modified census transform with dynamic histogram is used to provide the cost in the cost computation. The algorithm applied the fixed-window strategy with bilateral filtering to retain image depth information and edge in the cost aggregation stage. A winner takes all (WTA) optimisation and left-right check with adaptive bilateral median filtering are employed for disparity refinement. Based on the Middlebury benchmark dataset, the algorithm developed in this work has better accuracy and outperformed several other state-of-the-art algorithms.