Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision
This work is significant for improving the accuracy of pedestrian trajectory prediction in crowded environments, benefiting autonomous navigation systems and intelligent security applications.
The paper addresses the problem of pedestrian trajectory prediction, which is crucial for autonomous vehicles and surveillance. It proposes a temporal pyramid network that effectively integrates both long-range and short-range motion information, leading to superior performance on various benchmarks.
Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is rather inefficient and difficult to simultaneously exploit the long-range information (e.g., the destination of the trajectory), and the short-range information (e.g., the walking direction and speed at a certain time) of the motion behavior. In this paper, we propose a temporal pyramid network for pedestrian trajectory prediction through a squeeze modulation and a dilation modulation. Our hierarchical framework builds a feature pyramid with increasingly richer temporal information from top to bottom, which can better capture the motion behavior at various tempos. Furthermore, we propose a coarse-to-fine fusion strategy with multi-supervision. By progressively merging the top coarse features of global context to the bottom fine features of rich local context, our method can fully exploit both the long-range and short-range information of the trajectory. Experimental results on several benchmarks demonstrate the superiority of our method.