DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes

TL;DR

DIVOTrack introduces a comprehensive dataset with diverse real-world scenes for cross-view multi-object tracking, along with a novel baseline method, enabling better evaluation and development of tracking algorithms.

Contribution

The paper presents DIVOTrack, the first dataset with diverse open scenes and dense pedestrian tracking, and proposes CrossMOT, a unified framework for detection, association, and cross-view matching.

Findings

DIVOTrack surpasses existing datasets in scene diversity and track count.

CrossMOT achieves competitive performance on the new benchmark.

Standard benchmarks facilitate fair comparison of cross-view tracking methods.

Abstract

Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased attention in recent years, existing datasets still have several issues, including 1) missing real-world scenarios, 2) lacking diverse scenes, 3) owning a limited number of tracks, 4) comprising only static cameras, and 5) lacking standard benchmarks, which hinder the investigation and comparison of cross-view tracking methods. To solve the aforementioned issues, we introduce DIVOTrack: a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians in realistic and non-experimental environments. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT, which learns object detection, single-view association, and cross-view matching with an all-in-one embedding model. Finally, we present a summary of current methodologies and a set of standard benchmarks with our DIVOTrack to provide a fair comparison and conduct a comprehensive analysis of current approaches and our proposed CrossMOT. The dataset and code are available at https://github.com/shengyuhao/DIVOTrack.