Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition

09/07/2017
by   Anders Glent Buch, et al.
0

It is possible to associate a highly constrained subset of relative 6 DoF poses between two 3D shapes, as long as the local surface orientation, the normal vector, is available at every surface point. Local shape features can be used to find putative point correspondences between the models due to their ability to handle noisy and incomplete data. However, this correspondence set is usually contaminated by outliers in practical scenarios, which has led to many past contributions based on robust detectors such as the Hough transform or RANSAC. The key insight of our work is that a single correspondence between oriented points on the two models is constrained to cast votes in a 1 DoF rotational subgroup of the full group of poses, SE(3). Kernel density estimation allows combining the set of votes efficiently to determine a full 6 DoF candidate pose between the models. This modal pose with the highest density is stable under challenging conditions, such as noise, clutter, and occlusions, and provides the output estimate of our method. We first analyze the robustness of our method in relation to noise and show that it handles high outlier rates much better than RANSAC for the task of 6 DoF pose estimation. We then apply our method to four state of the art data sets for 3D object recognition that contain occluded and cluttered scenes. Our method achieves perfect recall on two LIDAR data sets and outperforms competing methods on two RGB-D data sets, thus setting a new standard for general 3D object recognition using point cloud data.

READ FULL TEXT
research
04/24/2020

YCB-M: A Multi-Camera RGB-D Dataset for Object Recognition and 6DoF Pose Estimation

While a great variety of 3D cameras have been introduced in recent years...
research
02/17/2016

Density-based Denoising of Point Cloud

Point cloud source data for surface reconstruction is usually contaminat...
research
07/05/2017

Exploration of object recognition from 3D point cloud

We present our latest experiment results of object recognition from 3D p...
research
07/30/2022

Neural Correspondence Field for Object Pose Estimation

We propose a method for estimating the 6DoF pose of a rigid object with ...
research
03/07/2022

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

In this paper, we tackle the problem of category-level 9D pose estimatio...
research
05/07/2022

BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation

The challenges of learning a robust 6D pose function lie in 1) severe oc...
research
12/06/2012

Autonomous Navigation by Robust Scan Matching Technique

For effective autonomous navigation,estimation of the pose of the robot ...

Please sign up or login with your details

Forgot password? Click here to reset