Traffic Accident Recognition in First-Person Videos by Learning a Spatio-Temporal Visual Pattern

Kyung Ho Park, Dong Hyun Ahn, Huy Kang Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)


A camera-based perception of dangerous road situations such as traffic accidents is a significant task in modern autonomous driving and ADAS. The previous approaches have scrutinized a spatio-temporal characteristics of the traffic accident in a sequence of images. However, we figured out the limit of past works that the aforementioned spatio-temporal pattern is only considered in 2D manner, which loses a contextual knowledge of the road situation in 3D space where the accident actually happens. In this study, we propose a novel approach to learn a spatio-temporal pattern of traffic accidents in a sequence of traffic scene images. First, we designed a spatial feature extractor that illustrates the distance among traffic objects in a 3D manner, which contextually describes the road situation better by considering traffic objects' location with their depth information. Second, we proposed an accident detection model and examined the model identified traffic accidents with 0.8560 accuracy and a 0.9080 F1 score. Lastly, we suggested an accident anticipation model, and it outperformed the previously-proposed benchmark anticipation model in a challenging task. We expect further improvement of our approach can contribute to the safe vehicular technology for autonomous driving and ADAS development.

Original languageEnglish
Title of host publication2021 IEEE 93rd Vehicular Technology Conference, VTC 2021-Spring - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728189642
Publication statusPublished - 2021 Apr
Event93rd IEEE Vehicular Technology Conference, VTC 2021-Spring - Virtual, Online
Duration: 2021 Apr 252021 Apr 28

Publication series

NameIEEE Vehicular Technology Conference
ISSN (Print)1550-2252


Conference93rd IEEE Vehicular Technology Conference, VTC 2021-Spring
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021 IEEE.


  • Monocular Depth Estimation
  • Object Detection
  • Recurrent Neural Network
  • Traffic Accident Recognition

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Traffic Accident Recognition in First-Person Videos by Learning a Spatio-Temporal Visual Pattern'. Together they form a unique fingerprint.

Cite this