pith. sign in

arxiv: 2606.13127 · v1 · pith:273IOUHZnew · submitted 2026-06-11 · 💻 cs.CV

Fully Distributed Multi-View 3D Tracking in Real-Time

Byron Hernandez , Fangyu Li , Aotian Wu , Paul J. Shin , Kaustubh Purandare , Henry Medeiros This is my paper

Pith reviewed 2026-06-27 07:23 UTC · model grok-4.3

classification 💻 cs.CV
keywords multi-view trackingdistributed tracking3D object trackingmulti-camera systemsreal-time trackingpeer-to-peer coordinationocclusion recovery
0
0 comments X

The pith

MV3DT performs real-time 3D multi-view tracking through peer-to-peer messaging without any central server.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces MV3DT as a fully distributed framework where each camera node runs its own monocular 3D perception, associates views across the network via lightweight messages, and fuses results collaboratively. This setup is shown to deliver tracking performance on the WILDTRACK dataset that matches state-of-the-art centralized systems while scaling to networks of 100 cameras. The method requires only camera calibrations and no scene-specific training, allowing direct deployment in new environments. If correct, it removes the computational and bandwidth bottlenecks that currently limit multi-camera systems to smaller scales.

Core claim

MV3DT achieves accurate identity propagation and occlusion recovery through peer-to-peer coordination in a fully distributed setup. Each node executes a lightweight modular pipeline comprising monocular 3D perception, distributed multi-view association, and collaborative fusion via lightweight messaging. On the WILDTRACK benchmark it reaches 94.3 percent IDF1 and 93.3 percent MOTA, sustains 30 frames per second across 100 cameras with less than 10 ms inter-camera latency and 2.2 percent communication overhead, and operates in a zero-shot regime given only camera calibrations.

What carries the argument

The modular pipeline of monocular 3D perception, distributed multi-view association, and collaborative fusion via lightweight messaging that enables peer-to-peer identity propagation and occlusion recovery.

If this is right

  • Tracking accuracy remains competitive with centralized methods on standard benchmarks.
  • Real-time operation at 30 FPS is sustained on networks of at least 100 cameras.
  • Communication overhead stays below 3 percent even at large scale.
  • The system deploys directly in new scenes given only camera calibrations.
  • No central aggregation point is required for identity consistency or occlusion handling.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Large camera networks could be built with lower hardware and bandwidth costs because no high-capacity central server is needed.
  • Privacy may improve because raw video never leaves individual camera nodes.
  • The same messaging pattern could be tested on other distributed sensor fusion tasks such as multi-robot mapping.
  • Temporary node failures might be tolerated better than in centralized designs if identity recovery mechanisms are robust.

Load-bearing premise

Peer-to-peer coordination via lightweight messaging can reliably achieve identity propagation and occlusion recovery across the network without requiring central aggregation.

What would settle it

Run the system on a 100-camera network where one node experiences a 500 ms communication delay and measure whether track identities are lost or correctly recovered compared with a centralized baseline.

Figures

Figures reproduced from arXiv: 2606.13127 by Aotian Wu, Byron Hernandez, Fangyu Li, Henry Medeiros, Kaustubh Purandare, Paul J. Shin.

