Real-Time Video Analytics: The Killer App for Edge Computing
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Video analytics will drive a wide range of applications with great potential to impact society. A geographically distributed architecture of public clouds and edges that extend down to the cameras is the only feasible approach to meeting the strict real-time requirements of large-scale live video analytics.
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
“real-time video analytics is envisioned to be a killer application for edge computing [12], [37], [38].”
From Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019) · cites this paper as [12]
Citations
Cites
Han, S., Shen, H., Philipose, M., Agarwal, S., Wolman, A., & Krishnamurthy, A. (2016) · Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/2906388.2906396 · Cited by 367 · cited 11×
“Execution of DNNs on GPUs is made dramatically more efficient by running a DNN execution service on each machine that handles all DNN requests on the GPU (described below in “Efficient DNNs execution on GPUs”).”
BackgroundMethodInfluentialSelf-citationGlimpse: Continuous, Real-Time Object Recognition on Mobile Devices
Chen, T. Y.-H., Ravindranath, L., Deng, S., Bahl, P., & Balakrishnan, H. (2015) · Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/2809695.2809711 · Cited by 358
Self-citation(2017) · Networked Systems Design and Implementation · Cited by 329
Self-citationThe Design and Implementation of a Wireless Video Surveillance System
Zhang, T., Chowdhery, A., Bahl, P. (., Jamieson, K., & Banerjee, S. (2015) · Proceedings of the 21st Annual International Conference on Mobile Computing and Networking · doi:10.1145/2789168.2790123 · Cited by 272 · cited 2×
“The system we have developed processes the incoming video stream at each of the intelligent cameras and/or edge nodes to detect objects of interest [8].”
MethodSelf-citationLow Latency Geo-distributed Data Analytics
Pu, Q., Ananthanarayanan, G., Bodik, P., Kandula, S., Akella, A., Bahl, P., & Stoica, I. (2015) · Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication · doi:10.1145/2785956.2787505 · Cited by 246 · cited 1×
“This is analogical to big data analytics whose original focus was on executing on a single cluster but now is beginning to execute across geo-distributed clusters [2].”
BackgroundSelf-citationScalable crowd-sourcing of video from mobile devices
Simoens, P., Xiao, Y., Pillai, P., Chen, Z., Ha, K., & Satyanarayanan, M. (2013) · Proceeding of the 11th annual international conference on Mobile systems, applications, and services · doi:10.1145/2462456.2464440 · Cited by 164 · cited 2×
“Video storage is a key component of our stack and we intend to build upon ideas from prior work like GigaSight [12] for faster cataloging and retrieval of videos.”
MethodDynamic Network Surgery for Efficient DNNs
Guo, Y., Yao, A., & Chen, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.04493 · Cited by 137 · cited 1×
“The machine learning community has proposed several optimizations such as replacing matrices with smaller factors [9], limiting the number of bits used to represent model parameters [11] and reducing the architectural complexity of models in systematic ways [10].”
MethodA Scalable and Privacy-Aware IoT Service for Live Video Analytics
Wang, J., Amos, B., Das, A., Pillai, P. S., Sadeh, N., & Satyanarayanan, M. (2017) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3083187.3083192 · Cited by 123 · cited 1×
“While the infrastructure in Figure 1 is general enough to capture all video analytics deployments, we believe that the deployments in practice will vary across the spectrum ranging from all the analytics in the cloud (for small deployments of cameras), all analytics in the private clusters (insufficient bandwidths to…”
BackgroundCompression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
Kim, Y., Park, E., Yoo, S., Choi, T., Lu, Y., & Shin, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06530 · Cited by 111 · cited 1×
“The machine learning community has proposed several optimizations such as replacing matrices with smaller factors [9], limiting the number of bits used to represent model parameters [11] and reducing the architectural complexity of models in systematic ways [10].”
