Multiple Object Tracking Using K-Shortest Paths Optimization
Open accessAbstract
Multi-object tracking can be achieved by detecting objects in individual frames and then linking detections across frames. Such an approach can be made very robust to the occasional detection failure: If an object is not detected in a frame but is in previous and following ones, a correct trajectory will nevertheless be produced. By contrast, a false-positive detection in a few frames will be ignored. However, when dealing with a multiple target problem, the linking step results in a difficult optimization problem in the space of all possible families of trajectories. This is usually dealt with by sampling or greedy search based on variants of Dynamic Programming which can easily miss the global optimum. In this paper, we show that reformulating that step as a constrained flow optimization results in a convex problem. We take advantage of its particular structure to solve it using the k-shortest paths algorithm, which is very fast. This new approach is far simpler formally and algorithmically than existing techniques and lets us demonstrate excellent performance in two very different contexts.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A note on two problems in connexion with graphs
Dijkstra, E. (1959) · Numerische Mathematik · doi:10.1007/bf01386390 · Cited by 24,351 · see citing works
Adhi Harmoko, S., M.Komp, Jacquard, J. M., Zuse, K., & Eniac (2005) · Cited by 18,035 · see citing works
Bellman, R. E. (2010) · doi:10.1515/9781400835386 · Cited by 14,588 · see citing works
Linear Programming and Extensions
Dantzig, G. B. (1963) · RAND Corporation eBooks · doi:10.7249/r366 · Cited by 5,800 · see citing works
A new polynomial-time algorithm for linear programming
Karmarkar, N. K. (1984) · COMBINATORICA · doi:10.1007/bf02579150 · Cited by 4,851 · see citing works
Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics
Bernardin, K., & Stiefelhagen, R. (2008) · EURASIP Journal on Image and Video Processing · doi:10.1155/2008/246309 · Cited by 2,918 · see citing works
Linear Programming and Extensions
Dantzig, G. B. (1963) · Princeton University Press eBooks · doi:10.1515/9781400884179 · Cited by 2,730 · see citing works
Introduction to algorithms [2nd ed.]
Cormen, T. H. (2001) · Cited by 1,902 · see citing works
O’Regan, G. (2023) · Texts in computer science · doi:10.1007/978-3-031-26212-8_4 · Cited by 1,614 · see citing works
A Boosted Particle Filter: Multitarget Detection and Tracking
Okuma, K., Taleghani, A., de Freitas, N., Little, J. J., & Lowe, D. G. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24670-1_3 · Cited by 1,022 · see citing works
Linear Inequalities and Related Systems.
Dantzig, G. B., Kuhn, H. W., & Tucker, A. W. (1956) · Medical Entomology and Zoology · Cited by 995 · see citing works
Global data association for multi-object tracking using network flows
Zhang, L., Li, Y., & Nevatia, R. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587584 · Cited by 945 · see citing works
Multicamera People Tracking with a Probabilistic Occupancy Map
Fleuret, F., Berclaz, J., Lengagne, R., & Fua, P. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1174 · Cited by 823 · see citing works
Self-citationMCMC-based particle filtering for tracking a variable number of interacting targets
Khan, Z., Balch, T. R., & Dellaert, F. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.223 · Cited by 776 · see citing works
Suurballe, J. W. (1974) · Networks · doi:10.1002/net.3230040204 · Cited by 693 · see citing works
Learning to associate: HybridBoosted multi-target tracker for crowded scene
Li, Y., Huang, C., & Nevatia, R. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206735 · Cited by 633 · see citing works
Kasturi, R., Goldgof, D., Soundararajan, P., Manohar, V., Garofolo, J. S., Bowers, R., Boonstra, M., Korzhova, V., & Zhang, J. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.57 · Cited by 580 · see citing works
Robust Object Tracking by Hierarchical Association of Detection Responses
Huang, C., Wu, B., & Nevatia, R. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88688-4_58 · Cited by 501 · see citing works
Unsupervised Bayesian Detection of Independent Motion in Crowds
Brostow, G., & Cipolla, R. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.320 · Cited by 408 · see citing works
Maintaining multimodality through mixture tracking
Vermaak, Doucet, & Pérez (2003) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238473 · Cited by 390 · see citing works
Integral Boundary Points of Convex Polyhedra
Hoffman, A. J., & Kruskal, J. B. (2009) · Springer eBooks · doi:10.1007/978-3-540-68279-0_3 · Cited by 373 · see citing works
M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene
Mittal, A., & Davis, L. S. (2003) · International Journal of Computer Vision · doi:10.1023/a:1021849801764 · Cited by 362 · see citing works
A Linear Programming Approach for Multiple Object Tracking
