Rotational Projection Statistics for 3D Local Surface Description and Object Recognition

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.

The final publication is available at link.springer.com International Journal of Computer Vision 2013

Cited by in corpus (20)

• A review on deep learning techniques for 3D sensed data classification
• Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
• Dense 3D Face Correspondence
• Learning general and distinctive 3D local deep descriptors for point cloud registration
• A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation
• Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition
• Point Cloud Registration for LiDAR and Photogrammetric Data: a Critical Synthesis and Performance Analysis on Classic and Deep Learning Algorithms
• A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registration
• Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
• LiDAR-Based Place Recognition For Autonomous Driving: A Survey
• Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching
• MGCN: Descriptor Learning using Multiscale GCNs
• DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds
• Radial Intersection Count Image: a Clutter Resistant 3D Shape Descriptor
• PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling
• Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds
• An Indexing Scheme and Descriptor for 3D Object Retrieval Based on Local Shape Querying
• Learning Dense Features for Point Cloud Registration Using a Graph Attention Network
• Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching
• Single and Cross-Dimensional Feature Detection and Description: An Evaluation