Figure 1
Figure 1. Figure 1: MV3DT Overview. MV3DT deploys a modular pipeline on each camera node without requiring a central server. Monocular Detection extracts 2D bound￾ing boxes. Then, 3D foot location estimates and full-body bounding boxes are com￾puted for Data Association, where detection-to-targets matches, both intra-view and multi-view, are found using several similarity measures. Target Management main￾tains target state an… view at source ↗
Figure 2
Figure 2. Figure 2: Full body bounding box and foot location recovered from an occluded detection: (left) projection of the cylinder model at the expected waist point pwaist, (center) convex hull of the projected cylinder used to recover the full body, (right) adjusting the projection based on top-edge comparison to handle occlusions. Algorithm 1 Recover 3D coordinates from bounding box Require: b = [u, v, w, h], cylinder mod… view at source ↗
Figure 3
Figure 3. Figure 3: MV3DT track lifecycle and recovery logic. Tracks begin as Tentative, are pro￾moted to Active after a short probation with consistent matches, and fall back to Inactive for shadow tracking when detections are missed. Quasi-Active denotes targets confirmed by peer cameras. enabling multi-view continuity, while Terminated closes stale tracks. Single View Data Association ensures the consistency of target iden… view at source ↗
Figure 4
Figure 4. Figure 4: Message fields: all message types include frame, camID, targetID, and targetID Ts (timestamp). tracklet and stateUpdate also carry targetAge, state, stateTime, visibility, and camDist; tracklet further includes the tracklet payload, while adoptedID adds only prevID (the ID replaced by targetID). 3.5 Inter-camera Communication The communication module is based on a publish/subscribe paradigm, in which each … view at source ↗
read the original abstract

Multi-camera tracking with overlapping fields of view typically relies on centralized fusion, which creates computational bottlenecks that prevent deployment at scale. We present MV3DT, a fully distributed framework for real-time multi-view 3D tracking that achieves accurate identity propagation and occlusion recovery through peer-to-peer coordination, eliminating the need for central aggregation. Each camera node executes a lightweight modular pipeline comprising monocular 3D perception, distributed multi-view association, and collaborative fusion via lightweight messaging. MV3DT achieves 94.3% IDF1 and 93.3% MOTA on WILDTRACK, competitive with state-of-the-art centralized methods, while demonstrating superior scalability by sustaining 30 FPS on 100 cameras with less than 10 ms inter-camera latency and only 2.2% communication overhead. MV3DT operates in a zero-shot regime given camera calibrations, requiring no scene-specific learning and making it directly deployable in new environments. These results establish MV3DT as a practical solution for real-time multi-view tracking in large-scale overlapping camera networks.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper introduces MV3DT, a fully distributed framework for real-time multi-view 3D tracking. Each camera node runs a modular pipeline with monocular 3D perception, distributed multi-view association, and collaborative fusion using lightweight messaging. It claims to achieve 94.3% IDF1 and 93.3% MOTA on the WILDTRACK dataset, competitive with centralized methods, while scaling to 100 cameras at 30 FPS with less than 10 ms latency and 2.2% communication overhead, operating zero-shot with only camera calibrations.

Significance. If the distributed coordination mechanism reliably maintains global consistency, this would represent a significant advance in scalable multi-camera tracking by eliminating central aggregation bottlenecks. The reported performance metrics and scalability results, including low overhead, would make it a practical solution for large-scale deployments in new environments without scene-specific training.

major comments (1)
  1. [Abstract] Abstract: The description of the 'distributed multi-view association' module claims it enables 'accurate identity propagation and occlusion recovery through peer-to-peer coordination' without central aggregation, but provides no details on the specific protocol for resolving cross-camera identity conflicts or ensuring no duplicate tracks. This mechanism is load-bearing for both the accuracy claims on WILDTRACK and the scaling to 100 cameras at 30 FPS.
minor comments (1)
  1. Confirm the exact dataset name (WILDTRACK vs. Wildtrack) and include its standard citation in the abstract if not already present.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive comment on the abstract. We address it point-by-point below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The description of the 'distributed multi-view association' module claims it enables 'accurate identity propagation and occlusion recovery through peer-to-peer coordination' without central aggregation, but provides no details on the specific protocol for resolving cross-camera identity conflicts or ensuring no duplicate tracks. This mechanism is load-bearing for both the accuracy claims on WILDTRACK and the scaling to 100 cameras at 30 FPS.

