DeepAI AI Chat
Log In Sign Up

CorAl – Are the point clouds Correctly Aligned?

09/20/2021
by   Daniel Adolfsson, et al.
oru.se
0

In robotics perception, numerous tasks rely on point cloud registration. However, currently there is no method that can automatically detect misaligned point clouds reliably and without environment-specific parameters. We propose "CorAl", an alignment quality measure and alignment classifier for point cloud pairs, which facilitates the ability to introspectively assess the performance of registration. CorAl compares the joint and the separate entropy of the two point clouds. The separate entropy provides a measure of the entropy that can be expected to be inherent to the environment. The joint entropy should therefore not be substantially higher if the point clouds are properly aligned. Computing the expected entropy makes the method sensitive also to small alignment errors, which are particularly hard to detect, and applicable in a range of different environments. We found that CorAl is able to detect small alignment errors in previously unseen environments with an accuracy of 95 achieve a substantial improvement to previous methods.

READ FULL TEXT

page 1

page 3

page 5

page 6

05/12/2022

CorAl: Introspection for Robust Radar and Lidar Perception in Diverse Environments Using Differential Entropy

Robust perception is an essential component to enable long-term operatio...
08/05/2021

Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration

Point cloud registration is a fundamental problem in 3D computer vision....
11/23/2021

GenReg: Deep Generative Method for Fast Point Cloud Registration

Accurate and efficient point cloud registration is a challenge because t...
08/21/2020

Deterministic PointNetLK for Generalized Registration

There has been remarkable progress in the application of deep learning t...
10/06/2021

DeepBBS: Deep Best Buddies for Point Cloud Registration

Recently, several deep learning approaches have been proposed for point ...
05/05/2021

Multi-Modal Loop Closing in Unstructured Planetary Environments with Visually Enriched Submaps

Future planetary missions will rely on rovers that can autonomously expl...
03/28/2020

A Benchmark for Point Clouds Registration Algorithms

Point clouds registration is a fundamental step of many point clouds pro...