# Estimating Pedestrian Moving State Based on Single 2D Body Pose

## TL;DR

This paper introduces a neural network-based method to classify pedestrian crossing states, including walking along the vehicle's path, using only a single 2D body pose, enhancing autonomous vehicle safety.

## Contribution

It extends the crossing classification to include pedestrians moving along the vehicle's direction, using a lightweight neural network with single pose data, unlike previous methods requiring multiple poses or context.

## Key findings

- Achieved 81.23% accuracy on JAAD dataset.
- Model is adaptable to various sensors and conditions.
- First to recognize pedestrians walking along the vehicle's path.

## Abstract

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.