A Multilevel Strategy to Improve People Tracking in a Real-World Scenario
This work addresses people tracking in a specific real-world surveillance scenario, but it is incremental as it builds on existing trackers.
The paper tackled the problem of improving people tracking in real-world surveillance footage from the Brazilian presidential office invasion by proposing a multilevel hierarchy method that combines existing trackers, resulting in up to a 9.5% increase in IDF1 score.
The Palácio do Planalto, office of the President of Brazil, was invaded by protesters on January 8, 2023. Surveillance videos taken from inside the building were subsequently released by the Brazilian Supreme Court for public scrutiny. We used segments of such footage to create the UFPR-Planalto801 dataset for people tracking and re-identification in a real-world scenario. This dataset consists of more than 500,000 images. This paper presents a tracking approach targeting this dataset. The method proposed in this paper relies on the use of known state-of-the-art trackers combined in a multilevel hierarchy to correct the ID association over the trajectories. We evaluated our method using IDF1, MOTA, MOTP and HOTA metrics. The results show improvements for every tracker used in the experiments, with IDF1 score increasing by a margin up to 9.5%.