Abstract
We propose a Dynamic-Spatial-Attention (DSA) Recurrent Neural Network (RNN) for anticipating accidents in dashcam videos (Fig. 1.1). Our DSA-RNN learns to (1) distribute soft-attention to candidate objects dynamically to gather subtle cues and (2) model the temporal dependencies of all cues to robustly anticipate an accident. Anticipating accidents is much less addressed than anticipating events such as changing a lane, making a turn, etc., since accidents are rare to be observed and can happen in many different ways mostly in a sudden. To overcome these challenges, we (1) utilize state-of-the-art object detector [1] and tracking-by-detection [2] to detect and track candidate objects, and (2) incorporate full-frame and object-based appearance and motion features in our model. We also harvest a diverse dataset of 968 dashcam accident videos on the web (Fig.5.1). The dataset is unique, since various accidents (e.g., a motorbike hits a car, a car hits another car, etc.) occur in all videos. We manually mark the time-location of accidents and use them as supervision to train and evaluate our method. We show that our method anticipates accidents about 1.22 seconds before they occur with 80% recall and 46.92% precision. Most importantly, it achieves the highest mean average precision (63.98\%) outperforming other baselines without attention or RNN.