Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles

Multimodal sensor systems require precise calibration if they are to be used in the field. Due to the difficulty of obtaining the corresponding features from different modalities, the calibration of such systems is an open problem. We present a systematic approach for calibrating a set of cameras wi...

Full description

Bibliographic Details
Main Authors: Jon Muhovič, Janez Perš
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/12/5676
_version_ 1797592646403751936
author Jon Muhovič
Janez Perš
author_facet Jon Muhovič
Janez Perš
author_sort Jon Muhovič
collection DOAJ
description Multimodal sensor systems require precise calibration if they are to be used in the field. Due to the difficulty of obtaining the corresponding features from different modalities, the calibration of such systems is an open problem. We present a systematic approach for calibrating a set of cameras with different modalities (RGB, thermal, polarization, and dual-spectrum near infrared) with regard to a LiDAR sensor using a planar calibration target. Firstly, a method for calibrating a single camera with regard to the LiDAR sensor is proposed. The method is usable with any modality, as long as the calibration pattern is detected. A methodology for establishing a parallax-aware pixel mapping between different camera modalities is then presented. Such a mapping can then be used to transfer annotations, features, and results between highly differing camera modalities to facilitate feature extraction and deep detection and segmentation methods.
first_indexed 2024-03-11T01:57:07Z
format Article
id doaj.art-7ddca5a2615c42c68ea38a987cff4bf9
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-11T01:57:07Z
publishDate 2023-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-7ddca5a2615c42c68ea38a987cff4bf92023-11-18T12:34:30ZengMDPI AGSensors1424-82202023-06-012312567610.3390/s23125676Joint Calibration of a Multimodal Sensor System for Autonomous VehiclesJon Muhovič0Janez Perš1Faculty of Electrical Engineering, University of Ljubljana, Tržaška Cesta 25, SI-1000 Ljubljana, SloveniaFaculty of Electrical Engineering, University of Ljubljana, Tržaška Cesta 25, SI-1000 Ljubljana, SloveniaMultimodal sensor systems require precise calibration if they are to be used in the field. Due to the difficulty of obtaining the corresponding features from different modalities, the calibration of such systems is an open problem. We present a systematic approach for calibrating a set of cameras with different modalities (RGB, thermal, polarization, and dual-spectrum near infrared) with regard to a LiDAR sensor using a planar calibration target. Firstly, a method for calibrating a single camera with regard to the LiDAR sensor is proposed. The method is usable with any modality, as long as the calibration pattern is detected. A methodology for establishing a parallax-aware pixel mapping between different camera modalities is then presented. Such a mapping can then be used to transfer annotations, features, and results between highly differing camera modalities to facilitate feature extraction and deep detection and segmentation methods.https://www.mdpi.com/1424-8220/23/12/5676USVcalibrationmultimodal systemannotationautonomous vehicle
spellingShingle Jon Muhovič
Janez Perš
Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles
Sensors
USV
calibration
multimodal system
annotation
autonomous vehicle
title Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles
title_full Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles
title_fullStr Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles
title_full_unstemmed Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles
title_short Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles
title_sort joint calibration of a multimodal sensor system for autonomous vehicles
topic USV
calibration
multimodal system
annotation
autonomous vehicle
url https://www.mdpi.com/1424-8220/23/12/5676
work_keys_str_mv AT jonmuhovic jointcalibrationofamultimodalsensorsystemforautonomousvehicles
AT janezpers jointcalibrationofamultimodalsensorsystemforautonomousvehicles