상세정보
학술대회
Accurate Dense Stereo Matching of Slanted Surfaces Using 2D Integral Images
- 발행일
- 201306
- 출처
- International Conference on Computer Vision Systems (ICVS) 2013 (LNCS 7963), v.7963, pp.284-293
- 협약과제
- 13ZC1100, 지능형 상황인지 및 IOT 기반 기술개발, 함호상
- 초록
- This paper presents an advanced algorithm providing accurate stereo correspondences of two frames through concise disparity gradient estimation at the per-pixel level and 2D integral images. The key contributions of this novel algorithm are twofold: First, combining an upright cross-based support region with disparity gradient estimation realizes the implicit construction of a 3D support region for each anchor pixel. This approach yields the disparity accuracy for slanted surfaces as well as fronto-parallel surfaces. Second, the 2D integral image technique leads to a speedup of matching cost aggregation in the implicit 3D support regions. The experimental results show that the proposed algorithm can successfully convey the correspondences of actual sequence of outdoor stereo images and Middlebury stereo images with high accuracy in near real time. © 2013 Springer-Verlag.
- KSP 제안 키워드
- Dense stereo matching, High accuracy, Integral Image Technique, Near real time, Novel algorithm, Parallel surfaces, cost aggregation, gradient estimation, stereo images