    Authors: We agree the abstract is high-level and would benefit from a concise description of the protocol. The full manuscript (Section 3.3) specifies a lightweight peer-to-peer protocol: each node broadcasts local track proposals with unique IDs and confidence scores; conflicts are resolved via a distributed majority-vote mechanism over a fixed-size message window, with duplicate suppression enforced by ID uniqueness and timestamp ordering. This ensures no central aggregation while maintaining consistency. We will revise the abstract to include a one-sentence outline of this protocol. revision: yes

Circularity Check

0 steps flagged

No circularity; claims rest on external dataset evaluation

full rationale

The paper presents an empirical framework evaluated on the external WILDTRACK benchmark (7 cameras) with reported IDF1/MOTA metrics, plus separate scalability simulations to 100 cameras. No equations or derivations reduce to fitted parameters renamed as predictions, no self-citation chains justify core claims, and the zero-shot modular pipeline is described without self-definitional loops. Performance numbers derive from standard tracking metrics on held-out data rather than internal normalization or ansatz smuggling.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract does not detail any free parameters, axioms, or invented entities; relies on standard metrics (IDF1, MOTA) and the WILDTRACK dataset.

pith-pipeline@v0.9.1-grok · 5728 in / 1219 out tokens · 36198 ms · 2026-06-27T07:23:10.840489+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

57 extracted references · 4 canonical work pages

  1. [1]

    Neurocomputing (2023) 1, 2, 4

    Amosa, T.I., Sebastian, P., Izhar, L.I., Ibrahim, O., Ayinla, L.S., Bahashwan, A.A., Bala, A., Samaila, Y.A.: Multi-camera multi-object tracking: a review of current trends and future advances. Neurocomputing (2023) 1, 2, 4

    2023

  2. [2]

    In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

    Aung, S., Park, H., Jung, H., Cho, J.: Enhancing multi-view pedestrian detection through generalized 3d feature pulling. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. pp. 1196–1205 (2024) 5

    2024

  3. [3]

    In: 2016 IEEE International Conference on Image Processing (ICIP) (2016) 4, 9

    Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and real-time tracking. In: 2016 IEEE International Conference on Image Processing (ICIP) (2016) 4, 9

    2016

  4. [4]

    Image and Vision Computing (2006) 2, 3

    Black, J., Ellis, T.: Multi camera image tracking. Image and Vision Computing (2006) 2, 3

    2006

  5. [5]

    In: European Conference on Computer Vision (2020) 4

    Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End- to-end object detection with transformers. In: European Conference on Computer Vision (2020) 4

    2020

  6. [6]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018) 12

    Chavdarova, T., Baqué, P., Bouquet, S., Maksai, A., Jose, C., Bagautdinov, T., Lettry, L., Fua, P., Van Gool, L., Fleuret, F.: WILDTRACK: A multi-camera HD dataset for dense unscripted pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018) 12

    2018

  7. [7]

    IEEE Transactions on Multimedia (2011) 4

    Chen, K.W., Lai, C.C., Lee, P.J., Chen, C.S., Hung, Y.P.: Adaptive learning for target tracking and true linking discovering across multiple non-overlapping cam- eras. IEEE Transactions on Multimedia (2011) 4

    2011

  8. [8]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Daryani, A.E., Bhutta, M., Hernandez, B., Medeiros, H.: Camuvid: Calibration- free multi-view detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 1220–1229 (2025) 5

    2025

  9. [9]

    arXiv preprint arXiv:2408.06604 (2024) 5

    Dong, Z., Zhang, Y., Huang, X., Ji, H., Shi, Z., Zhan, X., Chen, J.: Mv-detr: Multi-modality indoor object detection by multi-view detecton transformers. arXiv preprint arXiv:2408.06604 (2024) 5

    work page arXiv 2024

  10. [10]

    In: IEEE Winter Conference on Applications of Computer Vision (2023) 12

    Engilberge, M., Liu, W., Fua, P.: Multi-view tracking using weakly supervised hu- man motion prediction. In: IEEE Winter Conference on Applications of Computer Vision (2023) 12

    2023

  11. [11]

    In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

    Engilberge, M., Shi, H., Wang, Z., Fua, P.: Two-level data augmentation for cali- brated multi-view detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. pp. 128–136 (2023) 5

