TU Darmstadt / ULB / TUbiblio

Feature Fusion Information Statistics for feature matching in cluttered scenes

Zhou, Wei and Ma, Caiwen and Liao, Shenghui and Shi, Jinjing and Yao, Tong and Chang, Peng and Kuijper, Arjan (2018):
Feature Fusion Information Statistics for feature matching in cluttered scenes.
In: Computers & Graphics, pp. 50-64, 77, ISSN 00978493,
DOI: 10.1016/j.cag.2018.09.012,
[Online-Edition: https://doi.org/10.1016/j.cag.2018.09.012],
[Article]

Abstract

Object recognizing in cluttered scenes remains a largely unsolved problem, especially when applying feature matching to cluttered scenes there are many feature mismatches between the scenes and models. We propose our Feature Fusion Information Statistics (FFIS) as the calculation framework for extracting salient information from a Local Surface Patch (LSP) by a Local Reference Frame (LRF). Our LRF is defined on each LSP by projecting the scatter matrix’s eigenvectors to a plane which is perpendicular to the normal of the LSP. Based on this, our FFIS descriptor of each LSP is calculated, for which we use the combined distribution of mesh and point information in a local domain. Finally, we evaluate the speed, robustness and descriptiveness of our FFIS with the state-of-the-art methods on several public benchmarks. Our experiments show that our FFIS is fast and obtains a more reliable matching rate than other approaches in cluttered situations.

Item Type: Article
Erschienen: 2018
Creators: Zhou, Wei and Ma, Caiwen and Liao, Shenghui and Shi, Jinjing and Yao, Tong and Chang, Peng and Kuijper, Arjan
Title: Feature Fusion Information Statistics for feature matching in cluttered scenes
Language: English
Abstract:

Object recognizing in cluttered scenes remains a largely unsolved problem, especially when applying feature matching to cluttered scenes there are many feature mismatches between the scenes and models. We propose our Feature Fusion Information Statistics (FFIS) as the calculation framework for extracting salient information from a Local Surface Patch (LSP) by a Local Reference Frame (LRF). Our LRF is defined on each LSP by projecting the scatter matrix’s eigenvectors to a plane which is perpendicular to the normal of the LSP. Based on this, our FFIS descriptor of each LSP is calculated, for which we use the combined distribution of mesh and point information in a local domain. Finally, we evaluate the speed, robustness and descriptiveness of our FFIS with the state-of-the-art methods on several public benchmarks. Our experiments show that our FFIS is fast and obtains a more reliable matching rate than other approaches in cluttered situations.

Journal or Publication Title: Computers & Graphics
Volume: 77
Uncontrolled Keywords: Partial 3D model retrieval, 3D Modeling, Feature selection, Feature matching
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Date Deposited: 26 Jun 2019 11:42
DOI: 10.1016/j.cag.2018.09.012
Official URL: https://doi.org/10.1016/j.cag.2018.09.012
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item