Journal
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
Volume 23, Issue 7, Pages 9590-9600Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2022.3155613
Keywords
Dynamic temporal attention; dynamic spatial attention; model fusion; autonomous vehicle; human-inspired AI
Categories
Funding
- National Science Foundation (NSF) [ECCS-2026357]
- NSF [ECCS-2025929]
Ask authors/readers for more resources
The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. This paper proposes a Dynamic Spatial-Temporal Attention (DSTA) network for early accident anticipation from dashcam videos, which has shown state-of-the-art performance in benchmark datasets and utilizes attention modules and fusion methods to improve the accuracy.
The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. Dashboard cameras (dashcams) have been widely deployed on both human driving vehicles and automated driving vehicles. A computational intelligence model that can accurately and promptly predict accidents from the dashcam video will enhance the preparedness for accident prevention. The spatial-temporal interaction of traffic agents is complex. Visual cues for predicting a future accident are embedded deeply in dashcam video data. Therefore, the early anticipation of traffic accidents remains a challenge. Inspired by the attention behavior of humans in visually perceiving accident risks, this paper proposes a Dynamic Spatial-Temporal Attention (DSTA) network for the early accident anticipation from dashcam videos. The DSTA-network learns to select discriminative temporal segments of a video sequence with a Dynamic Temporal Attention (DTA) module. It also learns to focus on the informative spatial regions of frames with a Dynamic Spatial Attention (DSA) module. A Gated Recurrent Unit (GRU) is trained jointly with the attention modules to predict the probability of a future accident. The evaluation of the DSTA-network on two benchmark datasets confirms that it has exceeded the state-of-the-art performance. A thorough ablation study that assesses the DSTA-network at the component level reveals how the network achieves such performance. Furthermore, this paper proposes a method to fuse the prediction scores from two complementary models and verifies its effectiveness in further boosting the performance of early accident anticipation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available