Pedestrian Environment Model for Automated Driving

TL;DR

This paper introduces a pedestrian environment model for automated driving that incorporates pose and position data from monocular camera images to improve pedestrian interaction safety.

Contribution

It presents a novel environment model combining pose estimation and position tracking using monocular images, tracking algorithms, and vehicle data for enhanced pedestrian understanding.

Findings

Achieved around 16% relative position error on CARLA and nuScenes datasets.

Integrated pose and position data for improved pedestrian behavior interpretation.

Demonstrated effectiveness with simulated and real-world datasets.

Abstract

Besides interacting correctly with other vehicles, automated vehicles should also be able to react in a safe manner to vulnerable road users like pedestrians or cyclists. For a safe interaction between pedestrians and automated vehicles, the vehicle must be able to interpret the pedestrian's behavior. Common environment models do not contain information like body poses used to understand the pedestrian's intent. In this work, we propose an environment model that includes the position of the pedestrians as well as their pose information. We only use images from a monocular camera and the vehicle's localization data as input to our pedestrian environment model. We extract the skeletal information with a neural network human pose estimator from the image. Furthermore, we track the skeletons with a simple tracking algorithm based on the Hungarian algorithm and an ego-motion compensation. To obtain the 3D information of the position, we aggregate the data from consecutive frames in conjunction with the vehicle position. We demonstrate our pedestrian environment model on data generated with the CARLA simulator and the nuScenes dataset. Overall, we reach a relative position error of around 16% on both datasets.