Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Efficient Object Re-Identification with A Novel Cloud-Edge Collaborative Framework (2401.02041v2)

Published 4 Jan 2024 in cs.CV

Abstract: Object re-identification (ReID) is committed to searching for objects of the same identity across cameras, and its real-world deployment is gradually increasing. Current ReID methods assume that the deployed system follows the centralized processing paradigm, i.e., all computations are conducted in the cloud server and edge devices are only used to capture images. As the number of videos experiences a rapid escalation, this paradigm has become impractical due to the finite computational resources in the cloud server. Therefore, the ReID system should be converted to fit in the cloud-edge collaborative processing paradigm, which is crucial to boost its scalability and practicality. However, current works lack relevant research on this important specific issue, making it difficult to adapt them into a cloud-edge framework effectively. In this paper, we propose a cloud-edge collaborative inference framework for ReID systems, aiming to expedite the return of the desired image captured by the camera to the cloud server by learning the spatial-temporal correlations among objects. In the system, a Distribution-aware Correlation Modeling network (DaCM) is particularly proposed to embed the spatial-temporal correlations of the camera network implicitly into a graph structure, and it can be applied 1) in the cloud to regulate the size of the upload window and 2) on the edge device to adjust the sequence of images, respectively. Notably, the proposed DaCM can be seamlessly combined with traditional ReID methods, enabling their application within our proposed edge-cloud collaborative framework. Extensive experiments demonstrate that our method obviously reduces transmission overhead and significantly improves performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. An improved deep learning architecture for person re-identification. In CVPR, pages 3908–3916. IEEE Computer Society, 2015.
  2. Recent advances in evolving computing paradigms: Cloud, edge, and fog technologies. Sensors, 22(1):196, 2022.
  3. Person re-identification by deep learning multi-scale representations. In ICCVW, pages 2590–2600. IEEE Computer Society, 2017.
  4. Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In CVPR, pages 1335–1344. IEEE Computer Society, 2016.
  5. Joint person re-identification and camera network topology inference in multiple cameras. Comput. Vis. Image Underst., 180:34–46, 2019.
  6. CDC: classification driven compression for bandwidth efficient edge-cloud collaborative deep learning. In IJCAI, pages 3378–3384. ijcai.org, 2020.
  7. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR. OpenReview.net, 2021.
  8. Cloud-device collaborative adaptation to continual changing environments in the real-world. In CVPR. IEEE, 2023.
  9. Deep residual learning for image recognition. In CVPR, pages 770–778. IEEE Computer Society, 2016.
  10. Fastreid: A pytorch toolbox for general instance re-identification. In ACM MM, pages 9664–9667. ACM, 2023.
  11. Transreid: Transformer-based object re-identification. In ICCV, pages 14993–15002. IEEE, 2021.
  12. Real-time surveillance video salient object detection using collaborative cloud-edge deep reinforcement learning. In IJCNN, pages 1–8. IEEE, 2021.
  13. Camera network based person re-identification by leveraging spatial-temporal constraint and multiple cameras relations. In MMM, pages 174–186. Springer, 2016.
  14. Su V. Huynh. A strong baseline for vehicle re-identification. In CVPRW, pages 4147–4154. Computer Vision Foundation / IEEE, 2021.
  15. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, pages 448–456. JMLR.org, 2015.
  16. Spatula: Efficient cross-camera video analytics on large camera networks. In IEEE/ACM SEC, pages 110–124. IEEE, 2020.
  17. High-efficiency device-cloud collaborative transformer model. In CVPR, pages 2204–2210, 2023.
  18. Human semantic parsing for person re-identification. In CVPR, pages 1062–1071. Computer Vision Foundation / IEEE Computer Society, 2018.
  19. Clip-reid: Exploiting vision-language model for image re-identification without concrete text labels. In AAAI, pages 1405–1413. AAAI Press, 2023.
  20. Person re-identification by local maximal occurrence representation and metric learning. In CVPR, pages 2197–2206. IEEE Computer Society, 2015.
  21. Improving person re-identification by attribute and identity learning. Pattern Recognit., 95:151–161, 2019.
  22. Beyond human-level license plate super-resolution with progressive vehicle search and domain priori GAN. In ACM MM, pages 1618–1626, 2017.
  23. Large-scale vehicle re-identification in urban surveillance videos. In ICME, pages 1–6. IEEE Computer Society, 2016a.
  24. A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In ECCV, pages 869–884, 2016b.
  25. Bag of tricks and a strong baseline for deep person re-identification. In CVPRW, pages 1487–1495. Computer Vision Foundation / IEEE, 2019.
  26. Learning instance-level spatial-temporal patterns for person re-identification. In ICCV, pages 14910–14919. IEEE, 2021.
  27. Performance measures and a data set for multi-target, multi-camera tracking. In ECCVW, pages 17–35, 2016.
  28. A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In CVPR, pages 420–429. Computer Vision Foundation / IEEE Computer Society, 2018.
  29. Svdnet for pedestrian retrieval. In ICCV, pages 3820–3828. IEEE Computer Society, 2017.
  30. Beyond part models: Person retrieval with refined part pooling (and A strong convolutional baseline). In ECCV, pages 501–518. Springer, 2018.
  31. Circle loss: A unified perspective of pair similarity optimization. In CVPR, pages 6397–6406. Computer Vision Foundation / IEEE, 2020.
  32. Attention is all you need. In NeurIPS, pages 5998–6008, 2017.
  33. Spatial-temporal person re-identification. In AAAI, pages 8933–8940. AAAI Press, 2019.
  34. Smarteye: An open source framework for real-time video analytics with edge-cloud collaboration. In ACM MM, pages 3767–3770. ACM, 2021.
  35. Edge-cloud collaboration enabled video service enhancement: A hybrid human-artificial intelligence scheme. IEEE TMM, 23:2208–2221, 2021.
  36. Deep learning for person re-identification: A survey and outlook. IEEE TPAMI, 44(6):2872–2893, 2022.
  37. Device-edge-cloud collaborative acceleration method towards occluded face recognition in high-traffic areas. IEEE TMM, 25:1513–1520, 2023.
  38. Scalable person re-identification: A benchmark. In ICCV, pages 1116–1124. IEEE Computer Society, 2015.
  39. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In ICCV, pages 3774–3782. IEEE Computer Society, 2017.
  40. Pedestrian alignment network for large-scale person re-identification. IEEE Trans. Circuits Syst. Video Technol., 29(10):3037–3045, 2019.
  41. Re-ranking person re-identification with k-reciprocal encoding. In CVPR, pages 1318–1327, 2017.
  42. Performance optimization for federated person re-identification via benchmark analysis. CoRR, abs/2008.11560, 2020.
  43. Joint optimization in edge-cloud continuum for federated unsupervised person re-identification. In ACM MM, pages 433–441, 2021.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now