    2023

  12. [12]

    arXiv preprint arXiv:2507.08494 (2025) 4, 12, 13

    Engilberge, M., Vrkic, I., Grosche, F.W., Pilet, J., Turetken, E., Fua, P.: One graph to track them all: Dynamic gnns for single-and multi-view tracking. arXiv preprint arXiv:2507.08494 (2025) 4, 12, 13

    work page arXiv 2025

  13. [13]

    Foundation, E.: Eclipse mosquitto.https://mosquitto.org/(2026), message bro- ker for MQTT 11

    2026

  14. [14]

    Multimedia Tools and Applications78, 10773–10793 (2019) 1, 2

    Iguernaissi, R., Merad, D., Aziz, K., Drap, P.: People tracking in multi-camera systems: a review. Multimedia Tools and Applications78, 10773–10793 (2019) 1, 2

    2019

  15. [15]

    In: Pro- ceedings of the 26th ACM International Conference on Multimedia (2018) 4

    Jiang, N., Bai, S., Xu, Y., Xing, C., Zhou, Z., Wu, W.: Online inter-camera trajec- tory association exploiting person re-identification and camera topology. In: Pro- ceedings of the 26th ACM International Conference on Multimedia (2018) 4

    2018

  16. [16]

    Procedia Computer Science (2022) 4

    Jiang, P., Ergu, D., Liu, F., Cai, Y., Ma, B.: A review of YOLO algorithm devel- opments. Procedia Computer Science (2022) 4

    2022

  17. [17]

    ASME Journal of Basic Engineering (1960) 10 16 B

    Kalman, R.E.: A new approach to linear filtering and prediction problems. ASME Journal of Basic Engineering (1960) 10 16 B. Hernandez et al

    1960

  18. [18]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Kim, J., Shin, W., Park, H., Baek, J.: Addressing the occlusion problem in multi-camera people tracking with human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 5463– 5469 (2023) 2

    2023

  19. [19]

    IEEE Transactions on Pattern Analysis and Machine Intelligence (2000) 3, 4

    Lee, L., Romano, R., Stein, G.: Monitoring activities from multiple video streams: Establishing a common coordinate frame. IEEE Transactions on Pattern Analysis and Machine Intelligence (2000) 3, 4

    2000

  20. [20]

    In: European Conference on Computer Vision

    Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Qiao, Y., Dai, J.: BEV- Former: Learning bird’s-eye-view representation from multi-camera images via spa- tiotemporal transformers. In: European Conference on Computer Vision. pp. 1–18. Springer (2022) 4

    2022

  21. [21]

    IEEE Journal of Selected Topics in Signal Processing (2008) 3, 5

    Medeiros, H., Park, J., Kak, A.: Distributed object tracking using a cluster-based Kalman filter in wireless camera networks. IEEE Journal of Selected Topics in Signal Processing (2008) 3, 5

    2008

  22. [22]

    In: Proceedings of the 1998 Image Understanding Workshop, Morgan- Kaufman, San Francisco (1998) 3

    Mikic, I., Santini, S., Jain, R.: Video processing and integration from multiple cameras. In: Proceedings of the 1998 Image Understanding Workshop, Morgan- Kaufman, San Francisco (1998) 3

    1998

  23. [23]

    org/(2019) 11

    MQTT.org: MQTT - The Standard for IoT Messaging — mqtt.org.https://mqtt. org/(2019) 11

    2019

  24. [24]

    Naphade, M., Anastasiu, D.C., Sharma, A., Jagrlamudi, V., Jeon, H., Liu, K., Chang, M.C., Lyu, S., Gao, Z.: The NVIDIA AI City Challenge. In: 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (Smart- World/SCA...

