Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement
LiDAR sensors, pivotal in various fields like agriculture and robotics for tasks such as 3D object detection and map creation, are increasingly coupled with thermal cameras to harness heat information. This combination proves particularly effective in adverse conditions like darkness and rain. Ensur...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/669 |
| _version_ | 1797339320899600384 |
|---|---|
| author | Farhad Dalirani Mahmoud R. El-Sakka |
| author_facet | Farhad Dalirani Mahmoud R. El-Sakka |
| author_sort | Farhad Dalirani |
| collection | DOAJ |
| description | LiDAR sensors, pivotal in various fields like agriculture and robotics for tasks such as 3D object detection and map creation, are increasingly coupled with thermal cameras to harness heat information. This combination proves particularly effective in adverse conditions like darkness and rain. Ensuring seamless fusion between the sensors necessitates precise extrinsic calibration. Our innovative calibration method leverages human presence during sensor setup movements, eliminating the reliance on dedicated calibration targets. It optimizes extrinsic parameters by employing a novel evolutionary algorithm on a specifically designed loss function that measures human alignment across modalities. Our approach showcases a notable <inline-formula><math display="inline"><semantics><mrow><mn>4.43</mn><mo>%</mo></mrow></semantics></math></inline-formula> improvement in the loss over extrinsic parameters obtained from target-based calibration in the FieldSAFE dataset. This advancement reduces costs related to target creation, saves time in diverse pose collection, mitigates repetitive calibration efforts amid sensor drift or setting changes, and broadens accessibility by obviating the need for specific targets. The adaptability of our method in various environments, like urban streets or expansive farm fields, stems from leveraging the ubiquitous presence of humans. Our method presents an efficient, cost-effective, and readily applicable means of extrinsic calibration, enhancing sensor fusion capabilities in the critical fields reliant on precise and robust data acquisition. |
| first_indexed | 2024-03-08T09:46:15Z |
| format | Article |
| id | doaj.art-0c47c6a830794f3a82d4263442704354 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:46:15Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0c47c6a830794f3a82d42634427043542024-01-29T14:17:58ZengMDPI AGSensors1424-82202024-01-0124266910.3390/s24020669Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup MovementFarhad Dalirani0Mahmoud R. El-Sakka1Computer Science Department, Western University, London, ON N6A 3K7, CanadaComputer Science Department, Western University, London, ON N6A 3K7, CanadaLiDAR sensors, pivotal in various fields like agriculture and robotics for tasks such as 3D object detection and map creation, are increasingly coupled with thermal cameras to harness heat information. This combination proves particularly effective in adverse conditions like darkness and rain. Ensuring seamless fusion between the sensors necessitates precise extrinsic calibration. Our innovative calibration method leverages human presence during sensor setup movements, eliminating the reliance on dedicated calibration targets. It optimizes extrinsic parameters by employing a novel evolutionary algorithm on a specifically designed loss function that measures human alignment across modalities. Our approach showcases a notable <inline-formula><math display="inline"><semantics><mrow><mn>4.43</mn><mo>%</mo></mrow></semantics></math></inline-formula> improvement in the loss over extrinsic parameters obtained from target-based calibration in the FieldSAFE dataset. This advancement reduces costs related to target creation, saves time in diverse pose collection, mitigates repetitive calibration efforts amid sensor drift or setting changes, and broadens accessibility by obviating the need for specific targets. The adaptability of our method in various environments, like urban streets or expansive farm fields, stems from leveraging the ubiquitous presence of humans. Our method presents an efficient, cost-effective, and readily applicable means of extrinsic calibration, enhancing sensor fusion capabilities in the critical fields reliant on precise and robust data acquisition.https://www.mdpi.com/1424-8220/24/2/669LiDARthermal cameraextrinsic calibrationsensor fusion |
| spellingShingle | Farhad Dalirani Mahmoud R. El-Sakka Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement Sensors LiDAR thermal camera extrinsic calibration sensor fusion |
| title | Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement |
| title_full | Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement |
| title_fullStr | Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement |
| title_full_unstemmed | Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement |
| title_short | Extrinsic Calibration of Thermal Camera and 3D LiDAR Sensor via Human Matching in Both Modalities during Sensor Setup Movement |
| title_sort | extrinsic calibration of thermal camera and 3d lidar sensor via human matching in both modalities during sensor setup movement |
| topic | LiDAR thermal camera extrinsic calibration sensor fusion |
| url | https://www.mdpi.com/1424-8220/24/2/669 |
| work_keys_str_mv | AT farhaddalirani extrinsiccalibrationofthermalcameraand3dlidarsensorviahumanmatchinginbothmodalitiesduringsensorsetupmovement AT mahmoudrelsakka extrinsiccalibrationofthermalcameraand3dlidarsensorviahumanmatchinginbothmodalitiesduringsensorsetupmovement |