mlsanityData to 7 Oct 2026

UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking

arXiv 2402.12303 ↗First posted 19 Feb 2024cs.CV cs.ROcited by 4

Not on the map. Why?

Abstract (arXiv)

Multi-object tracking (MOT) methods have seen a significant boost in performance recently, due to strong interest from the research community and steadily improving object detection methods. The majority of tracking methods follow the tracking-by-detection (TBD) paradigm, blindly trust the incoming detections with no sense of their associated localization uncertainty. This lack of uncertainty awareness poses a problem in safety-critical tasks such as autonomous driving where passengers could be put at risk due to erroneous detections that have propagated to downstream tasks, including MOT. While there are existing works in probabilistic object detection that predict the localization uncertainty around the boxes, no work in 2D MOT for autonomous driving has studied whether these estimates are meaningful enough to be leveraged effectively in object tracking. We introduce UncertaintyTrack, a collection of extensions that can be applied to multiple TBD trackers to account for localization uncertainty estimates from probabilistic object detectors. Experiments on the Berkeley Deep Drive MOT dataset show that the combination of our method and informative uncertainty estimates reduces the number of ID switches by around 19% and improves mMOTA by 2-3%. The source code is available at https://github.com/TRAILab/UncertaintyTrack

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

32 of 45 references.

References · 32

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2018YOLOv3: An Incremental Improvementcited by 2,652
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  8. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  9. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  12. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
20 more
  1. 2016Simple Online and Realtime Trackingcited by 862
  2. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  3. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  4. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  5. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  6. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  7. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  8. 2020Tracking Objects as Pointscited by 483
  9. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  10. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  11. 2020A Review and Comparative Study on Probabilistic Object Detection in Autonomous Drivingcited by 115
  12. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  13. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  14. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  15. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  16. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  17. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  18. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  19. 2019Uncertainty Estimation in One-Stage Object Detectioncited by 36
  20. 2021Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Drivingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenariocited by 3
  2. 2026CADENet: Condition-Adaptive Asynchronous Dual-Stream Enhancement Network for Adverse Weather Perception in Autonomous Drivingcited by 1
  3. 2026Detecting Object Tracking Failure via Sequential Hypothesis Testingcited by 0
  4. 2026Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edgecited by 0