The Fast Matching Algorithm for Rectified Stereo Images

Hits: 85
Dyscyplina naukowa:
Rok:
2016
Typ publikacji:
Artykuł
Słowa kluczowe:
Disparity, Stereo correspondence, Stereovision
Autorzy:
Czasopismo:
Advances in Intelligent Systems and Computing
Ilość:
471
Strony:
107-118
ISSN:
2194-5357
Punkty MNiSW:
15
Streszczenie:
In their research, the authors focus on the rapid methods for matching rectified images which can be readily implemented on mobile devices. First, the new method formatching images performs binarization of images and transforms them so that they depict edges. The disparity map is created in accordance with the principle that the correct disparity is theminimum distance of the calculated distances between a point in the left image and all the points in the right image in a given row. The method is illustrated on the basis of the authors’ own images as well as standard images from the Middlebury library. In addition, the method has been compared with well recognized and commonly used algorithms for matching images, namely variational and semi-global methods.

Copyright © 1997-2012 - Zakład Komputerowych Systemów Biomedycznych.
Uniwersytet Śląski, Wydział Informatyki i Nauki o Materiałach, Instytut Informatyki, ul. Będzińska 39, 41-200 Sosnowiec, Polska