Unsupervised Image Dataset Annotation Framework for Snow Covered Road Networks

Mohamed Karaa, Hakim Ghazzai, Lokman Sboui, Hichem Besbes, Yehia Massoud

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

3 Scopus citations

Abstract

Road surface condition estimation plays a crucial role in road safety and maintenance, especially in adverse weather conditions like snowfall. In this paper, we introduce a framework for unsupervised annotation of a dataset describing road snow cover level. This framework relies on feature learning using autoencoders and graph clustering using the Louvain community detection algorithm. We also incorporate time and weather data to facilitate the annotation process. We evaluate our method by assessing its different steps and comparing it to another density-based clustering method. We also present a large image dataset describing four road cover states in urban scenes, including different weather and visual conditions. The dataset comprises 41346 images collected from road monitoring cameras installed in Montreal, Canada, during the 2022 winter season. This dataset intends to help integrate computer vision techniques in planning snow removal operations.

Original languageEnglish (US)
Title of host publicationAPCCAS 2022 - 2022 IEEE Asia Pacific Conference on Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages110-114
Number of pages5
ISBN (Electronic)9781665450737
DOIs
StatePublished - 2022
Event2022 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2022 - Virtual, Online, China
Duration: Nov 11 2022Nov 13 2022

Publication series

NameAPCCAS 2022 - 2022 IEEE Asia Pacific Conference on Circuits and Systems

Conference

Conference2022 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2022
Country/TerritoryChina
CityVirtual, Online
Period11/11/2211/13/22

Keywords

  • Autoencoders
  • Community Detection
  • Intelligent Transportation
  • Road Surface Condition
  • Unsupervised Annotation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Unsupervised Image Dataset Annotation Framework for Snow Covered Road Networks'. Together they form a unique fingerprint.

Cite this