Rotational projection statistics for 3D local surface description and object recognition

DOI10.1007/S11263-013-0627-YMaRDI QIDQ2450390zbMATH OpenOpenAlexWikidataFDO

Authors Yulan Guo, Mohammed Bennamoun, Min Lu, Jianwei Wan, Ferdous A. Sohel

Publication date 14 May 2014

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1304.3192, http://researchrepository.murdoch.edu.au/id/eprint/28367/

zbMATH Keywords

feature matching3D object recognitionlocal feature3D representationlocal reference framesurface descriptor

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Machine vision and scene understanding (68T45)

Abstract: Recognizing 3D objects in the presence of noise, varying mesh resolution, occlusion and clutter is a very challenging task. This paper presents a novel method named Rotational Projection Statistics (RoPS). It has three major modules: Local Reference Frame (LRF) definition, RoPS feature description and 3D object recognition. We propose a novel technique to define the LRF by calculating the scatter matrix of all points lying on the local surface. RoPS feature descriptors are obtained by rotationally projecting the neighboring points of a feature point onto 2D planes and calculating a set of statistics (including low-order central moments and entropy) of the distribution of these projected points. Using the proposed LRF and RoPS descriptor, we present a hierarchical 3D object recognition algorithm. The performance of the proposed LRF, RoPS descriptor and object recognition algorithm was rigorously tested on a number of popular and publicly available datasets. Our proposed techniques exhibited superior performance compared to existing techniques. We also showed that our method is robust with respect to noise and varying mesh resolution. Our RoPS based algorithm achieved recognition rates of 100%, 98.9%, 95.4% and 96.0% respectively when tested on the Bologna, UWA, Queen's and Ca' Foscari Venezia Datasets.

Recommendations

• Three-dimensional invariants and their application to object recognition
• Computer Vision - ECCV 2004
• 3D object recognition using invariants of 2D projection curves
• A multiresolutional approach to 3D object recognition
• 3D target recognition based on invariant angle contour

Cites work

• scientific article; zbMATH DE number 1703902 (Why is no real title available?)
• scientific article; zbMATH DE number 3166617 (Why is no real title available?)
• A Mathematical Theory of Communication
• Computer Vision - ECCV 2004
• Keypoints and local descriptors of scalar functions on 2D manifolds
• Multidimensional binary search trees used for associative searching
• Rotational projection statistics for 3D local surface description and object recognition
• Shape distributions
• The First Absolute Central Moment in Low-Level Image Processing

Cited in

(5)

• Deep learning-based 3D local feature descriptor from Mercator projections
• Rotational projection statistics for 3D local surface description and object recognition
• Scale-free registrations in 3D: 7 degrees of freedom with Fourier Mellin SOFT transforms
• Efficient object recognition under cluttered scenes via descriptor-based matching and single point voting
• Image matching from handcrafted to deep features: a survey

Describes a project that uses

Uses Software

• SIFT
• PCA-SIFT

This page was built for publication: Rotational projection statistics for 3D local surface description and object recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2450390)