Calibrating LiDAR and Camera using Semantic Mutual information

04/24/2021
by   Peng Jiang, et al.
0

We propose an algorithm for automatic, targetless, extrinsic calibration of a LiDAR and camera system using semantic information. We achieve this goal by maximizing mutual information (MI) of semantic information between sensors, leveraging a neural network to estimate semantic mutual information, and matrix exponential for calibration computation. Using kernel-based sampling to sample data from camera measurement based on LiDAR projected points, we formulate the problem as a novel differentiable objective function which supports the use of gradient-based optimization methods. We also introduce an initial calibration method using 2D MI-based image registration. Finally, we demonstrate the robustness of our method and quantitatively analyze the accuracy on a synthetic dataset and also evaluate our algorithm qualitatively on KITTI360 and RELLIS-3D benchmark datasets, showing improvement over recent comparable approaches.

READ FULL TEXT

page 2

page 3

page 4

research
09/21/2021

SemCal: Semantic LiDAR-Camera Calibration using Neural MutualInformation Estimator

This paper proposes SemCal: an automatic, targetless, extrinsic calibrat...
research
02/10/2023

General, Single-shot, Target-less, and Automatic LiDAR-Camera Extrinsic Calibration Toolbox

This paper presents an open source LiDAR-camera calibration toolbox that...
research
06/05/2023

Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything

The research on extrinsic calibration between Light Detection and Rangin...
research
01/27/2020

DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration

In this work, we present a novel unsupervised image registration algorit...
research
01/08/2021

Maximizing Information Gain for the Characterization of Biomolecular Circuits

Quantitatively predictive models of biomolecular circuits are important ...
research
04/16/2018

Tree Morphology for Phenotyping from Semantics-Based Mapping in Orchard Environments

Measuring tree morphology for phenotyping is an essential but labor-inte...
research
01/28/2019

The CM Algorithm for the Maximum Mutual Information Classifications of Unseen Instances

The Maximum Mutual Information (MMI) criterion is different from the Lea...

Please sign up or login with your details

Forgot password? Click here to reset