Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking

TL;DR

This paper introduces a complete deep learning framework for multi-person localisation and tracking that leverages a generative model for occlusion handling and trajectory prediction, eliminating the need for appearance-based re-identification.

Contribution

A novel deep learning approach combining a lightweight GAN for localisation and a trajectory prediction-based data association scheme for tracking.

Findings

Outperforms recent deep learning methods on public benchmarks.

Effectively handles occlusions and noisy detections.

Produces human-like trajectories with minimal fragmentation.

Abstract

Current multi-person localisation and tracking systems have an over reliance on the use of appearance models for target re-identification and almost no approaches employ a complete deep learning solution for both objectives. We present a novel, complete deep learning framework for multi-person localisation and tracking. In this context we first introduce a light weight sequential Generative Adversarial Network architecture for person localisation, which overcomes issues related to occlusions and noisy detections, typically found in a multi person environment. In the proposed tracking framework we build upon recent advances in pedestrian trajectory prediction approaches and propose a novel data association scheme based on predicted trajectories. This removes the need for computationally expensive person re-identification systems based on appearance features and generates human like trajectories with minimal fragmentation. The proposed method is evaluated on multiple public benchmarks including both static and dynamic cameras and is capable of generating outstanding performance, especially among other recently proposed deep neural network based approaches.