Detecting Unsigned Physical Road Incidents from Driver-view Images

Alex Levering, Martin Tomko, Devis Tuia, Kourosh Khoshelham

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Safety on roads is of uttermost importance, especially in the context of autonomous vehicles. A critical need is to detect and communicate disruptive incidents early and effectively. In this paper we propose a system based on an off-the-shelf deep neural network architecture that is able to detect and recognize types of unsigned (non-placarded, such as traffic signs), physical (visible in images) road incidents. We develop a taxonomy for unsigned physical incidents to provide a means of organizing and grouping related incidents. After selecting eight target types of incidents, we collect a dataset of twelve thousand images gathered from publicly-available web sources. We subsequently fine-tune a convolutional neural network to recognize the eight types of road incidents. The proposed model is able to recognize incidents with a high level of accuracy (higher than 90%). We further show that while our system generalizes well across spatial context by training a classifier on geostratified data in the United Kingdom (with an accuracy of over 90%), the translation to visually less similar environments requires spatially distributed data collection.

Original languageEnglish
Pages (from-to)24-33
JournalIEEE Transactions on Intelligent Vehicles
Volume6
Issue number1
Early online date6 May 2020
DOIs
Publication statusPublished - Mar 2021

Fingerprint Dive into the research topics of 'Detecting Unsigned Physical Road Incidents from Driver-view Images'. Together they form a unique fingerprint.

Cite this