mlsanityData to 14 Oct 2026

TGOSPA Metric Parameters Selection and Evaluation for Visual Multi-object Tracking

arXiv 2412.08321 ↗First posted 11 Dec 2024eess.SY cs.CV cs.SYcited by 2

Not on the map. Why?

Abstract (arXiv)

Multi-object tracking algorithms are deployed in various applications, each with different performance requirements. For example, track switches pose significant challenges for offline scene understanding, as they hinder the accuracy of data interpretation. Conversely, in online surveillance applications, their impact is often minimal. This disparity underscores the need for application-specific performance evaluations that are both simple and mathematically sound. The trajectory generalized optimal sub-pattern assignment (TGOSPA) metric offers a principled approach to evaluate multi-object tracking performance. It accounts for localization errors, the number of missed and false objects, and the number of track switches, providing a comprehensive assessment framework. This paper illustrates the effective use of the TGOSPA metric in computer vision tasks, addressing challenges posed by the need for application-specific scoring methodologies. By exploring the TGOSPA parameter selection, we enable users to compare, comprehend, and optimize the performance of algorithms tailored for specific tasks, such as target tracking and training of detector or re-ID modules.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 45 references that are in the map. First posted on arXiv 11 Dec 2024.

Builds on

20 of 45 references.

References · 20

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  3. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  4. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  5. 2019Tracking without bells and whistlescited by 382
  6. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 320
  7. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  8. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 188
  9. 2020MOTChallenge: A Benchmark for Single-Camera Multiple Target Trackingcited by 136
  10. 2021Learning to Track with Object Permanencecited by 119
  11. 2020Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentationcited by 98
  12. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
8 more
  1. 2016Generalized optimal sub-pattern assignment metriccited by 33
  2. 2016A metric on the space of finite sets of trajectories for evaluation of multi-target tracking algorithmscited by 17
  3. 2020How Trustworthy are Performance Evaluations for Basic Vision Tasks?cited by 14
  4. 2016Multiple target tracking based on sets of trajectoriescited by 11
  5. 2024FeatureSORT: Essential Features for Effective Trackingcited by 8
  6. 2016A metric for sets of trajectories that is practical and mathematically consistentcited by 7
  7. 2021A time-weighted metric for sets of trajectories to assess multi-object tracking algorithmscited by 6
  8. 2016Multi-Object Tracking with Multiple Birth, Death, and Spawn Scenarios Using A Randomized Hypothesis Generation Technique (R-FISST)cited by 2

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Fast computation of the TGOSPA metric for multiple target tracking via unbalanced optimal transportcited by 1
  2. 2025Model-based Multi-object Visual Tracking: Identification and Standard Model Limitationscited by 0