Confidence-based iterative efficient large-scale stereo matching
نویسندگان
چکیده
منابع مشابه
Efficient Large-Scale Stereo Matching
In this paper we propose a novel approach to binocular stereo for fast matching of high-resolution images. Our approach builds a prior on the disparities by forming a triangulation on a set of support points which can be robustly matched, reducing the matching ambiguities of the remaining points. This allows for efficient exploitation of the disparity search space, yielding accurate dense recon...
متن کاملStereo Matching Based on Iterative Incompatibility Revision
The most important probIem remaining In 3D information recovery by stereopsis is the matchlng problem. A new segment-based stereo matching method. which achieves high stereo matchhg correctness for large vergence-angle stereo palm, Is presented. The algorithms used are [a) incornpatlbllity dissolution by lteratlve revision. (bl llmitauon or allowable drsparlty range sultable for vegence-stereop...
متن کاملConfidence-Based Surface Prior for Energy-Minimization Stereo Matching
This paper presents a novel confidence-based surface prior for energy minimization formulations of dense stereo matching. Given a dense disparity estimation we fit planes, in disparity space, to regions of the image. For each pixel, the probability of its depth lying on an object plane is modeled as a Gaussian distribution, whose variance is determined using the confidence from a previous match...
متن کاملRobust Real-Time Stereo Edge Matching by Confidence-Based Refinement
Edges are important features for tasks like object detection and vision-based navigation. In this paper, a novel real-time capable stereo edge refinement technique is presented. It propagates confidence and consistency along the detected edges, which reduces false matches significantly. Unmatched pixels are safely recovered by interpolation. We also investigate suitable support regions for edge...
متن کاملLeveraging Stereo Matching with Learning-based Confidence Measures (Supplementary Material)
1. Confidence measures We used a variety of confidence measures in [1–5] for constructing the 22-dimensional feature vector f. Before explaning each of them, we introduce a few notations to explain confidence measures in a simple and clear way. Instead of using C(p, d) as a matching cost, we use ci as the i th minimum matching cost among all disparity hypotheses D for p. di is the corresponding...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Cogent Engineering
سال: 2018
ISSN: 2331-1916
DOI: 10.1080/23311916.2018.1427676