| Title: |
Would SWIR modality help for detection and segmentation in harsh weather conditions? An experimental study. |
| Authors: |
Mehra, Rohan; Riffard, Alexandre; Labussière, Mathieu; Duthon, Pierre; Aufrère, Romuald |
| Contributors: |
Institut Pascal (IP); Centre National de la Recherche Scientifique (CNRS)-Université Clermont Auvergne (UCA)-Institut national polytechnique Clermont Auvergne (INP Clermont Auvergne); Université Clermont Auvergne (UCA)-Université Clermont Auvergne (UCA); Indian Institute of Science Education and Research Bhopal (IISER Bhopal); Centre d'Etudes et d'Expertise sur les Risques, l'Environnement, la Mobilité et l'Aménagement (Cerema); This work was supported by the International Research Center “Innovation Transportation and Production Systems” of the I-SITE CAP 20-25. |
| Source: |
Multispectral Imaging for Robotics and Automation workshop at the 2025 IEEE/CVF International Conference on Computer Vision (ICCV 2025) ; https://hal.science/hal-05330067 ; Multispectral Imaging for Robotics and Automation workshop at the 2025 IEEE/CVF International Conference on Computer Vision (ICCV 2025), Oct 2025, Honolulu, HI, United States ; https://iccv.thecvf.com/virtual/2025/index.html |
| Publisher Information: |
CCSD |
| Publication Year: |
2025 |
| Collection: |
HAL Clermont Auvergne (Université Blaise Pascal Clermont-Ferrand / Université d'Auvergne) |
| Subject Terms: |
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]; [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] |
| Subject Geographic: |
Honolulu; HI; United States |
| Description: |
International audience ; In the context of road perception for autonomous vehicles, short-wave infrared (SWIR) has opened up new perspectives beyond the visible spectrum, which is prone to performance degradation in harsh weather conditions like fog, rain and dust. This paper aims to analyze the feasibility of using SWIR images to enhance object detection and segmentation in such weather conditions. In our experiments, we used data obtained from three different cameras -including two SWIR technologies and a conventional visible camera -in different weather conditions. The conditions include a clear day for reference, rain at different rainfall rates, and fog at different visibility ranges. We explored the performance of several deep learning algorithms, originally trained on images from visible domain applied directly to SWIR images. Quantitative and qualitative analyses for detection and segmentation were conducted. When applied to SWIR modalities, the algorithms prove to perform comparatively to visible in the reference case and to improve detection and segmentation in harsh weather cases. |
| Document Type: |
conference object |
| Language: |
English |
| Availability: |
https://hal.science/hal-05330067; https://hal.science/hal-05330067v1/document; https://hal.science/hal-05330067v1/file/Mehra_Would_SWIR_modality_help_for_detection_and_segmentation_in_harsh_ICCVW_2025_paper.pdf |
| Rights: |
http://creativecommons.org/licenses/by-nc/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.3B317133 |
| Database: |
BASE |