Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project

TL;DR

This paper demonstrates that simple hierarchical clustering combined with well-trained person re-identification features can effectively address multi-target, multi-camera tracking challenges on the DukeMTMC benchmark.

Contribution

The paper introduces a straightforward hierarchical clustering approach utilizing re-identification features for multi-camera tracking, showing competitive results on DukeMTMC.

Findings

Hierarchical clustering achieves good tracking performance.

Well-trained re-identification features are crucial.

Method simplifies multi-camera tracking process.

Abstract

Although many methods perform well in single camera tracking, multi-camera tracking remains a challenging problem with less attention. DukeMTMC is a large-scale, well-annotated multi-camera tracking benchmark which makes great progress in this field. This report is dedicated to briefly introduce our method on DukeMTMC and show that simple hierarchical clustering with well-trained person re-identification features can get good results on this dataset.