Real-time Weather Monitoring and Desnowification through Image Purification - IRT SystemX Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Real-time Weather Monitoring and Desnowification through Image Purification

Eliott Py
  • Fonction : Auteur
Elies Gherbi
  • Fonction : Auteur
  • PersonId : 1064617
Martin Gonzalez
  • Fonction : Auteur
Hatem Hajri
  • Fonction : Auteur
  • PersonId : 1086606

Résumé

Object detection and tracking are essential for reliable decision-making in modern applications such as self-driving cars, drones, and industry. Adverse weather can hinder object detectability and pose a threat to the reliability of these systems. As a result, there is an increasing need for efficient image denoising and restoration techniques. In this study, we investigate the use of image purification as a means of defending against weather corruptions. Specifically, we focus on the effect of snow on an object detector and the benefits of efficient desnowification. We find that the performance of a strong image purifying baseline (PreNet) is not constant across different levels of snow intensity, leading to a reduced overall performance in diverse situations. Through extensive experimentation, we demonstrate that adding a lightweight snow detector significantly improves the overall object detection performance without needing to modify the purification model. Our proposed weather-robust architecture exhibits a 40% performance improvement compared to a strong image purification baseline on the gas cylinder counting task. In addition, it leads to significant reductions of the computational power required to run the purification pipeline with a minimal added cost.
Fichier principal
Vignette du fichier
AAAI_Press_Formatting_Instructions_for_Authors_Using_LaTeX-7.pdf (3.03 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03970670 , version 1 (02-02-2023)

Licence

Copyright (Tous droits réservés)

Identifiants

  • HAL Id : hal-03970670 , version 1

Citer

Eliott Py, Elies Gherbi, Nelson Fernandez Pinto, Martin Gonzalez, Hatem Hajri. Real-time Weather Monitoring and Desnowification through Image Purification. Workshop AITA AI Trustworthiness Assessment - AAAI Spring Symposium, Mar 2023, San Francisco, CA, United States. ⟨hal-03970670⟩
228 Consultations
81 Téléchargements

Partager

Gmail Facebook X LinkedIn More