Pedestrian Models for Autonomous Driving Part I: Low-Level Models, from Sensing to Tracking

Abstract

Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them. This narrative review article is Part I of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low-level image detection to high-level psychology models, from the perspective of an AV designer. This self-contained Part I covers the lower levels of this stack, from sensing, through detection and recognition, up to tracking of pedestrians. Technologies at these levels are found to be mature and available as foundations for use in high-level systems, such as behaviour modelling, prediction and interaction control.

Accepted for publication in the IEEE Transactions on Intelligent Transportation Systems

References in corpus (12)

• YOLOv3: An Incremental Improvement
• Multiple Object Tracking: A Literature Review
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Context-aware Deep Feature Compression for High-speed Visual Tracking
• Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior
• Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
• Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
• Towards Multi-Object Detection and Tracking in Urban Scenario under Uncertainties
• Multi-camera Multi-Object Tracking
• Benchmarking LiDAR Sensors for Development and Evaluation of Automotive Perception
• Multisensor Online Transfer Learning for 3D LiDAR-based Human Detection with a Mobile Robot

Cited by in corpus (7)

• Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior
• Interaction-aware Decision-making for Automated Vehicles using Social Value Orientation
• Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?
• Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition
• Comparing merging behaviors observed in naturalistic data with behaviors generated by a machine learned model
• Pedestrian-Aware Motion Planning for Autonomous Driving in Complex Urban Scenarios
• Single Shot Multitask Pedestrian Detection and Behavior Prediction