    2017

  25. [25]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023) 1

    Naphade, M., Wang, S., Anastasiu, D.C., Tang, Z., Chang, M.C., Yao, Y., Zheng, L., Rahman, M.S., Arya, M.S., Sharma, A., et al.: The 7th AI city challenge. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023) 1

    2023

  26. [26]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023) 4

    Nguyen, Q.Q.V., Le, H.D.A., Chau, T.T.T., Luu, D.T., Chung, N.M., Ha, S.V.U.: Multi-camera people tracking with mixture of realistic and synthetic knowledge. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023) 4

    2023

  27. [27]

    com/deepstream-sdk(2026) 11

    NVIDIA Corporation: NVIDIA deepstream SDK.https://developer.nvidia. com/deepstream-sdk(2026) 11

    2026

  28. [28]

    com/orgs/nvidia/teams/tao/models/peoplenet(2026), deployable quantized ONNX v2.6.3 11

    NVIDIA Corporation: NVIDIA TAO peoplenet.https://catalog.ngc.nvidia. com/orgs/nvidia/teams/tao/models/peoplenet(2026), deployable quantized ONNX v2.6.3 11

    2026

  29. [29]

    NVIDIA Corporation: NVIDIA TAO peoplenet transformer.https://catalog. ngc . nvidia . com / orgs / nvidia / teams / tao / models / peoplenet _ transformer (2026), deployable v1.1 11

    2026

  30. [30]

    NVIDIA Corporation: NVIDIA TAO toolkit.https://developer.nvidia.com/ tao-toolkit(2026) 11

    2026

  31. [31]

    IEEE Access (2020) 1, 4

    Olagoke, A.S., Ibrahim, H., Teoh, S.S.: Literature survey on multi-camera system and its application. IEEE Access (2020) 1, 4

    2020

  32. [32]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019) 5 MV3DT 17

    Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A.A., Tzionas, D., Black, M.J.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019) 5 MV3DT 17

    2019

  33. [33]

    Machine Vision and Applications (2017) 2, 3, 4

    Previtali, F., Bloisi, D.D., Iocchi, L.: A distributed approach for real-time multi- camera multiple object tracking. Machine Vision and Applications (2017) 2, 3, 4

    2017

  34. [34]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Quach, K.G., Nguyen, P., Le, H., Truong, T.D., Duong, C.N., Tran, M.T., Luu, K.: DyGLIP: A dynamic graph model with link prediction for accurate multi- camera multiple object tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13784–13793 (2021) 4

    2021

  35. [35]

    In: Proceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition (2016) 4

    Redmon, J.: You only look once: Unified, real-time object detection. In: Proceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition (2016) 4

    2016

  36. [36]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017) 4

    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017) 4

    2017

  37. [37]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018) 4

    Ristani, E., Tomasi, C.: Features for multi-target multi-camera tracking and re- identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018) 4

    2018

  38. [38]

    IEEE Transactions on Systems, Man, and Cybernetics: Systems (2022) 4

    Siddique, A., Medeiros, H.: Tracking passengers and baggage items using multiple overhead cameras at security checkpoints. IEEE Transactions on Systems, Man, and Cybernetics: Systems (2022) 4

    2022

  39. [39]

    In: Proceedings

    Stein, G.P.: Tracking from multiple view points: Self-calibration of space and time. In: Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1999) 3

    1999

  40. [40]

    IEEE Signal Processing Magazine (2011) 3

    Taj, M., Cavallaro, A.: Distributed and decentralized multicamera tracking. IEEE Signal Processing Magazine (2011) 3

    2011

  41. [41]

    Tang, Z., Wang, S., Anastasiu, D.C., Chang, M.C., Sharma, A., Kong, Q., Ko- bori, N., Gochoo, M., Batnasan, G., Otgonbold, M.E., Alnajjar, F., Hsieh, J.W., Kornuta, T., Li, X., Zhao, Y., Zhang, H., Radhakrishnan, S., Jain, A., Kumar, R., Murali, V.N., Wang, Y., Pusegaonkar, S.S., Wang, Y., Biswas, S., Wu, X., Zheng, Z., Chakraborty, P., Chellappa, R.: The...

