TU Darmstadt / ULB / TUbiblio

Histograms of Gaussian normal distribution for 3D feature matching in cluttered scenes

Zhou, Wei and Ma, Caiwen and Yao, Tong and Chang, Peng and Zhang, Qi and Kuijper, Arjan (2019):
Histograms of Gaussian normal distribution for 3D feature matching in cluttered scenes.
35, In: The Visual Computer, (4), pp. 489-505, ISSN 0178-2789, DOI: 10.1007/s00371-018-1478-x,
[Online-Edition: https://doi.org/10.1007/s00371-018-1478-x],
[Article]

Abstract

3D feature descriptors provide essential information to find given models in captured scenes. In practical applications, these scenes often contain clutter. This imposes severe challenges on the 3D object recognition leading to feature mismatches between scenes and models. As such errors are not fully addressed by the existing methods, 3D feature matching still remains a largely unsolved problem. We therefore propose our Histograms of Gaussian Normal Distribution (HGND) for capturing salient feature information on a local reference frame (LRF) that enables us to solve this problem. We define a LRF on each local surface patch by using the eigenvectors of the scatter matrix. Different from the traditional local LRF-based methods, our HGND descriptor is based on the combination of geometrical and spatial information without calculating the distribution of every point and its geometrical information in a local domain. This makes it both simple and efficient. We encode the HGND descriptors in a histogram by the geometrical projected distribution of the normal vectors. These vectors are based on the spatial distribution of the points.We use three public benchmarks, the Bologna, the UWA and the Ca’ Foscari Venezia dataset, to evaluate the speed, robustness, and descriptiveness of our approach. Our experiments demonstrate that the HGND is fast and obtains a more reliable matching rate than state-of-the-art approaches in cluttered situations.

Item Type: Article
Erschienen: 2019
Creators: Zhou, Wei and Ma, Caiwen and Yao, Tong and Chang, Peng and Zhang, Qi and Kuijper, Arjan
Title: Histograms of Gaussian normal distribution for 3D feature matching in cluttered scenes
Language: English
Abstract:

3D feature descriptors provide essential information to find given models in captured scenes. In practical applications, these scenes often contain clutter. This imposes severe challenges on the 3D object recognition leading to feature mismatches between scenes and models. As such errors are not fully addressed by the existing methods, 3D feature matching still remains a largely unsolved problem. We therefore propose our Histograms of Gaussian Normal Distribution (HGND) for capturing salient feature information on a local reference frame (LRF) that enables us to solve this problem. We define a LRF on each local surface patch by using the eigenvectors of the scatter matrix. Different from the traditional local LRF-based methods, our HGND descriptor is based on the combination of geometrical and spatial information without calculating the distribution of every point and its geometrical information in a local domain. This makes it both simple and efficient. We encode the HGND descriptors in a histogram by the geometrical projected distribution of the normal vectors. These vectors are based on the spatial distribution of the points.We use three public benchmarks, the Bologna, the UWA and the Ca’ Foscari Venezia dataset, to evaluate the speed, robustness, and descriptiveness of our approach. Our experiments demonstrate that the HGND is fast and obtains a more reliable matching rate than state-of-the-art approaches in cluttered situations.

Journal or Publication Title: The Visual Computer
Volume: 35
Number: 4
Uncontrolled Keywords: Feature matching, Partial 3D model retrieval, 3D Model reconstruction, Shape matching
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Date Deposited: 26 Jun 2019 11:43
DOI: 10.1007/s00371-018-1478-x
Official URL: https://doi.org/10.1007/s00371-018-1478-x
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)

View Item View Item