MethodPanoptes: servicing multiple applications simultaneously using steerable cameras
Jain, S., Nguyen, V., Gruteser, M., & Bahl, P. (2017) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1145/3055031.3055085 · Cited by 26 · cited 1×
“Experiments with a live camera feeds have shown that in a typical traffic intersection setting our system captures up to 80% more events of interest in a wide scene, compared to a system which allows applications to control the cameras directly [6].”
BackgroundSelf-citation
Research works printed but not linked: 2
- jouppi, 2016, Google Supercharges Machine Learning Tasks with TPU Custom Chip
- ray, 2016, From Airplane Engines to Street Lights Transportation Is Becoming More Intelligent
Cited by
Items 201–300 of 495
Application Prospect of Edge Computing in Smart Distribution
Chen, J., Wei, J., Jiao, H., Guo, Y., Guoji, N., & Chen, W. (2018) · China International Conference on Electricity Distribution (CICED) · doi:10.1109/ciced.2018.8592104 · Cited by 14
“Researchers have discussed the application of edge computing in smart city, video surveillance, Internet performance optimization and other fields ([7-9]).”
BackgroundNeural Network-based Vehicle Image Classification for IoT Devices
Payvar, S., Khan, M., Stahl, R., Mueller-Gritschneder, D., & Boutellier, J. J. (2019) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips47522.2019.9020464 · Cited by 15
“Unfortunately, up to recently the computational requirements of CNNs have restricted their use to server or desktop class computers, although their deployment to edge devices could open up a variety of new applications [5].”
BackgroundInterstate-24 MOTION: Closing the Loop on Smart Mobility
Gloudemans, D., Barbour, W., Gloudemans, N., Neuendorf, M., Freeze, P. B., ElSaid, S., & Work, D. B. (2020) · IEEE Workshop on Design Automation for CPS and IoT (DESTION) · doi:10.1109/destion50928.2020.00014 · Cited by 12
“and when there are few objects in the frame [20], or by intelligently sharing on and off-edge compute resources as in [22].”
BackgroundHou, B., & Zhang, J. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533581 · Cited by 12
“As a consequence, both academia and industry have shown a tremendous amount of interest in surveillance video [2].”
BackgroundElasticEdge: An Intelligent Elastic Edge Framework for Live Video Analytics
Sun, H., Li, Q., Sha, K., & Yu, Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3187621 · Cited by 19
“In edge remote live video, Ananthanarayanan et al. [60] indicated that real-time video analysis is a killer application of edge computing.”
BackgroundGreenFog: A Framework for Sustainable Fog Computing
Toosi, A. N., Agarwal, C., Mashayekhy, L., Moghaddam, S. K., Mahmud, R., & Tari, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20984-0_38 · Cited by 12
Impact of Software Approximations on the Resiliency of a Video Summarization System
Venkatagiri, R., Swaminathan, K., Lin, C.-C., Wang, L., Buyuktosunoglu, A., Bose, P. K., & Adve, S. V. (2018) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn.2018.00067 · Cited by 12
“Real time edge computing [1], [2] is a rapidly growing field where real time data processing and other compute services are pushed away from centralized points to the logical extremes or edge of a network.”
BackgroundCost-effective Hardware Accelerator Recommendation for Edge Computing.
Zhou, X., Canady, R. E., Bao, S., & Gokhale, A. S. (2020) · Cited by 19
Enable Pipeline Processing of DNN Co-inference Tasks In the Mobile-Edge Cloud
Hu, S., Dong, C., & Wen, W. (2021) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs52626.2021.9449178 · Cited by 16
“Take mobile intelligent video analytic, one of the most valuable edge intelligence application [10], as an example.”
BackgroundOn Interactive Machine Learning and the Potential of Cognitive FeedbackPreprint
Michael, C. J., Acklin, D., & Scheuerman, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.10365 · Cited by 20
“Though many AML approaches to video analytics exist, they are typically tied to certain certain features of interest within some constrained context [Ananthanarayanan et al., 2017].”
BackgroundVisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras
Yan, Y., Zhang, S., Wang, X., Chen, N., Chen, Y., Liang, Y., Xiao, M., & Lu, S. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621148 · Cited by 14
“The surge in surveillance needs has led to the deployment of cameras across various settings like factories, campuses, and crossroads [1]–[3].”
BackgroundAdaStreamer: Machine-Centric High-Accuracy Multi-Video Analytics with Adaptive Neural Codecs
Zhu, A., Zhang, S., Cheng, K., Shi, X., Qian, Z., & Lu, S. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621074 · Cited by 11
“In spite of high potential in machine-centric coding, it is inadvisable to naively apply autoencoder in prevalent multi-video analytics [15]–[17].”
BackgroundJia, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3530242 · Cited by 19
“2) Medical Imaging: Deep learning models improve the accuracy of medical imaging jobs like finding tumors in MRI scans and analyzing disease in digital pathology slides, which helps doctors make decisions [42].”
Repurposing of TV boxes for a circular economy in smart cities applications
da Luz, G. P. C. P., Sato, G. M., Gonzalez, L. F. G., & Borin, J. F. (2025) · Scientific Reports · doi:10.1038/s41598-025-97379-4 · Cited by 14
“Real-time video analytics, in particular, is regarded as one of the killer applications for edge computing 11 , and when combined with artificial intelligence, it becomes a core component of the emerging field of edge intelligence 12 .”
Shepherd: Seamless Stream Processing on the Edge
Ramprasad, B., Mishra, P., Thiessen, M., Chen, H., Veith, A. D. S., Gabel, M., Balmau, O., Chow, A., & de Lara, E. (2022) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec54971.2022.00011 · Cited by 11
“This application uses video cameras and OpenCV [19] to track vehicles for smart traffic monitoring [20], [21].”
MethodFast and Accurate Object Detection Using Image Cropping/Resizing in Multi-View 4K Sports Videos
Xu, J., Lertniphonphan, K., & Tasaka, K. (2018) · ACM International Workshop on Multimedia Content Analysis in Sports (MMSports) · doi:10.1145/3265845.3265852 · Cited by 11
“However, it becomes even more challenging to process multi-view 4K videos with a limited computational resource [3].”
BackgroundDesign and Implementation of Video Analytics System Based on Edge Computing
Chen, Y., Xie, Y., Hu, Y., Liu, Y., & Shou, G. (2018) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc.2018.00035 · Cited by 13
Sensitivity-Aware Spatial Quality Adaptation for Live Video Analytics
Wang, W., Wang, B., Zhang, L., & Huang, H. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3180801 · Cited by 12
LEP-CNN: A Lightweight Edge Device Assisted Privacy-preserving CNN Inference Solution for IoTPreprint
Tian, Y., Yuan, J., Yu, S., & Hou, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04100 · Cited by 16
“Most current research [16], [17] on edge computing mainly emphasizes on fundamental issues such as resource allocation but assumes the edge devices are fully trusted.”
BackgroundEdge-Computing-Enabled Abnormal Activity Recognition for Visual Surveillance
Ali, M., Goyal, L., Sharma, C. M., & Kumar, S. (2024) · Electronics · doi:10.3390/electronics13020251 · Cited by 11
Inference serving with end-to-end latency SLOs over dynamic edge networks
Nigade, V., Bauszat, P., Bal, H. E., & Wang, L. (2024) · Real-Time Systems · doi:10.1007/s11241-024-09418-4 · Cited by 16
Spatial and Temporal Detection With Attention for Real-Time Video Analytics at Edges
Yan, Y., Zhang, S., Jin, Y., Cheng, F., Qian, Z., & Lu, S. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3361016 · Cited by 10
Crucio: End-to-End Coordinated Spatio-Temporal Redundancy Elimination for Fast Video Analytics
Zhu, A., Zhang, S., Shi, X., Cheng, K., Sun, H., & Lu, S. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621116 · Cited by 11
“Under these advancements, real-time video analytics (e.g., object detection), characterized by low delay and high accuracy, has emerged as an attractive research topic [2], [3].”
