English

VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction

Computer Vision and Pattern Recognition 2022-08-10 v1 Artificial Intelligence Robotics

Abstract

Predicting future behaviors of road agents is a key task in autonomous driving. While existing models have demonstrated great success in predicting marginal agent future behaviors, it remains a challenge to efficiently predict consistent joint behaviors of multiple agents. Recently, the occupancy flow fields representation was proposed to represent joint future states of road agents through a combination of occupancy grid and flow, which supports efficient and consistent joint predictions. In this work, we propose a novel occupancy flow fields predictor to produce accurate occupancy and flow predictions, by combining the power of an image encoder that learns features from a rasterized traffic image and a vector encoder that captures information of continuous agent trajectories and map states. The two encoded features are fused by multiple attention modules before generating final predictions. Our simple but effective model ranks 3rd place on the Waymo Open Dataset Occupancy and Flow Prediction Challenge, and achieves the best performance in the occluded occupancy and flow prediction task.

Keywords

Cite

@article{arxiv.2208.04530,
  title  = {VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction},
  author = {Xin Huang and Xiaoyu Tian and Junru Gu and Qiao Sun and Hang Zhao},
  journal= {arXiv preprint arXiv:2208.04530},
  year   = {2022}
}

Comments

Technical report. 5 pages, 1 figure, and 2 tables

R2 v1 2026-06-25T01:35:11.072Z