GSC: A Graph and Spatio-Temporal Continuity Based Framework for Accident Anticipation
Tianhang Wang, Kai Chen, Guang Chen, Bin Li, Zhijun Li, Zhengfa Liu, Changjun Jiang
Abstract
Accident anticipation attempts to predict whether an accident may occur in advance, which is greatly significant for improving the safety of intelligent vehicles. Most existing approaches integrate the features of accident-relevant agents with spatial information for accident anticipation. However, these approaches ignore the actual spatio-temporal state of missing agents, whether they are occluded or left, which is relevant to accident occurrence. To address this issue, we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</i> raph and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</i> patio-temporal <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> ontinuity based framework for accident anticipation called GSC, which takes the missing agents into account. Specifically, the proposed GSC maintains the spatio-temporal continuity of missing agents, which are in the occluded spatial state in the process of the graph convolution operation. Besides, we define a novel adjacent matrix to add dynamic features to graph learning. In particular, our adjacent matrix utilizes the historical trajectory of each agent to integrate dynamic information into the original static interaction, which improves the quality of the spatial relation feature for accident anticipation. Experimental results on public datasets demonstrate state-of-the-art performance in the correctness of identifying an accident, which is found to reach over 60%.