BackgroundMasykuroh, K., Hendrawan, H., Mulyana, E., & Krishna, F. (2025) · IEEE Access · doi:10.1109/access.2025.3561063 · Cited by 10
“The importance of video compression in video analytics applications—such as smart city surveillance, traffic management, and public safety monitoring—cannot be overstated [13], [69], [70].”
Camera-Based Edge Analytics for Drilling Optimization
Gooneratne, C. P., Magana-Mora, A., Affleck, M., Otalvora, W. B. C., Zhan, G. D., & Moellendick, T. E. (2020) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge50951.2020.00024 · Cited by 10
“Currently, deep-learning models for video processing have achieved outstanding results in different industries and applications, which enables the use of cameras as intelligent and autonomous sensing devices [13-19].”
BackgroundEdge-Assisted Adaptive Configuration for Serverless-Based Video Analytics
Wang, Z., Zhang, S., Cheng, J. L., Wu, Z., Cao, Z. Z., & Cui, Y. (2023) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs57875.2023.00058 · Cited by 14
“To fully unleash the potential of these installed cameras, video analytics applications have been developed to assist various public and private institutions (such as law enforcement agencies and retail businesses) to increase efficiency, decrease expenses, and improve security [3], [4], [5].”
BackgroundDecentralized Storage System for Edge Computing
Gheorghe, A.-G., Crecana, C.-C., Negru, C., Pop, F., & Dobre, C. (2019) · International Symposium on Parallel and Distributed Computing · doi:10.1109/ispdc.2019.00009 · Cited by 10
“In 2017 Microsoft [6] proposed an infrastructure and video analytics software stack, built on top of this architecture, called Rocket to handle the varied inputs from cameras, on edge nodes.”
MethodAdaptive client and communication optimizations in Federated Learning
Wu, J., Wang, Y., Shen, Z., & Liu, L. (2023) · Information Systems · doi:10.1016/j.is.2023.102226 · Cited by 11
Evaluating the Four-Way Performance Trade-Off for Data Stream Classification in Edge Computing
Lopes, J. F., Santana, E. J., da Costa, V. G. T., Zarpel�ão, B. B., & Barbon, S. (2020) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2020.2983921 · Cited by 13
“THE GROWING adoption of Internet of Things (IoT) solutions demands methods capable of extracting accurate information from raw sensor data [1], [2] and managing”
MethodVisualWorldDB: A DBMS for the Visual World.
Haynes, B. M., Daum, M., Mazumdar, A., Bałazińska, M., Cheung, A., & Ceze, L. (2020) · Conference on Innovative Data Systems Research · Cited by 19
OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos
Zhang, M., Zhu, Y., Shen, L., Wang, F., & Liu, J. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229105 · Cited by 11
“Thus, collaborating geo-distributed resources (e.g., device, edge, and cloud resources) is considered promising to achieve low latency and high accuracy [20].”
BackgroundInfluentialHong, Z., Lin, Q., & Hu, B. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3376579 · Cited by 19
“However, research on edge intelligence is still in its infancy stage, and a dedicated ability to handle new tasks and abstraction of perception is highly desired by interactive behavior-aware planning in the autonomous driving system [17].”
BackgroundRAVAS: Interference-Aware Model Selection and Resource Allocation for Live Edge Video Analytics
Rahmanian, A. A., Ali-Eldin, A., Tesfatsion, S. K., Skubic, B., Gustafsson, H., Shenoy, P. J., & Elmroth, E. (2023) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3583740.3628443 · Cited by 10
“DNNs models, such as Yolo [1], ResNet [2], and EfficientNet [3], are widely used for object detection and classification, with an increasing focus on edge deployment [4–6].”
MethodRailcar Detection, Identification and Tracking for Rail Yard Management
Chang, M., Zhao, G., Pandey, A. K., Pulver, A., & Tu, P. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190763 · Cited by 9
“With the raise of AI visual analytics, deep neural network (DNN) based vision systems can now achieve high technical readiness for industrial use in logistics and asset management [2].”
