Superpixel-guided two-view deterministic geometric model fitting
Document Type
Journal Article
Publication Title
International Journal of Computer Vision
Publisher
Springer New York LLC
School
School of Science
RAS ID
28116
Abstract
Geometric model fitting is a fundamental research topic in computer vision and it aims to fit and segment multiple-structure data. In this paper, we propose a novel superpixel-guided two-view geometric model fitting method (called SDF), which can obtain reliable and consistent results for real images. Specifically, SDF includes three main parts: a deterministic sampling algorithm, a model hypothesis updating strategy and a novel model selection algorithm. The proposed deterministic sampling algorithm generates a set of initial model hypotheses according to the prior information of superpixels. Then the proposed updating strategy further improves the quality of model hypotheses. After that, by analyzing the properties of the updated model hypotheses, the proposed model selection algorithm extends the conventional “fit-and-remove” framework to estimate model instances in multiple-structure data. The three parts are tightly coupled to boost the performance of SDF in both speed and accuracy, and SDF has the deterministic nature. Experimental results show that the proposed SDF has significant advantages over several state-of-the-art fitting methods when it is applied to real images with single-structure and multiple-structure data. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.
DOI
10.1007/s11263-018-1100-8
Access Rights
subscription content
Comments
Xiao, G., Wang, H., Yan, Y., & Suter, D. (2019). Superpixel-guided two-view deterministic geometric model fitting. International Journal of Computer Vision, 127(4), 323-339. Available here.