TraPHic: Predicting Trajectories of Road-Agents in Dense and Heterogeneous Traffic.

Paper Code Dataset
TraPHic, CVPR 2019 GitHub Code TRAF

We present a new algorithm for predicting the near-term trajectories of road-agents in dense traffic videos. Our approach is designed for heterogeneous traffic, where the roadagents may correspond to buses, cars, scooters, bi-cycles, or pedestrians. We model the interactions between different roadagents using a novel LSTM-CNN hybrid network for trajectory prediction. In particular, we take into account heterogeneous interactions that implicitly accounts for the varying shapes, dynamics, and behaviors of different road agents. In addition, we model horizon-based interactions which are used to implicitly model the driving behavior of each road-agent. We evaluate the performance of our prediction algorithm, TraPHic, on the standard datasets and also introduce a new dense, heterogeneous traffic dataset corresponding to urban Asian videos and agent trajectories. We outperform state-of-the-art methods on dense traffic datasets by 30%.

Please cite our work if you found it useful,

  title={Traphic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions},
  author={Chandra, Rohan and Bhattacharya, Uttaran and Bera, Aniket and Manocha, Dinesh},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},