CoChat

Edge-Constrained Video Analytics: A Comprehensive Survey on Detection, Tracking, and Recognition

Open access
Toshpulatov, Mukhiddin Amonkulovich, Lee, Wookey, Cho, Jinsoo · 2026 · SSRN Electronic Journal

The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.

Abstract

A comprehensive survey of edge-constrained video analytics, including detection, tracking, recognition, edge hardware, edge-cloud collaboration, privacy-preserving machine learning, fairness, and regulatory issues.

Overview

Integrity signals

Registry

Crossref · 10.2139/ssrn.6614394

Cites

60 of 60 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Research works printed but not linked: 58

  1. G Jocher, 2024, Advancing real-time object detection with enhanced architecture, 11
  2. 2024, NVIDIA Jetson Orin: Next-generation edge AI computing, NVIDIA Developer Blog
  3. Hailo Technologies, 2024, Hailo-10H: Next-generation edge AI processor with generative AI support
  4. Regulation 2024/1689 of Parliament and Council laying down harmonised rules (AI Act), Off. J. Eur. Union
  5. J Chen, 2019, Deep learning for edge computing applications: A stateof-the-art survey, IEEE Access, 7, 6974
  6. W Luo, 2021, Multiple object tracking, Artif. Intell, 293
  7. 2024, Market guide for edge AI platform, Research Report
  8. J Chen, 2023, Edge-cloud collaborative video analytics: A survey, ACM Computing Surveys, 55, 1
  9. Q Wang, 2024, A comprehensive survey on multi-object tracking: From traditional methods to DL, Pattern Recognition, 148
  10. K Yi, 2023, REVAMP2T: Privacy-aware real-time video analytics with multi-camera tracking at edge, 3154
  11. H Tang, 2024, OCTOPINF: Multi-tenant edge inference with gpu colocation and workload scheduling, 456
  12. D Jia, 2023, DETRs with collaborative hybrid assignments training, 6748
  13. W Chen, 2024, Queue-aware adaptive edgecloud inference for video analytics, Proceedings of the SEC
  14. Jain, 2023, SPATULA: Efficient cross-camera video analytics on large camera networks, 110
  15. Z Liu, 2024, MobileLLM: Optimizing sub-billion parameter language models for on-device use cases
  16. G Jocher, 2023, YOLOv, 8
  17. Y Gao, 2024, MOTIP: Multi-object tracking
  18. T.-Y Lin, 2017, Focal loss for dense od, 2980
  19. Z Tian, 2019, FCOS: FC one-stage OD, 9627
  20. N Carion, 2020, End-to-end object detection with transformers, 213
  21. X Zhu, 2021, Deformable DETR: for object detection
  22. W A Lv, 2025, RT-DETRv2: Improved baseline with bag-of-freebies for realtime detection transformer
  23. G Jocher, 2022, YOLOv5 by ultralytics
  24. C Li, 2022, YOLOv6: A single-stage object detection framework for industrial applications
  25. 2022, NVIDIA Jetson platform for embedded computing
  26. G Hinton, 2015, Distilling knowledge in a nn
  27. A Milan, 2016, A benchmark for mot, 16
  28. Y A Du, 2023, StrongSORT: Make DeepSORT great again, IEEE TM, 25, 8725
  29. N Aharon, 2022, Robust associations multi-pedestrian tracking
  30. F Zeng, 2022, MOTR: End-to-end multiple-object tracking with transformer, 659
  31. G Maggiolino, 2024, HopTrack: A real-time multi-object tracking system for embedded devices, 1234
  32. Z Wang, 2020, Towards real-time mot, 107
  33. W Zhang, 2024, OMAN++ multimodal object trackin
  34. J Kim, 2024, Keyframe-based point tracking with temporal prediction
  35. K Bae, 2023, Diffusion-c: Unveiling the generative challenges of diffusion models through corrupted data
  36. S Li, 2024, Matching any by segmenting, 18961
  37. P Sun, 2024, AR-MOT: Autoregressive MOT
  38. Z Xu, 2024, HomView-MOT: Homographic view-centric multi-object tracking for moving cameras
  39. E Luna, 2022, Graph-based spatial-temporal feature learning for multicamera tracking, 2279
  40. J Lee, 2024, SAE-MCVT: Self-supervised association for edge multi-camera vehicle tracking
  41. M Naphade, 2024, The 8th AI city challenge, 7271
  42. J Guo, SCRFD: Sample and computation redistribution for efficient face detection, Proceedings of the International Conference on Learning Representations (ICLR)
  43. Y Du, 2022, SVTR: Scene text recognition with a single visual model, IJCAI, 884
  44. Y Zou, 2020, A robust chinese license plate detection and recognition system, Pattern Recognition, 100
  45. X Chen, 2024, Deformable DETR++: Efficient and more efficient for object detection and segmentation, 16798
  46. T Wang, 2023, STEERER: Resolving scale variations for counting and localization via selective inheritance learning, ICCV
  47. S M Marvasti-Zadeh, 2021, Deep learning for action and gesture recognition in image sequences, Pattern Recognition, 110
  48. F Safarov, 2025, Hyperspectral anomaly detection with enhanced spectral graph transformer network, IEEE Access, 12, 234
  49. Hailo Technologies, 2022, Hailo-8: High-performance edge AI processor
  50. Llc Google, 2019, Google Coral edge TPU platforms
  51. Qualcomm Technologies, 2023, Qualcomm Snapdragon: Mobile AI processing, Qualcomm Technical Documentation
  52. W Liu, 2024, Multi-modal inference at the edge for video understanding, 3456
  53. W Zhang, 2024, How2compress: Analytics-aware video compression for edge intelligence, Proc. ACM Multimedia
  54. J Park, 2023, MONDRIAN: Prompt-based roi packing and canvas inference for efficient edge vision analytics, Proc. USENIX NSDI
  55. Y Li, 2024, Legilimens: Practical and unified on-device continual adaptation for edge intelligence, Proc. ACM MobiSys
  56. B Chen, 2024, Dynamic model switching for adaptive edge inference, Proc. IEEE INFOCOM
  57. L Lyu, 2022, Privacy, robustness in federated learning, TNNLS
  58. A Radford, 2021, Learning transferable visual models from natural language supervision, 8748

Metadata

Authors
Toshpulatov, M. A., Lee, W., & Cho, J.
Affiliations
  • Inha University (KR)
  • Gachon University (KR)
Corresponding author
Cho, Jinsoo
Venue
SSRN Electronic Journal
Publisher
Elsevier BV
Published
2026
ISSN
1556-5068 (ISSN-L)
OpenAlex
W7154950739
Cited by
0
References
15
Type
posted content
Language
en
Open access
Locations
SSRN Electronic Journal (acceptedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
Keywords
object detection, multi-target tracking, face recognition, license plate recognition, YOLO, RT-DETR, tracking-by-detection, LITE, cloud-edge collaboration, privacy-preserving machine learning, algorithmic fairness, EU AI Act, federated continual learning, responsible AI governance, embedded systems

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.