TGRMPT: A Head-Shoulder Aided Multi-Person Tracker and a New Large-Scale Dataset for Tour-Guide Robot

TL;DR

This paper introduces TGRDB, a large-scale dataset for multi-person tracking tailored for Tour-Guide Robots, and proposes TGRMPT, a new multi-person tracker utilizing head-shoulder and full-body cues, achieving state-of-the-art results.

Contribution

The paper provides a new large-scale dataset and a novel multi-person tracking system specifically designed for Tour-Guide Robots, addressing existing limitations.

Findings

TGRDB contains 5.6 hours of annotated videos with 450 long-term trajectories.

TGRMPT achieves state-of-the-art performance on the new dataset.

A new evaluation metric better suited for TGR is proposed.

Abstract

A service robot serving safely and politely needs to track the surrounding people robustly, especially for Tour-Guide Robot (TGR). However, existing multi-object tracking (MOT) or multi-person tracking (MPT) methods are not applicable to TGR for the following reasons: 1. lacking relevant large-scale datasets; 2. lacking applicable metrics to evaluate trackers. In this work, we target the visual perceptual tasks for TGR and present the TGRDB dataset, a novel large-scale multi-person tracking dataset containing roughly 5.6 hours of annotated videos and over 450 long-term trajectories. Besides, we propose a more applicable metric to evaluate trackers using our dataset. As part of our work, we present TGRMPT, a novel MPT system that incorporates information from head shoulder and whole body, and achieves state-of-the-art performance. We have released our codes and dataset in https://github.com/wenwenzju/TGRMPT.