Online and Real-Time Tracking in a Surveillance Scenario

David Zibriczky; Jan-Philip Richter; Maximilian Otten; Oliver Bredtmann; Oliver Urbann; Thilo Bauer

Online and Real-Time Tracking in a Surveillance Scenario

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.01153 v1 pith:EVGK5FEC submitted 2021-06-02 cs.CV cs.LG

Online and Real-Time Tracking in a Surveillance Scenario

Oliver Urbann , Oliver Bredtmann , Maximilian Otten , Jan-Philip Richter , Thilo Bauer , David Zibriczky This is my paper

classification cs.CV cs.LG

keywords scenariotrackingreal-timeapproachbenchmarkcapabledetectionsfingerprints

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

This paper presents an approach for tracking in a surveillance scenario. Typical aspects for this scenario are a 24/7 operation with a static camera mounted above the height of a human with many objects or people. The Multiple Object Tracking Benchmark 20 (MOT20) reflects this scenario best. We can show that our approach is real-time capable on this benchmark and outperforms all other real-time capable approaches in HOTA, MOTA, and IDF1. We achieve this by contributing a fast Siamese network reformulated for linear runtime (instead of quadratic) to generate fingerprints from detections. Thus, it is possible to associate the detections to Kalman filters based on multiple tracking specific ratings: Cosine similarity of fingerprints, Intersection over Union, and pixel distance ratio in the image.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Learning Association via Track-Detection Matching for Multi-Object Tracking
cs.CV 2025-12 conditional novelty 6.0

TDLP uses a link-prediction head to match tracks to detections, beating heuristic and metric-learning trackers on several MOT benchmarks while underperforming on MOT17.