Estimating Pedestrian Moving State Based on Single 2D Body Pose
This work addresses a safety-critical gap in autonomous vehicle perception by extending pedestrian state classification to include walking along the vehicle's direction, though it is incremental as it builds on existing crossing/not-crossing frameworks.
The paper tackles the problem of estimating pedestrian moving states (crossing, not crossing, or walking along) for autonomous vehicles using only a single 2D body pose, achieving an average accuracy of 81.23% on the JAAD dataset.
The Crossing or Not-Crossing (C/NC) problem is important to autonomous vehicles (AVs) for safe vehicle/pedestrian interactions. However, this problem setup often ignores pedestrians walking along the direction of the vehicles' movement (LONG). To enhance the AVs' awareness of pedestrians behavior, we make the first step towards extending the C/NC to the C/NC/LONG problem and recognize them based on single body pose. In contrast, previous C/NC state classifiers depend on multiple poses or contextual information. Our proposed shallow neural network classifier aims to recognize these three states swiftly. We tested it on the JAAD dataset and reported an average 81.23% accuracy. Furthermore, this model can be integrated with different sensors and algorithms that provide 2D pedestrian body pose so that it is able to function across multiple light and weather conditions.