Target-less camera-LiDAR extrinsic calibration using a bagged dependence estimator

The goal of this study is to achieve automatic extrinsic calibration of a camera-LiDAR system that does not require calibration targets. Calibration through maximization of statistical dependence using mutual information (MI) is a promising approach. However, we observed that existing methods perfor...

Full description

Saved in:
Bibliographic Details
Main Authors: Irie, Kiyoshi, Sugiyama, Masashi, Tomono, Masahiro
Format: Conference Proceeding
Language:English
Subjects:
Calibration
Cameras
Feature extraction
Image edge detection
Laser radar
Robot sensing systems
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The goal of this study is to achieve automatic extrinsic calibration of a camera-LiDAR system that does not require calibration targets. Calibration through maximization of statistical dependence using mutual information (MI) is a promising approach. However, we observed that existing methods perform poorly on outdoor data sets. Because of their susceptibility to noise, objective functions of previous methods tend to be non-smooth, and gradient-based searches fail in local optima. To overcome these issues, we introduce a novel dependence estimator called bagged least-squares mutual information (BLSMI). BLSMI is a combination of methods composed of a kernel-based dependence estimator and noise reduction by bootstrap aggregating (bagging), which can handle richer features and robustly estimate dependence. We compared ours with previous methods using indoor and outdoor data sets, and observed that our method performed best in terms of calibration accuracy. While previous methods showed degraded performance on outdoor data sets because of the local optima problem, our method exhibited high calibration accuracy both on indoor and outdoor data sets.
ISSN:2161-8089
DOI:10.1109/COASE.2016.7743564