    work page arXiv 2025

  42. [42]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Teepe, T., Wolters, P., Gilg, J., Herzog, F., Rigoll, G.: Lifting multi-view detection and tracking to the bird’s eye view. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 667–676 (2024) 4, 12

    2024

  43. [43]

    In: Advances in Neural Information Processing Systems (2024) 4

    Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: Real- time end-to-end object detection. In: Advances in Neural Information Processing Systems (2024) 4

    2024

  44. [44]

    arXiv preprint arXiv:2402.13616 (2024) 4

    Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: YOLOv9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616 (2024) 4

    work page arXiv 2024

  45. [45]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024) 1, 12

    Wang, S., Anastasiu, D.C., Tang, Z., Chang, M.C., Yao, Y., Zheng, L., Rahman, M.S., Arya, M.S., Sharma, A., Chakraborty, P., et al.: The 8th AI City Challenge. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024) 1, 12

    2024

  46. [46]

    arXiv e-prints pp

    Wang, Y., Meinhardt, T., Cetintas, O., Yang, C.Y., Satish Pusegaonkar, S., Mis- saoui,B.,Biswas,S.,Tang,Z.,Leal-Taixé,L.:Bev-sushi:Multi-targetmulti-camera 3d detection and tracking in bird’s-eye view. arXiv e-prints pp. arXiv–2412 (2024) 4, 14

    2024

  47. [47]

    The University of Nebraska-Lincoln (2013) 5 18 B

    Wang, Y.: Distributed multi-object tracking with multi-camera systems composed of overlapping and non-overlapping cameras. The University of Nebraska-Lincoln (2013) 5 18 B. Hernandez et al

    2013

  48. [48]

    In: 2017 IEEE International Conference on Image Processing (ICIP) (2017) 7, 9

    Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP) (2017) 7, 9

    2017

  49. [49]

    In: CVPR Workshop

    Xie, Z., Ni, Z., Yang, W., Zhang, Y., Chen, Y., Zhang, Y., Ma, X.: A robust online multi-camera people tracking system with geometric consistency and state-aware re-id correction. In: CVPR Workshop. Seattle, WA, USA (2024) 14

    2024

  50. [50]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Yamane, T., Masumura, R., Suzuki, S., Orihashi, S.: Mvtrajecter: Multi-view pedestrian tracking with trajectory motion cost and trajectory appearance cost. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13270–13280 (2025) 4, 12

    2025

  51. [51]

    Scientific Reports (2022) 2, 3, 4

    Yang, S., Ding, F., Li, P., Hu, S.: Distributed multi-camera multi-target association for real-time tracking. Scientific Reports (2022) 2, 3, 4

    2022

  52. [52]

    Computer Vision and Image Understanding249, 104203 (2024) 4

    Yang, Y., Xu, M., Ralph, J.F., Ling, Y., Pan, X.: An end-to-end tracking frame- work via multi-view and temporal feature aggregation. Computer Vision and Image Understanding249, 104203 (2024) 4

    2024

  53. [53]

    IEEE Transactions on Image Processing (2010) 3

    Yoder,J.,Medeiros,H.,Park,J.,Kak,A.C.:Cluster-baseddistributedfacetracking in camera networks. IEEE Transactions on Image Processing (2010) 3

    2010

  54. [54]

    In: CVPR Workshop

    Yoshida, R., Okubo, J., Fujii, J., Amakata, M., Yamashita, T.: Overlap suppression clustering for offline multi-camera people tracking. In: CVPR Workshop. Seattle, WA, USA (2024) 14

    2024

  55. [55]

    In: European Conference on Computer Vision (2022) 8

    Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., Wang, X.: Bytetrack: Multi-object tracking by associating every detection box. In: European Conference on Computer Vision (2022) 8

    2022

  56. [56]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: RT- DETR: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 16788– 16797 (2024) 4

    2024

  57. [57]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2023) 4

    Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2023) 4

    2023