mlsanityData to 7 Oct 2026

Online and Real-Time Tracking in a Surveillance Scenario

arXiv 2106.01153 ↗First posted 2 Jun 2021cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 10 of its 12 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

10 of 12 references.

References · 10

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2016Simple Online and Realtime Trackingcited by 862
  3. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  4. 2019Tracking without bells and whistlescited by 382
  5. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 355
  6. 2016Gated Siamese Convolutional Neural Network Architecture for Human Re-Identificationcited by 34
  7. 2020Simple Unsupervised Multi-Object Trackingcited by 33
  8. 2015Deep Feature Learning with Relative Distance Comparison for Person Re-identificationcited by 25
  9. 2020GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalizationcited by 25
  10. 2019Occlusion-Robust Online Multi-Object Visual Tracking using a GM-PHD Filter with CNN-Based Re-Identificationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 0; 2024: 2; 2025: 2; 2026: 1.

8 papers.

  1. 2022In Pursuit of Many: A Review of Modern Multiple Object Tracking Systemscited by 12
  2. 2024Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Trackingcited by 8
  3. 2021SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flowcited by 7
  4. 2024Engineering an Efficient Object Tracker for Non-Linear Motioncited by 4
  5. 2025YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-IDcited by 3
  6. 2022STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Trackingcited by 0
  7. 2025Learning Association via Track-Detection Matching for Multi-Object Trackingcited by 0
  8. 2026Revisiting Multi-Object Tracking Baselines: Hyperparameter Optimization with Multi-Fidelity Greedy Coordinate Searchcited by 0