BackgroundComputation Offloading via Sinkhorn’s Matrix Scaling for Edge Services
Wang, L., Zhang, Y., & Chen, S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3042164 · Cited by 9
“VRs/ARs are computing-intensive latency-sensitive applications [43], [44].”
EdgeEye: A Data-Driven Approach for Optimal Deployment of Edge Video Analytics
Sun, H., Yu, Y., Sha, K., & Zhong, H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3166896 · Cited by 13
“Delay (i.e., Real–Time): Video analytics is mostly deployed in real-time applications, which require a low delay [34], i.e., response should be delivered to users before a deadline.”
BackgroundDynamic Offloading on a Hybrid Edge–Cloud Architecture for Multiobject Tracking
Lu, C.-H., & Lai, K.-T. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3165571 · Cited by 9
“To address the identified issue regarding real-time processing and quality maintenance, a hybrid computing architecture by combining edge and cloud computing has also been demonstrated to maintain a high quality of IoT services [10], [11].”
BackgroundEdge-Assisted Intelligent Video Compression for Live Aerial Streaming
Liu, Z., Wang, M., Chen, F., & Lu, Q. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2022.3172900 · Cited by 10
“Ananthanarayanan et al. [26] utilized public clouds, private clusters and edge devices to construct a low-cost, high-precision video real-time analysis system.”
BackgroundGnibga, W. E., Blavette, A., & Orgerie, A. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads60453.2023.00349 · Cited by 15
“The Cloud has become a bottleneck in terms of timeliness of the service, inducing a latency usually higher than 100ms which is not supportable in use cases like real-time video analytics [2].”
ThingsMigrate: Platform‐independent migration of stateful JavaScript Internet of Things applications
Jung, K., Gascon‐Samson, J., Goyal, S., Rezaiean‐Asel, A., & Pattabiraman, K. (2020) · Software Practice and Experience · doi:10.1002/spe.2936 · Cited by 9
Delay-Energy Joint Optimization for Task Offloading in Mobile Edge ComputingPreprint
Wang, Z., Liang, W., Huang, M., & Ma, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.10416 · Cited by 13
“It has attracted lots of attentions from both industries [2], [9] and academia [1], [6], [13].”
BackgroundMontpetit, M., & Crespi, N. (2021) · Wiley eBooks · doi:10.1002/9781119765554.ch10 · Cited by 10
AI-Driven QoS-Aware Scheduling for Serverless Video Analytics at the Edge
Giagkos, D., Tzenetopoulos, A., Masouros, D., Xydis, S., Catthoor, F., & Soudris, D. (2024) · Information · doi:10.3390/info15080480 · Cited by 8
“Video analytics are shifting from conventional “if/then” statements to more intelligent approaches, where machine learning techniques are applied to detect or classify objects in the frames of the video [44].”
BackgroundEdge-Assisted Adaptive Configuration for Serverless-Based Video Analytics
Wang, Z., Zhang, R., Zhang, S., Cheng, W., Wang, W., & Cui, Y. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2024.3523956 · Cited by 14
“To fully unleash the potential of these installed cameras, video analytics applications have been developed to assist various public and private institutions (such as law enforcement agencies and retail businesses) to increase efficiency, decrease expenses, and improve security [4], [5], [6], [7].”
Akram, M. S., Varma, B. S., Javed, A., Harkin, J., & Finlay, D. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103587 · Cited by 18
Coral-Pie: A Geo-Distributed Edge-compute Solution for Space-Time Vehicle Tracking
Xu, Z., Shah, H. S., & Ramachandran, U. (2020) · International Middleware Conference · doi:10.1145/3423211.3425686 · Cited by 9
“Often referred to as situation awareness applications [28], they span a variety of domains including safety ( e.g., surveillance [3, 35]), retail ( e.g., drone delivery [2, 34]), and transportation ( e.g., assisted/autonomous driving [21, 44]).”
