FusionTrack: End-to-End Multi-Object Tracking in Arbitrary Multi-View Environment
This work addresses the need for flexible and scalable cooperative tracking systems in applications like intelligent transportation and surveillance, though it is incremental as it builds on existing multi-view tracking methods.
The paper tackles the problem of multi-view multi-object tracking in arbitrary environments by constructing the MDMOT dataset and proposing FusionTrack, an end-to-end framework that integrates tracking and re-identification, achieving state-of-the-art performance on benchmark datasets.
Multi-view multi-object tracking (MVMOT) has found widespread applications in intelligent transportation, surveillance systems, and urban management. However, existing studies rarely address genuinely free-viewpoint MVMOT systems, which could significantly enhance the flexibility and scalability of cooperative tracking systems. To bridge this gap, we first construct the Multi-Drone Multi-Object Tracking (MDMOT) dataset, captured by mobile drone swarms across diverse real-world scenarios, initially establishing the first benchmark for multi-object tracking in arbitrary multi-view environment. Building upon this foundation, we propose \textbf{FusionTrack}, an end-to-end framework that reasonably integrates tracking and re-identification to leverage multi-view information for robust trajectory association. Extensive experiments on our MDMOT and other benchmark datasets demonstrate that FusionTrack achieves state-of-the-art performance in both single-view and multi-view tracking.