Joint Attention in Autonomous Driving (JAAD)

Abstract

In this paper we present a novel dataset for a critical aspect of autonomous driving, the joint attention that must occur between drivers and of pedestrians, cyclists or other drivers. This dataset is produced with the intention of demonstrating the behavioral variability of traffic participants. We also show how visual complexity of the behaviors and scene understanding is affected by various factors such as different weather conditions, geographical locations, traffic and demographics of the people involved. The ground truth data conveys information regarding the location of participants (bounding boxes), the physical conditions (e.g. lighting and speed) and the behavior of the parties involved.

fixed formatting, added references

Cited by in corpus (18)

• Stepwise Goal-Driven Networks for Trajectory Prediction
• A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services
• Context Model for Pedestrian Intention Prediction using Factored Latent-Dynamic Conditional Random Fields
• People as Sensors: Imputing Maps from Human Actions
• Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
• VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users
• Driving Datasets Literature Review
• Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving
• BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
• Saccade Sequence Prediction: Beyond Static Saliency Maps
• Pedestrian Intention Prediction: A Multi-task Perspective
• Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction
• GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction
• Coupling Intent and Action for Pedestrian Crossing Behavior Prediction
• DEV: A Driver-Environment-Vehicle Closed-Loop Framework for Risk-Aware Adaptive Automation of Driving
• Action and intention recognition of pedestrians in urban traffic
• Bosch Deep Learning Hardware Benchmark