BackgroundMonitoring Social Distancing With Single Image Depth Estimation
Mingozzi, A., Conti, A., Aleotti, F., Poggi, M., & Mattoccia, S. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3171769 · Cited by 13
“The underlining problem, consisting of monitoring people’s behavior, is not new in the literature [2] and is at the core of many business intelligence tasks for data analytics [3]–[8].”
BackgroundContainerized Computer Vision Applications on Edge Devices
Alqaisi, O. I., Tosun, A. Ş., & Korkmaz, T. (2023) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge60047.2023.00014 · Cited by 9
Efficient Compute at the Edge: Optimizing Energy Aware Data Structures for Emerging Edge Hardware
Khan, A. M., Umar, I., & Ha, P. H. (2018) · International Conference on High Performance Computing & Simulation (HPCS) · doi:10.1109/hpcs.2018.00060 · Cited by 8
“Such edge platforms can play an important role in performing data analytics and data intelligence at the edge [2].”
BackgroundBringing AI to the edge: a formal M&S specification to deploy effective IoT architectures
Cárdenas, R., Arroba, P., & Risco‐Martín, J. L. (2021) · Journal of Simulation · doi:10.1080/17477778.2020.1863755 · Cited by 13
TEEp: Supporting Secure Parallel Processing in ARM TrustZone
Li, Z., Li, W., Xia, Y., & Zang, B. (2020) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads51040.2020.00076 · Cited by 9
“On IoT equipments such as smart cameras, object detection algorithms are deployed to reduce the latency of processing and minimize data transfering [5], [6], which is also known as edge computing [7], [8].”
BackgroundA Review on Edge Intelligence based Collaborative Learning Approaches
Welagedara, L., Harischandra, J., & Jayawardene, N. (2021) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc51732.2021.9376119 · Cited by 10
“Furthermore, tech giants such as Microsoft, Intel and IBM have demonstrated advantages of the application of EI which has led to the developments of smart homes [5], live video analytics systems [6] and Industrial Internet of Things (IIoT) [7].”
BackgroundPerformance characterization of video analytics workloads in heterogeneous edge infrastructures
Rivas-Barragan, D., Guim, F., Polo, J., & Carrera, D. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6317 · Cited by 8
Burgoon, J. K., Wang, R. X., Chen, X., Ge, T. S., & Dorn, B. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.781487 · Cited by 12
PreActo: Efficient Cross-Camera Object Tracking System in Video Analytics Edge Computing
Nguyen, T.-T., Jang, S. Y., Kostadinov, B., & Lee, D. (2023) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom56429.2023.10099298 · Cited by 9
“Regarding the former, it can be largely divided into two categories: edge serverdriven approach [12], [13], where the server analyzes video feeds collected from all geo-distributed cameras; and edge device-driven approach [14], where powerful smart AI-enabled cameras filter out large portions of the videos before uplo…”
BackgroundMiddleware for Fog and Edge Computing: Design Issues
Pore, M., Chakati, V., Banerjee, A., & Gupta, S. (2019) · doi:10.1002/9781119525080.ch6 · Cited by 8
Candal‐Ventureira, D., González‐Castaño, F. J., Gil‐Castiñeira, F., & Fondo‐Ferreiro, P. (2023) · Software: Practice and Experience · doi:10.1002/spe.3161 · Cited by 7
Deka, R. K., Ghosh, A., Nanda, S., Barik, R. K., & Saikia, M. J. (2024) · Computers · doi:10.3390/computers13040105 · Cited by 7
Yu, J., Wu, H., Zhou, T., Cai, Z., Kuang, W., & Xia, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3532965 · Cited by 8
“There have been reports of thousands of surveillance devices being deployed in megacities, such as New York and Singapore [6].”
Ravindran, S., & Aghila, G. (2022) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2022.3177688 · Cited by 7
“Suppose if complex machine learning algorithm is required for analysis then it could be offloaded to the cloud [7].”
