Forecasting Pedestrian Trajectory with Machine-Annotated Training Data
This work addresses the challenge of unpredictable pedestrian behavior for autonomous vehicles and driver assistance systems, but it is incremental as it builds on existing deep learning approaches with a focus on data annotation.
The paper tackles pedestrian trajectory forecasting for autonomous vehicles by introducing a scalable machine annotation scheme to address the lack of training data, and proposes the Dynamic Trajectory Predictor (DTP) model, which shows improved performance in anticipating dynamic motion up to one second into the future.
Reliable anticipation of pedestrian trajectory is imperative for the operation of autonomous vehicles and can significantly enhance the functionality of advanced driver assistance systems. While significant progress has been made in the field of pedestrian detection, forecasting pedestrian trajectories remains a challenging problem due to the unpredictable nature of pedestrians and the huge space of potentially useful features. In this work, we present a deep learning approach for pedestrian trajectory forecasting using a single vehicle-mounted camera. Deep learning models that have revolutionized other areas in computer vision have seen limited application to trajectory forecasting, in part due to the lack of richly annotated training data. We address the lack of training data by introducing a scalable machine annotation scheme that enables our model to be trained using a large dataset without human annotation. In addition, we propose Dynamic Trajectory Predictor (DTP), a model for forecasting pedestrian trajectory up to one second into the future. DTP is trained using both human and machine-annotated data, and anticipates dynamic motion that is not captured by linear models. Experimental evaluation confirms the benefits of the proposed model.