Context-based Detection of Pedestrian Crossing Intention for Autonomous Driving in Urban Environments

This paper focuses on the detection of pedestrian crossing intention to improve the situation awareness for autonomous driving in urban environments. A new definition of pedestrian crossing intention is discussed, which allows self driving vehicles to identify pedestrians, whose intended actions are relevant for the own behavior planning, at an early stage. We propose a context-based feature descriptor in combination with a SVM classifier for detecting this. The descriptor captures the movement of a pedestrian relative to the road and the spatial layout of other scene elements in a generic manner. The performance of the feature descriptor is evaluated in relation to various SVM setups. Feasibility of the approach is demonstrated with data captured on-board of a vehicle in real inner-city traffic. The evaluation of the classification results confirms, that context-based data is a promising indicator for pedestrian crossing intention and that the proposed feature descriptor is capable of representing this. It is further shown that a lack of information about the pedestrian's posture and body movement results in a delayed detection of the pedestrians changing their crossing intention when compared to a human observer.