TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions

By Rohan Chandra, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha. Computer Vision and Pattern Recognition, 2018

306 citations recorded by the source corpus.

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 road agents may correspond to buses, cars, scooters, bi-cycles, or pedestrians. We model the interactions between different road agents using a novel LSTM-CNN hybrid network for trajectory prediction. In particular, we take into account heterogeneous interactions that implicitly account 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%.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0e6a84eb1ef0dfe8a8a1f28e0d7e01fb215cd9b5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sibo Zhang
2. Jiatong Du
3. Dinesh Manocha
4. Yuexin Ma
5. Zewei Zhou
6. Lin Zhang
7. Yanjun Huang
8. Hong Chen

In Automotive Engineering

1. Jiatong Du
2. Dinesh Manocha
3. Zewei Zhou
4. Lin Zhang
5. Yanjun Huang
6. Hong Chen
7. Ziru Yang

In Computer Vision and Pattern Recognition

1. Jiatong Du
2. Dinesh Manocha
3. Yuexin Ma
4. Zewei Zhou
5. Lin Zhang
6. Yanjun Huang
7. Hong Chen
8. Ziru Yang

Citations in the corpus

• A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, methodology): “Chandra et al. [104] propose a model called TraPHic based on the CNN-LSTM hybrid network to predict traffic participants’ trajectories.”
• TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents (2018, methodology): “These methods may not work in heterogeneous traffic, where different vehicles and pedestrians coexist and interact with each other(Chandra et al. 2018b).”