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

## TL;DR

TraPHic introduces a novel LSTM-CNN hybrid model for predicting trajectories of diverse road-agents in dense, heterogeneous traffic, outperforming existing methods by 30% on standard datasets.

## Contribution

The paper presents a new trajectory prediction algorithm that models heterogeneous interactions and horizon-based behaviors in dense traffic using a hybrid neural network.

## Key findings

- Outperforms state-of-the-art methods by 30% on dense traffic datasets.
- Introduces a new dense, heterogeneous traffic dataset from urban Asian videos.
- Effectively models diverse agent interactions and behaviors.

## Abstract

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, bicycles, 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 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%.