TY - GEN
T1 - Traffic Accident Recognition in First-Person Videos by Learning a Spatio-Temporal Visual Pattern
AU - Ho Park, Kyung
AU - Hyun Ahn, Dong
AU - Kang Kim, Huy
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/4
Y1 - 2021/4
N2 - 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.
AB - 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.
KW - Monocular Depth Estimation
KW - Object Detection
KW - Recurrent Neural Network
KW - Traffic Accident Recognition
UR - http://www.scopus.com/inward/record.url?scp=85112426994&partnerID=8YFLogxK
U2 - 10.1109/VTC2021-Spring51267.2021.9448683
DO - 10.1109/VTC2021-Spring51267.2021.9448683
M3 - Conference contribution
AN - SCOPUS:85112426994
T3 - IEEE Vehicular Technology Conference
BT - 2021 IEEE 93rd Vehicular Technology Conference, VTC 2021-Spring - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 93rd IEEE Vehicular Technology Conference, VTC 2021-Spring
Y2 - 25 April 2021 through 28 April 2021
ER -