Distributed and Efficient Object Detection in Edge Computing: Challenges and Solutions
The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
In the past decade, it was a significant trend for surveillance applications to send huge amounts of real-time media data to the cloud via dedicated high-speed fiber networks. However, with the explosion of mobile devices and services in the era of Internet-of-Things, it becomes more promising to undertake real-time data processing at the edge of the network in a distributed way. Moreover, in order to reduce the investment of network deployment, media communication in surveillance applications is gradually changing to be wireless. It consequently poses great challenges to detect objects at the edge in a distributed and communication-efficient way. In this article, we propose an edge computing based object detection architecture to achieve distributed and efficient object detection via wireless communications for real-time surveillance applications. We first introduce the proposed architecture as well as its potential benefits, and identify the associated challenges in the implementation of the architecture. Then, a case study is presented to show our preliminary solution, followed by performance evaluation results. Finally, future research directions are pointed out for further studies.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“At the end level, video capture devices, such as smartphones and surveillance cameras are responsible for video capture, media data compression [102], image preprocessing, and image segmentation [103].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [102]
In the citing paper
“Since the distributed model training performance on an edge node may be significantly impaired due to its local knowledge, the cloud needs to integrate different well-trained DL models to achieve global knowledge.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [102]
In the citing paper
“At the cloud level, the cloud is responsible for the integration of DL models among the edge layer and updating parameters of distributed DL models on edge nodes [102].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [102]
In the citing paper
“The emerging 5G technology further enhances the advances of edge computing from the perspective of low latency transmission, which empowers a series of emerging applications, such as autonomous driving [24], virtual reality/augmented reality and healthcare-related applications.”
From Deep learning for edge computing applications: A State-of-the-Art survey (2020) · cites this paper as [24]
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“Edge servers adopt Faster R-CNN for model training and object detection [9], and can also adaptively control end devices to adjust the size of RoI areas according to their detection accuracy.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 1×
“Edge servers adopt Faster R-CNN for model training and object detection [9], and can also adaptively control end devices to adjust the size of RoI areas according to their detection accuracy.”
MethodThe JPEG still picture compression standard
Wallace, G. K. (1992) · IEEE Transactions on Consumer Electronics · doi:10.1109/30.125072 · Cited by 2,851
The PASCAL visual object classes challenge 2006 (VOC2006) results
Everingham, M., Zisserman, A., Williams, C. K. I., & Gool, L. V. (2006) · Cited by 2,223
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Cheng, M.-M., Zhang, Z., Lin, W.-Y., & Torr, P. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.414 · Cited by 1,050
Guo, C., & Zhang, L. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2030969 · Cited by 934 · cited 2×
“[11] C.”
Fadlullah, Z. M., Tang, F., Mao, B., Kato, N., Akashi, O., Inoue, T., & Mizutani, K. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2707140 · Cited by 810 · cited 1×
“In addition, compared to cloud computing, distributed edge training and inference may lack global knowledge for object detection [3].”
BackgroundServing at the Edge: A Scalable IoT Architecture Based on Transparent Computing
Ren, J., Guo, H., Xu, C., & Zhang, Y. (2017) · IEEE Network · doi:10.1109/mnet.2017.1700030 · Cited by 416 · cited 9×
“His research interests include Internet-of-Things, transparent computing and edge computing.”
BackgroundInfluentialSelf-citationRodrigues, T. G., Suto, K., Nishiyama, H., & Kato, N. (2017) · IEEE Transactions on Computers · doi:10.1109/tc.2016.2620469 · Cited by 374 · cited 8×
“His research interests include Internet-of-Things, transparent computing and edge computing.”
BackgroundInfluentialLIBLINEAR: A Library for Large Linear Classification
FanRong-En, ChangKai-Wei, HsiehCho-Jui, WangXiang-Rui, & LinChih-Jen (2008) · Journal of Machine Learning Research · doi:10.5555/1390681.1442794 · Cited by 328 · cited 1×
“BING uses binary approximation [12] of a linear support vector machine (SVM) [13] to efficiently evaluate whether there is an object in an image window.”
