Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving
Object detection is recognized as one of the most critical research areas for the perception of self-driving cars. Current vision systems combine visible imaging, LIDAR, and/or RADAR technology, allowing perception of the vehicle’s surroundings. However, harsh weather conditions mitigate the perform...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Journal of Imaging |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-433X/8/11/306 |
_version_ | 1797467737094619136 |
---|---|
author | Josué Manuel Rivera Velázquez Louahdi Khoudour Guillaume Saint Pierre Pierre Duthon Sébastien Liandrat Frédéric Bernardin Sharon Fiss Igor Ivanov Raz Peleg |
author_facet | Josué Manuel Rivera Velázquez Louahdi Khoudour Guillaume Saint Pierre Pierre Duthon Sébastien Liandrat Frédéric Bernardin Sharon Fiss Igor Ivanov Raz Peleg |
author_sort | Josué Manuel Rivera Velázquez |
collection | DOAJ |
description | Object detection is recognized as one of the most critical research areas for the perception of self-driving cars. Current vision systems combine visible imaging, LIDAR, and/or RADAR technology, allowing perception of the vehicle’s surroundings. However, harsh weather conditions mitigate the performances of these systems. Under these circumstances, thermal imaging becomes the complementary solution to current systems not only because it makes it possible to detect and recognize the environment in the most extreme conditions, but also because thermal images are compatible with detection and recognition algorithms, such as those based on artificial neural networks. In this paper, an analysis of the resilience of thermal sensors in very unfavorable fog conditions is presented. The goal was to study the operational limits, i.e., the very degraded fog situation beyond which a thermal camera becomes unreliable. For the analysis, the mean pixel intensity and the contrast were used as indicators. Results showed that the angle of view (AOV) of a thermal camera is a determining parameter for object detection in foggy conditions. Additionally, results show that cameras with AOVs 18° and 30° are suitable for object detection, even under thick fog conditions (from 13 m meteorological optical range). These results were extended using object detection software, with which it is shown that, for the pedestrian, a detection rate ≥90% was achieved using the images from the 18° and 30° cameras. |
first_indexed | 2024-03-09T18:56:56Z |
format | Article |
id | doaj.art-b52f28fd6abb4a6da4c9ac6e24915ef8 |
institution | Directory Open Access Journal |
issn | 2313-433X |
language | English |
last_indexed | 2024-03-09T18:56:56Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Imaging |
spelling | doaj.art-b52f28fd6abb4a6da4c9ac6e24915ef82023-11-24T05:20:59ZengMDPI AGJournal of Imaging2313-433X2022-11-0181130610.3390/jimaging8110306Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous DrivingJosué Manuel Rivera Velázquez0Louahdi Khoudour1Guillaume Saint Pierre2Pierre Duthon3Sébastien Liandrat4Frédéric Bernardin5Sharon Fiss6Igor Ivanov7Raz Peleg8Cerema Occitanie, Research Team “Intelligent Transport Systems”, 1 Avenue du Colonel Roche, 31400 Toulouse, FranceCerema Occitanie, Research Team “Intelligent Transport Systems”, 1 Avenue du Colonel Roche, 31400 Toulouse, FranceCerema Occitanie, Research Team “Intelligent Transport Systems”, 1 Avenue du Colonel Roche, 31400 Toulouse, FranceCerema Centre-Est, Research Team “Intelligent Transport Systems”, 8-10, Rue Bernard Palissy, 63017 Clermont-Ferrand, FranceCerema Centre-Est, Research Team “Intelligent Transport Systems”, 8-10, Rue Bernard Palissy, 63017 Clermont-Ferrand, FranceCerema Centre-Est, Research Team “Intelligent Transport Systems”, 8-10, Rue Bernard Palissy, 63017 Clermont-Ferrand, FranceADASKY, 7 Hamada Street, Yokneam Illit 2069206, IsraelADASKY, 7 Hamada Street, Yokneam Illit 2069206, IsraelADASKY, 7 Hamada Street, Yokneam Illit 2069206, IsraelObject detection is recognized as one of the most critical research areas for the perception of self-driving cars. Current vision systems combine visible imaging, LIDAR, and/or RADAR technology, allowing perception of the vehicle’s surroundings. However, harsh weather conditions mitigate the performances of these systems. Under these circumstances, thermal imaging becomes the complementary solution to current systems not only because it makes it possible to detect and recognize the environment in the most extreme conditions, but also because thermal images are compatible with detection and recognition algorithms, such as those based on artificial neural networks. In this paper, an analysis of the resilience of thermal sensors in very unfavorable fog conditions is presented. The goal was to study the operational limits, i.e., the very degraded fog situation beyond which a thermal camera becomes unreliable. For the analysis, the mean pixel intensity and the contrast were used as indicators. Results showed that the angle of view (AOV) of a thermal camera is a determining parameter for object detection in foggy conditions. Additionally, results show that cameras with AOVs 18° and 30° are suitable for object detection, even under thick fog conditions (from 13 m meteorological optical range). These results were extended using object detection software, with which it is shown that, for the pedestrian, a detection rate ≥90% was achieved using the images from the 18° and 30° cameras.https://www.mdpi.com/2313-433X/8/11/306thermal imagingmeterological optical rangeobject detectionoperability limits |
spellingShingle | Josué Manuel Rivera Velázquez Louahdi Khoudour Guillaume Saint Pierre Pierre Duthon Sébastien Liandrat Frédéric Bernardin Sharon Fiss Igor Ivanov Raz Peleg Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving Journal of Imaging thermal imaging meterological optical range object detection operability limits |
title | Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving |
title_full | Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving |
title_fullStr | Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving |
title_full_unstemmed | Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving |
title_short | Analysis of Thermal Imaging Performance under Extreme Foggy Conditions: Applications to Autonomous Driving |
title_sort | analysis of thermal imaging performance under extreme foggy conditions applications to autonomous driving |
topic | thermal imaging meterological optical range object detection operability limits |
url | https://www.mdpi.com/2313-433X/8/11/306 |
work_keys_str_mv | AT josuemanuelriveravelazquez analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT louahdikhoudour analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT guillaumesaintpierre analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT pierreduthon analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT sebastienliandrat analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT fredericbernardin analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT sharonfiss analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT igorivanov analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving AT razpeleg analysisofthermalimagingperformanceunderextremefoggyconditionsapplicationstoautonomousdriving |