A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents

TL;DR

This paper introduces a Dynamic Spatial-Temporal Attention network that predicts traffic accidents early from dashcam videos by focusing on critical spatial regions and temporal segments, outperforming existing methods.

Contribution

It proposes a novel attention-based model with dynamic spatial and temporal modules for early accident prediction from dashcam videos, achieving state-of-the-art results.

Findings

Outperforms existing accident anticipation models on benchmark datasets.

Effective fusion method further improves prediction accuracy.

Component analysis shows the importance of spatial and temporal attention modules.

Abstract

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.