Share Email Print

Proceedings Paper

Edge-aware stereo matching with O(1) complexity
Author(s): Cevahir Çiğla; A. Aydin Alatan
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, a novel local stereo matching algorithm is introduced, providing precise disparity maps with low computational complexity. Following the common steps of local matching methods, namely cost calculation, aggregation, minimization and occlusion handling; the time consuming intensity dependent aggregation procedure is improved in terms of both speed and precision. For this purpose, a novel approach, denoted as permeability filtering (PF), is introduced, engaging computationally efficient two pass integration approach by weighted and connected support regions. The proposed approach exploits a new paradigm, separable successive weighted summation (SWS), among horizontal and vertical directions enabling constant operational complexity for adaptive filtering, as well as providing connected 2D support regions. Once aggregation of the cost values for each disparity candidate is performed independently, minimization is achieved by winner-take-all approach. The same procedure is also utilized to diffuse information through overlapped pixels during occlusion handling, after detecting unreliable disparity assignments. According to the experimental results on Middlebury stereo benchmark, the proposed method outperforms the state-of-the- art local methods in terms of precision and computational efficiency through unifying constant time filtering and weighted aggregation.

Paper Details

Date Published: 30 January 2012
PDF: 11 pages
Proc. SPIE 8290, Three-Dimensional Image Processing (3DIP) and Applications II, 829002 (30 January 2012); doi: 10.1117/12.906140
Show Author Affiliations
Cevahir Çiğla, Middle East Technical Univ. (Turkey)
VESTEK Electronics Research and Development Corp. (Turkey)
A. Aydin Alatan, Middle East Technical Univ. (Turkey)

Published in SPIE Proceedings Vol. 8290:
Three-Dimensional Image Processing (3DIP) and Applications II
Atilla M. Baskurt; Robert Sitnik, Editor(s)

© SPIE. Terms of Use
Back to Top