Robustness of Object Detectors in Degrading Weather Conditions

Muhammad Jehanzeb Mirza, Cornelius Buerkle, Julio Jarquin, Michael Opitz, Fabian Oboril, Kay Ulrich Scholl, Horst Bischof

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


State-of-the-art object detection systems for autonomous driving achieve promising results in clear weather conditions. However, such autonomous safety critical systems also need to work in degrading weather conditions, such as rain, fog and snow. Unfortunately, most approaches evaluate only on the KITTI dataset, which consists only of clear weather scenes. In this paper we address this issue and perform one of the most detailed evaluation on single and dual modality architectures on data captured in real weather conditions. We analyze the performance degradation of these architectures in degrading weather conditions. We demonstrate that an object detection architecture performing well in clear weather might not be able to handle degrading weather conditions. We also perform ablation studies on the dual modality architectures and show their limitations.

Original languageEnglish
Title of host publication2021 IEEE International Intelligent Transportation Systems Conference, ITSC 2021
PublisherInstitute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781728191423
Publication statusPublished - 19 Sep 2021
Event24th IEEE International Conference on Intelligent Transportation: ITSC 2021 - Hybrider Event, Austria
Duration: 19 Sep 202122 Sep 2021


Conference24th IEEE International Conference on Intelligent Transportation
Abbreviated title ITSC 2021
CityHybrider Event

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications


Dive into the research topics of 'Robustness of Object Detectors in Degrading Weather Conditions'. Together they form a unique fingerprint.

Cite this