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.”
Method
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
Items 101–147 of 147
Nedelkoski, S., Thamsen, L., Verbitskiy, I., & Kao, O. (2019) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge.2019.00015 · Cited by 5
“For example, an advantage is that the models can be trained on the collected data on seemingly unlimited cloud resources before they are transmitted to the edge devices and utilized for prediction on the data streams in near real-time [6].”
BackgroundAn Edge–Cloud Collaborative Scalp Inspection System Based on Robust Representation Learning
Jhong, S.-Y., Li, G.-T., & Hsia, C. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3474911 · Cited by 5
Mobile edge computing resource allocation: An operating system view
Chen, X. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.107925 · Cited by 3
Distributing intelligence for object detection using edge computing
Chakroun, I., Aa, T. V., Roel Wuyts, B., & Verachtert, W. (2021) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud53861.2021.00087 · Cited by 3
“In [11] and [12], an object detection architecture based on edge computing for surveillance applications is presented.”
BackgroundAn algorithm of fuzzy edge detection for wetland remote sensing image based on fuzzy theory
He, D., & Wang, G. (2022) · Applied Nanoscience · doi:10.1007/s13204-021-02209-4 · Cited by 3
“5 and 1, so that the contrast of wetland remote sensing image is increased and the clarity of wetland remote sensing image is enhanced (Ju et al. 2018).”
BackgroundInfluentialOnline Market Mechanism for Mobile Data Rate Trading With Temporal Constraints
He, J., Zhang, D., Ren, J., Zhou, Y., & Zhang, Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3168061 · Cited by 3
“The bid value is further computed based on the product of the overall data rate demands and the unit demand valuation randomly sampled from distribution [6, 24] over the accessing time window, i.”
MethodSelf-citationWang, L., Gao, Y., Cai, G., & Shen, C. (2026) · World Electric Vehicle Journal · doi:10.3390/wevj17030156 · Cited by 2
Artificial Intelligence Applications on Edge
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_4 · Cited by 2
Li, W., Huang, Y., He, C., Xu, C., Xu, P., Gao, T., & Zhang, J. (2022) · IEEE International Conference on Digital Twins and Parallel Intelligence (DTPI) · doi:10.1109/dtpi55838.2022.9998943 · Cited by 2
“In [7], approximate cooperative computing offloading algorithm and game theory are introduced to realize joint offloading between cloud and edge computing.”
MethodComputation offloading and heterogeneous task caching in MEC-enabled vehicular networks
Wu, R., & Li, B. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05328-7 · Cited by 2
An Edge Computing-Enabled Track Obstacle Detection Method Based on YOLOv5
Zhang, Z., Cai, Y., Lu, H., Wen, T., & Cai, B. (2023) · International Conference on Electromagnetics in Advanced Applications (ICEAA) · doi:10.1109/iceaa57318.2023.10297912 · Cited by 2
EdgeInsight: An Agent-Driven Framework for System Health Monitoring in Edge Computing Platforms
Ayyappan, B., & Kumar, G. S. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-97-6957-5_19 · Cited by 2
Deployment of Object Detection Enhanced with Multi-label Multi-classification on Edge Device
Oderhohwo, O., Odetola, T. A., Mohammed, H., & Hasan, S. R. (2020) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas48704.2020.9184601 · Cited by 2
“Conventional object detection algorithms offer huge cost of computation making their deployment on edge devices challenging [5].”
BackgroundEfficient Computing Resource Sharing for Mobile Edge-Cloud Computing Networks
Mishra, S., Gupta, A., & Naik, K. J. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-5191-6_42 · Cited by 2
Edge Computing for Real-Time Video Stream Analytics
Hu, M., Zhuang, L., Wu, D., Huang, Z., & Hu, H. (2018) · Springer eBooks · doi:10.1007/978-3-319-32903-1_275-1 · Cited by 2
Cheng, C., Dai, H., Li, L., Wang, J., & Gu, F. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-67537-0_12 · Cited by 1
Generative Model-Based Edge-Assisted Object Detection in Bandwidth-Constrained Network
Liu, J., Luo, K., Wang, H., & Chen, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71464-1_26 · Cited by 1
Optimization of Managing Resources in Edge-Cloud Networks
Bansal, S., Mittal, A., Habelalmateen, M. I., Manhas, S., Achilov, A., & Joshi, A. (2024) · International Conference on Communication, Computing and Energy Efficient Technologies (I3CEET) · doi:10.1109/i3ceet61722.2024.10993638 · Cited by 1
Yang, X., Peng, Z., & Xie, X. (2025) · Sensors · doi:10.3390/s25216628 · Cited by 2
Tammisetti, V., Stettinger, G., Cuéllar, M. P., & Molina-Solana, M. (2025) · Applied Sciences · doi:10.3390/app152211964 · Cited by 1
Sun, Y., Qin, Y., Chen, W., Zhao, W., & Sun, H. (2026) · Electronics · doi:10.3390/electronics15132879 · Cited by 1
MCSEC: Secure Coded Matrix Multiplication Scheme for Edge Computing with Minimum Communication Cost
Dong, T., Wang, J., Gu, F., Zhou, J., Lu, K., & Wang, J. (2020) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00050 · Cited by 1
“Edge computing, a new computing paradigm, was proposed as it adopted the nearby edge devices to process data timely, hence reducing completion time for computing tasks [2], [3].”
