Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

• Published in: IEEE robotics and automation letters Vol. 5; no. 2; pp. 3484 - 3491
• Main Authors: Liu, Bingbin, Adeli, Ehsan, Cao, Zhangjie, Lee, Kuan-Hui, Shenoi, Abhijeet, Gaidon, Adrien, Niebles, Juan Carlos
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Autonomous navigation; Autonomous vehicles; autonomous-driving; Cognition; Convolution; Datasets; Forecasting; graph neural networks; Mathematical models; Pedestrians; Predictive models; Reasoning; Robotics; Spatiotemporal graphs; Spatiotemporal phenomena; Videos; Visualization

Reasoning over visual data is a desirable capability for robotics and vision-based applications. Such reasoning enables forecasting the next events or actions in videos. In recent years, various models have been developed based on convolution operations for prediction or forecasting, but they lack t...