Jiang, H., Fels, S., & Little, J. J. (2007) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2007.383180 · Cited by 323 · see citing works
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes
Khan, S. M., & Shah, M. A. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.102 · Cited by 322 · see citing works
Fast multiple object tracking via a hierarchical particle filter
Yang, C., Ramani Duraiswami, B., & Davis, L. S. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.95 · Cited by 315 · see citing works
Binding, J. (2011) · Cited by 312 · see citing works
Coupled Detection and Trajectory Estimation for Multi-Object Tracking
Leibe, B., Schindler, K., & Gool, L. V. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4408936 · Cited by 273 · see citing works
Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions
Perera, A. G. A., Srinivas, C., Hoogs, A. J., Brooksby, G. W., & Hu, W. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.195 · Cited by 262 · see citing works
Tracking multiple vehicles using foreground, background and motion models
Magee, D. R. (2003) · Image and Vision Computing · doi:10.1016/s0262-8856(03)00145-8 · Cited by 232 · see citing works
A noniterative greedy algorithm for multiframe point correspondence
Shafique, K. H., & Shah, M. A. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.1 · Cited by 232 · see citing works
Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection
Wu, B., & Nevatia, R. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.312 · Cited by 227 · see citing works
Using Particles to Track Varying Numbers of Interacting People
Smith, K. C., Gática-Pérez, D., & Odobez, J. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.361 · Cited by 208 · see citing works
Oki, E. (2012) · CRC Press eBooks · doi:10.1201/b12733-4 · Cited by 200 · see citing works
Homography based multiple camera detection and tracking of people in a dense crowd
Eshel, R., & Moses, Y. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587539 · Cited by 188 · see citing works
Multi view image surveillance and tracking
Black, J., Ellis, T. J., & Rosin, P. L. (2003) · IEEE Workshop on Motion and Video Computing · doi:10.1109/motion.2002.1182230 · Cited by 182 · see citing works
GLPK (GNU Linear Programming Kit)
Oki, E. (2012) · CRC Press eBooks · doi:10.1201/b12733-5 · Cited by 176 · see citing works
Efficient Multitarget Visual Tracking Using Random Finite Sets
Maggio, E., Taj, M., & Cavallaro, A. (2008) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2008.928221 · Cited by 174 · see citing works
Multi-Target Tracking - Linking Identities using Bayesian Network Inference
Nillius, P., Sullivan, J., & Carlsson, S. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.198 · Cited by 142 · see citing works
Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association
Yu, Q., Medioni, G., & Cohen, I. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.382991 · Cited by 132 · see citing works
A Bayesian Framework for Multi-cue 3D Object Tracking
Giebel, J., Gavrila, D. M., & Schnörr, C. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24673-2_20 · Cited by 123 · see citing works
Finding the best set of K paths through a trellis with application to multitarget tracking
Wolf, J. K., Viterbi, A. M., & Dixon, G. S. (1989) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/7.18692 · Cited by 98 · see citing works
Multi-camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration
Du, W., & Piater, J. (2007) · Springer eBooks · doi:10.1007/978-3-540-76386-4_34 · Cited by 92 · see citing works
Tracking football players with multiple cameras
Thirde, D., Xu, M., & Orwell, J. (2006) · Institution of Engineering and Technology eBooks · doi:10.1049/pbpc005e_ch8 · Cited by 82 · see citing works
Parallel tracking of all soccer players by integrating detected positions in multiple view images
Iwase, S., & Saito, H. (2004) · Cited by 75 · see citing works
An LP-based algorithm for the data association problem in multitarget tracking
Storms, P. P. A., & Spieksma, F. C. R. (2003) · Computers & Operations Research · doi:10.1016/s0305-0548(02)00057-6 · Cited by 69 · see citing works
Parallel tracking of all soccer players by integrating detected positions in multiple view images
IWASE, S., & Saitô, H. (2004) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2004.1333881 · Cited by 66 · see citing works
PETS2009 and Winter-PETS 2009 results: A combined evaluation
Ellis, A., Shahrokni, A., & Ferryman, J. M. (2009) · doi:10.1109/pets-winter.2009.5399728 · Cited by 61 · see citing works
Multi-target Data Association by Tracklets with Unsupervised Parameter Estimation
Ge, W., & Collins, R. T. (2008) · British Machine Vision Conference (BMVC) · doi:10.5244/c.22.93 · Cited by 41 · see citing works
Tracking football players with multiple cameras
Xu, M., Orwell, J., & Jones, G. (2005) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2004.1421721 · Cited by 37 · see citing works
