Multi-Task Deep Learning for Pedestrian Detection, Action Recognition and Time to Cross Prediction

A pedestrian detection system is a crucial component of advanced driver assistance systems since it contributes to road flow safety. The safety of traffic participants could be significantly improved if these systems could also predict and recognize pedestrians actions, or even estimate the time, for each pedestrian, to cross the street. In this paper, we focus not only on pedestrian detection and pedestrian action recognition but also on estimating if the pedestrians action presents a risky situation according to time to cross the street. We propose 1) a pedestrian detection and action recognition component based, on RetinaNet; 2) an estimation of the time to cross the street for multiple pedestrians using a recurrent neural network. For each pedestrian, the recurrent network estimates the pedestrians action intention in order to predict the time to cross the street. We based our experiments on the JAAD dataset, and show that integrating multiple pedestrian action tags for the detection part when merge with a recurrent neural network (LSTM) allows a significant performance improvement.