Precise Real‐Time Path and Endpoint Prediction of Pedestrian Trajectories Using Deep CoordConv Autoencoder Network

ABSTRACT Pedestrian trajectory prediction based on computer vision technology is crucial for automatic driving systems and robot vision. This study proposes the use of deep CoordConv with autoencoders for the high‐precision prediction of pedestrian trajectories and endpoints in real‐time. First, an autoencoder‐based model combines with CoordConv using a past trajectory encoder, endpoint decoder and future trajectory decoder to enhance the coordinate features. Second, the proposed model predicts the possible endpoints and generates the trajectory from the start predicted position to each endpoint to overcome the multi‐modality problem. Finally, in extensive experiments, the proposed model for short‐term, long‐term and endpoint predictions outperformed conventional RNN‐based models.