Target tracking with incomplete detection
Ma, Y., Yu, Q., & Cohen, I. (2009) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.01.002 · Cited by 30 · see citing works
Robust tracking of spatial related components
Mauthner, T., Donoser, M., & Bischof, H. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761044 · Cited by 28 · see citing works
Architecture and algorithms for tracking football players with multiple cameras
Xu, M. (2004) · doi:10.1049/ic:20040098 · Cited by 26 · see citing works
Multiple Object Tracking Using Local PCA
Beleznai, C., Frühstück, B., & Bischof, H. (2006) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2006.842 · Cited by 21 · see citing works
Flagged first, then by citations
Research works printed but not linked: 3
- [37][37] A. Ellis, A. Shahrokni, and J. Ferryman, 'Pets 2009 and winterpets 2009 results: A combined evaluation,' in Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance , Snowbird, December 2009. -
- [39][39] 'Eleventh ieee international workshop on performance evaluation of tracking and surveillance,' http://pets2009.net. -
- [43][43] A. Ghouila-Houri, 'Caract´ erisation Des Matrices Totalement Unimodulaires,' Comptes Rendus Hebdomadaires des S´ eances de l'Acad´ emie des Sciences , vol. 254, pp. 1192-1194, 1962. -
Cited by
Sorted by citations
Simple online and realtime tracking with a deep association metric
Wojke, N., Bewley, A., & Paulus, D. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296962 · Cited by 5,286 · see citing works
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01513-4 · Cited by 1,861 · see citing works
TrackFormer: Multi-Object Tracking with Transformers
Meinhardt, T., Kirillov, A., Leal-Taixe, L., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00864 · Cited by 1,081 · see citing works
Tracking Without Bells and Whistles
Bergmann, P., Meinhardt, T., & Leal-Taixe, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00103 · Cited by 1,110 · see citing works
Globally-optimal greedy algorithms for tracking a variable number of objects
Pirsiavash, H., Ramanan, D., & Fowlkes, C. C. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995604 · Cited by 790 · see citing works
UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
Wen, L., Du, D., Cai, Z., Lei, Z., Chang, M.-C., Qi, H., Lim, J., Yang, M.-H., & Lyu, S. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.102907 · Cited by 804 · see citing works
Multiple Hypothesis Tracking Revisited
Kim, C., Li, F., Ciptadi, A., & Rehg, J. M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.533 · Cited by 666 · see citing works
Features for Multi-target Multi-camera Tracking and Re-identification
Ristani, E., & Tomasi, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00632 · Cited by 556 · see citing works
Learning a Neural Solver for Multiple Object Tracking
Braso, G., & Leal-Taixe, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00628 · Cited by 504 · see citing works
Learning by Tracking: Siamese CNN for Robust Target Association
Leal-Taixe, L., Canton-Ferrer, C., & Schindler, K. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.59 · Cited by 444 · see citing works
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
Pang, B., Li, Y., Zhang, Y., Li, M., & Lu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00634 · Cited by 303 · see citing works
Learning to Track with Object Permanence
Tokmakov, P., Li, J., Burgard, W., & Gaidon, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01068 · Cited by 226 · see citing works
No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles Using Cameras and LiDARs
Rangesh, A., & Trivedi, M. M. (2019) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2019.2938110 · Cited by 158 · see citing works
An efficient edge artificial intelligence multipedestrian tracking method with rank constraint
Yang, H., Wen, J., Wu, X., He, L., & Mumtaz, S. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2897128 · Cited by 38 · see citing works
- Authors
- Berclaz, J., Fleuret, F., Turetken, E., & Fua, P.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- Idiap Research Institute (CH)
- ORCID
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2011-09
- Volume
- 33
- Issue
- 9
- Pages
- 1806-1819
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2171243491
- Cited by
- 1,015
- References
- 53
- Citations by year
- 2026: 15 · 2025: 34 · 2024: 44 · 2023: 47 · 2022: 39 · 2021: 63 · 2020: 74 · 2019: 81 · 2018: 92 · 2017: 102 · 2016: 110 · 2015: 118 · 2014: 84 · 2013: 71 · 2012: 36
- FWCI
- 67.45
- Type
- journal article
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Funders
- University of Reading
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- multi-target tracking, k-shortest paths, convex optimization, data association, false positive detection, dynamic programming
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
