Learning Trajectory-Conditioned Relations to Predict Pedestrian Crossing Behavior
This work addresses pedestrian safety in smart transportation by improving intent prediction, though it appears incremental with modest performance gains.
The paper tackles the problem of predicting pedestrian crossing intent by incorporating dependencies on traffic surroundings, achieving a 0.04 improvement in F1-score on the JAAD dataset and a 0.01 improvement in recall on the PIE dataset compared to state-of-the-art methods.
In smart transportation, intelligent systems avoid potential collisions by predicting the intent of traffic agents, especially pedestrians. Pedestrian intent, defined as future action, e.g., start crossing, can be dependent on traffic surroundings. In this paper, we develop a framework to incorporate such dependency given observed pedestrian trajectory and scene frames. Our framework first encodes regional joint information between a pedestrian and surroundings over time into feature-map vectors. The global relation representations are then extracted from pairwise feature-map vectors to estimate intent with past trajectory condition. We evaluate our approach on two public datasets and compare against two state-of-the-art approaches. The experimental results demonstrate that our method helps to inform potential risks during crossing events with 0.04 improvement in F1-score on JAAD dataset and 0.01 improvement in recall on PIE dataset. Furthermore, we conduct ablation experiments to confirm the contribution of the relation extraction in our framework.