Vehicle-Pedestrian Dynamic Interaction through Tractography of Relative Movements and Articulated Pedestrian Pose Estimation

To design robust Pre-Collision Systems (PCS) we must develop new techniques that will allow a better understanding of the vehicle-pedestrian dynamic relationship, and which can predict pedestrian future movements. This paper focuses on the potential-conflict situations where a collision may happen if no avoidance action is taken from driver or pedestrian. We have used 1000 15-second videos to find vehicle-pedestrian relative dynamic trajectories and pose of pedestrians. Adaptive structural local appearance model and particle filter methods have been implemented to track the pedestrians. We have obtained accurate tractography results for over 82% of the videos. For pose estimation, we have used flexible mixture model for capturing cooccurrence between pedestrian body segments. Based on existing single-frame human pose estimation model, we have implemented Kalman filtering with other new techniques to make stable stickfigure videos of the pedestrian dynamic motion. These tractography and pose estimation data were used as features to train a neural network for classifying 'potential conflict' and 'no potential conflict' situations. The training of the network achieved 91.2% true label accuracy, and 8.8% false level accuracy. Finally, the trained network was used to assess the probability of collision over time for the 15 seconds videos which generates a spike when there is a 'potential conflict' situation. The paper enables new analysis on potential-conflict pedestrian cases with 2D tractography data and stick-figure pose representation of pedestrians, which provides significant insight on the vehicle-pedestrian dynamics that are critical for safe autonomous driving and transportation safety innovations