BackgroundMethodTracking Missing Objects in a Video Using YOLO3 in Cloudlet Network
Srilatha, M., Srinivasu, N., & Karthik, B. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-16-1773-7_30 · Cited by 1
Privacy-Preserving Multi-Party Machine Learning for Object Detection
Chakroun, I., Aa, T. V., Wuyts, R., & Verarcht, W. (2021) · IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) · doi:10.1109/gcaiot53516.2021.9692980 · Cited by 1
Edge Computing Offloading Strategy for Fast Diagnosis of Image of Substation
Xue, H., Zhu, X., Wang, Z., Liu, Z., Lu, Y., & Hu, C. (2022) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac54830.2022.9929798 · Cited by 1
Edge Analytics and Deep Learning for Sustainable Development
Singh, S. K., Chakraborty, S., & Soodan, V. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-70183-3_10 · Cited by 1
Edge Computing for Real-Time Video Stream Analytics
Hu, M., Zhuang, L., Wu, D., Huang, Z., & Hu, H. (2020) · Springer eBooks · doi:10.1007/978-3-319-78262-1_275 · Cited by 1
Complementary Approach for Image Edge Detection Using Rough Mirror Mapping in Neural Network
Bhat, N. N., Eranna, U., & Singh, M. K. (2018) · International Journal of Engineering & Technology · doi:10.14419/ijet.v7i3.4.16760
Lessons Learned and Open Challenges
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_9
Explainable AI in Internet of Control System Distributed at Edge-Cloud Architecture
Roopaei, M., Durian, H., & Godiska, J. (2021) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.c2246.0210321
Berthier, G. N., Gomes, D. L., Maia, I. M. O., & de Paiva, A. C. (2021) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.5753/sibgrapi.est.2021.20044
Research on Low Power Technology of Power Wireless Private Network Based on Computational Offloading
Bu, X., Shi, Q., Bu, X., Shi, X., Li, S., & Bu, X. (2022) · IEEE Conference on Energy Internet and Energy System Integration (EI2) · doi:10.1109/ei256261.2022.10116161
Federated Learning based Object Detection using Dampened Harmonic Optimization
Jain, D. K., Khanna, A., Gera, B., & Sangwan, D. (2023) · International Conference on Machine Learning and Soft Computing (ICMLSC) · doi:10.1145/3583788.3583815
“[26] and [4] look to intelligently perform object detection in cloud-edge systems.”
BackgroundEdge Computing Task Scheduling Based on Improved African Vulture Optimization Algorithm
Shi, Y., Huang, L. Q., & Gu, J. (2023) · International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE) · doi:10.1109/cbase60015.2023.10439073
“With the further development of edge computing, distributed edge computing, which is one of the most extended and deepened edge computing [4] , has been widely used and promoted, and has become an important computing model for IoT, but it also brings new problems and challenges.”
BackgroundHeteroEML: Heterogeneous Design Methodology of Edge Machine Learning on CPU+FPGA Platform
Wu, Y.-T., Yen, T.-Y., Lin, Y., & Lai, B.-C. C. (2024) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas59952.2024.10595974
“The advancement of Machine Learning (ML) is increasingly evident in edge computing applications, spanning from simple object classification [1] and recognition [2] to complex super-resolution [3].”
BackgroundLin, Z., Ji, C., Yan, W., Huang, T., & Hong, Q. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662165
Investigating Salient Object Detection Methods Tailored for Edge Computing Infrastructure
Sebastian, E., & Martin, J. P. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-79041-6_30
Surface feature recognition of surrounding rock of TBM tunnel based on mask R-CNN model
Zhang, X., & Liu, Y. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adf945
Kuvakohteiden tunnistus koneoppimisen ja reunalaskennan avulla
Kuulasmaa, O. (2024) · LUTPub (LUT University)
Retracted: Edge Computing and Real-Time Analytics as the Next Frontier for Big Data in IT Companies
Radhakrishnan, P., Shravani, K., Prasadula, N., Maheshwari, S., Acharjee, P. B., & Dhanraj, J. A. (2025) · IEEE International Conference on Smart Innovations in Systems, Infrastructure, Mechanical, Power, AI and Computing Technologies (SISIMPACT) · doi:10.1109/sisimpact67725.2025.11439636
“The progress in big data processing has also led to a large change in the concept of cloud computing being centralized to more decentralized approaches, largely because of struggles in cloud design with real-time data that are latency sensitive [10].”
RetractedModel Training for Edge Video Analytics
Bai, T. (2025) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-14764-6_4
End-Edge-Cloud Orchestration for Video Analytics
Bai, T. (2025) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-14764-6_6
DIMO: Constrained Computing Power Information Dissemination with Multi-hop Task Offloading
Xu, W., Zhang, X., Li, X., 甘天春, Wang, Z., & Luo, H. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571234
“The rapid proliferation of the Internet of Things (IoT) is fueling an insatiable demand for intelligent applications, yet this very progress is starkly constrained by the limited computational power of ubiquitous edge devices [1].”
Wu, J.-T., Hsieh, T.-Y., Ichihara, H., & Inoue, T. (2026) · IEEE Access · doi:10.1109/access.2026.3710200
“These capabilities are enabled by recent developments in Edge Computing, Wireless Multimedia Sensor Networks (WMSNs), and AI edge devices, which allow object detection and anomaly analysis to be executed locally on edge nodes without relying on cloud resources [5], [6], [7], [8].”
Efficiency and Temporal Reasoning in Transformer-Based Video Object Detection: A Systematic Review
Keravnos, Y., Ioannou, A., Papadopoulos, A., & Lesta, V. P. (2026) · Journal of Imaging · doi:10.3390/jimaging12090419
Song, J., Wang, J., Yan, J., Ma, P., & Yi, S. (2026) · Applied Sciences · doi:10.3390/app16178783
“Regarding multi-tier collaborative architectures, Lu et al. [10] designed a lightweight mobile computation offloading framework, while Ren et al. [11] proposed a distributed edge-based object detection architecture for video surveillance applications, validating the effectiveness of distributed…”
Jhong, S.-Y., Wu, Y.-C., & Hsia, C. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3744010
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.