MethodDynamic Channel Access to Improve Energy Efficiency in Cognitive Radio Sensor Networks
Ren, J., Zhang, Y., Zhang, N., Zhang, D., & Shen, X. (2016) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2016.2517618 · Cited by 192 · cited 1×
“Since the data generation rate in media applications far exceeds the bandwidth of wireless channels, IoT terminals have to compress the raw media data before transmission [7].”
BackgroundSelf-citationZhang, D., Chen, Z., Awad, M. K., Zhang, N., Zhou, H., & Shen, X. S. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2611960 · Cited by 172 · cited 1×
“Real-time media data is first captured by IoT devices and then transmitted to edge servers for object detection [5].”
MethodSelf-citationA Survey on Emerging Computing Paradigms for Big Data
Zhang, Y., Ren, J., Liu, J., Xu, C., Guo, H., & Liu, Y. (2017) · Chinese Journal of Electronics · doi:10.1049/cje.2016.11.016 · Cited by 163 · cited 8×
“His research interests include Internet-of-Things, transparent computing and edge computing.”
BackgroundInfluentialSelf-citationEfficient online structured output learning for keypoint-based object tracking
Hare, S., Saffari, A., & Torr, P. H. S. (2012) · 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.2012.6247889 · Cited by 130 · cited 1×
“BING uses binary approximation [12] of a linear support vector machine (SVM) [13] to efficiently evaluate whether there is an object in an image window.”
MethodSecure Content Delivery With Edge Nodes to Save Caching Resources for Mobile Users in Green Cities
Xu, Q., Su, Z., Zheng, Q., Luo, M., & Dong, B. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2787201 · Cited by 82 · cited 1×
“By leveraging the data storage and processing capabilities of nearby infrastructures and devices, edge computing can provide distributed and timely media data analyzing services for surveillance applications [2].”
Background
Research works printed but not linked: 2
- everingham, 0, The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results
- zhu, 2004, Recall Precision and Average Precision, 2, 30
Cited by
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“1) End Level: At the end level, video capture devices, such as smartphones and surveillance cameras are responsible for video capture, media data compression [102], image”
BackgroundMethodInfluentialRen, J., Zhang, D., He, S., Zhang, Y., & Li, T. (2020) · ACM Computing Surveys · doi:10.1145/3362031 · Cited by 615
“Therefore, finding ways to leverage the orchestration of end devices, edge servers, and the cloud to design sophisticated security solutions becomes a hot research trend for all the network computing paradigms [124].”
BackgroundSelf-citationJoint Computation Offloading and User Association in Multi-Task Mobile Edge Computing
Dai, Y., Xu, D., Maharjan, S., & Zhang, Y. (2018) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2018.2876804 · Cited by 372
“, surveillance, augmented/virtual reality, and e-Health care) through both machine-to-machine and machine-to-human interactions [1], [2].”
Self-citationRSOD: Real-time small object detection algorithm in UAV-based traffic monitoring
Sun, W., Dai, L., Zhang, X., Chang, P., & He, X. (2022) · Applied Intelligence · doi:10.1007/s10489-021-02893-3 · Cited by 281
Efficient Computing Resource Sharing for Mobile Edge-Cloud Computing Networks
Zhang, Y., Lan, X., Ren, J., & Cai, L. (2020) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2020.2979807 · Cited by 261
“For the network access technology, [8] proposed heuristic link-path formulations, which can design mobile access networks in a reasonable time and [24] proposed an MEC-based object detection architecture via wireless communications for real-time surveillance applications.”
BackgroundSelf-citation
Metadata
- Authors
- Ren, J., Guo, Y., Zhang, D., Liu, Q., & Zhang, Y.
- Affiliations
- Central South University (CN)
- Venue
- IEEE Network
- Published
- 2018-11
- Volume
- 32
- Issue
- 6
- Pages
- 137-143
- ISSN
- 0890-8044 (ISSN-L)
- 1558-156X
- OpenAlex
- W2797952247
- Cited by
- 148
- References
- 14
- Citations by year
- 2026: 6 · 2025: 16 · 2024: 14 · 2023: 25 · 2022: 20 · 2021: 27 · 2020: 22 · 2019: 12 · 2018: 6
- FWCI
- 10.37
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Network (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Central South University
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- edge computing, object detection, real-time surveillance, wireless communication, Internet of Things, communication efficiency, edge computing architecture
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.