Skip to Main content Skip to Navigation
Conference papers

Détection d'obstacles par vision et LiDAR par temps de brouillard pour lesvéhicules autonomes

Abstract : This work concerns the generation of a synthetic fog data-set based on available datasets in good weather conditions. A synthetic dataset is necessary because it is not always possible to collect real data under degraded conditions. In addition, post-processing such as labeling or filtering data is not easy and time-consuming. A 3D object detection algorithm for autonomous vehicles is then implemented and evaluated on the dataset produced in order to analyze the impact of the weather on its performance. In the light of the results obtained, perspectives are proposed to improve performance of the proposed method earlier.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03339637
Contributor : Ccsd Sciencesconf.Org Connect in order to contact the contributor
Submitted on : Thursday, September 9, 2021 - 3:39:48 PM
Last modification on : Tuesday, October 19, 2021 - 2:24:25 PM

File

Minh_ORASIS_2_pages.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03339637, version 1

Citation

Nguyen Anh Minh Mai, Pierre Duthon, Alain Crouzil, Louahdi Khoudour, Sergio A. Velastin. Détection d'obstacles par vision et LiDAR par temps de brouillard pour lesvéhicules autonomes. 18èmes journées francophones des jeunes chercheurs en vision par ordinateur (ORASIS 2021), Centre National de la Recherche Scientifique [CNRS]; Equipe REVA, IRIT : Institut de Recherche en Informatique de Toulouse., Sep 2021, Saint Ferréol, France. ⟨hal-03339637⟩

Share

Metrics

Record views

100

Files downloads

92