BackgroundInfluentialUsas: A Sustainable Continuous-Learning´ Framework for Edge Servers
Mishra, C. S., Sampson, J., Kandemir, M., Narayanan, V., & Das, C. R. (2024) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca57654.2024.00073 · Cited by 14
“As a result, “on-premise” edge servers [7], [8] have become prime choices for local inference and prediction [6], [39], [85], [86], necessitating the handling of both learning and inference tasks to meet application needs, including privacy preservation, reduced data communication, and…”
BackgroundEnhancing Support for Machine Learning and Edge Computing on an IoT Data Marketplace
Sajan, K. K., Ramachandran, G. S., & Krishnamachari, B. (2019) · International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (AIChallengeIoT) · doi:10.1145/3363347.3363364 · Cited by 7
“The edge devices can be used to train models or run inference or prediction close to the origin [2, 5, 8, 10].”
BackgroundLiu, Z., Qiao, B., & Fang, K. (2020) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-020-00204-8 · Cited by 8
Bellazi, K. M., Marino, R., Lanza-Gutiérrez, J. M., & Riesgo, T. (2020) · IEEE Access · doi:10.1109/access.2020.3042699 · Cited by 7
“Therefore, transmitting data through the network would increase energy consumption and would produce privacy problems [6]–[8].”
BackgroundSassu, A., Saenz-Cogollo, J. F., & Agelli, M. (2021) · Sensors · doi:10.3390/s21124045 · Cited by 10
“Given the large scale of the data generated by cameras and the real-time requirements often involved, an edge solution is the most practical approach as it conducts the video analytics close to (or on) the cameras [2].”
BackgroundReal-time camera analytics for enhancing traffic intersection safety
Ghasemi, M., Kleisarchaki, S., Calmant, T., Gürgen, L., Ghaderi, J., Kostić, Z., & Zussman, G. (2022) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3498361.3538669 · Cited by 7
“in traffic videos [7], and alerts following anomalous traffic patterns [2].”
BackgroundInfluentialTwenty-five years of real-time surveillance video analytics: a bibliometric review
Nallola, S. R., & Ayyasamy, V. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18325-6 · Cited by 7
“VOS viewer is used for its visualization capabilities, which allow researchers to create visualization networks that are both intuitive and informative [60, 82, 89].”
Alam, A., & Lee, Y.-K. (2020) · Sensors · doi:10.3390/s20123581 · Cited by 8
“A CVAS was proposed by Ananthanarayanan et al. [26,27] called Killer App to meet the real-time demands of video analytics and to address latency, bandwidth, and provisioning challenges.”
MethodOptimizing the Performance-Cost Tradeoff in Cross-Edge Analytics
Jia, L., Zhou, Z., & Jin, H. (2018) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld.2018.00118 · Cited by 7
“To satisfy the strict requirements of real-time and large-scale video analytics, a hybrid and cost-efficient architecture based on both cloud and edge is proposed [4].”
BackgroundMethodBi-objective Traffic Optimization in Geo-distributed Data Flows
Michailidou, A.-V., & Gounaris, A. (2019) · Big Data Research · doi:10.1016/j.bdr.2019.04.002 · Cited by 7
A Workload and Programming Ease Driven Perspective of Processing-in-MemoryPreprint
Ghose, S., Boroumand, A., Kim, J. S., Gómez-Luna, J., & Mutlu, O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12947 · Cited by 7
“As an example, an object classification algorithm in an augmented reality application typically trains on millions of example images and video clips, and performs classification on real-time high-definition video streams [7, 9].”
BackgroundEdge Computing for Real-Time Near-Crash Detection for Smart Transportation ApplicationsPreprint
Ke, R., Cui, Z., Chen, Y., Zhu, M., Yang, H., & Wang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.00549 · Cited by 16
“Under the context of edge computing, real-time video analytics is regarded as the Killer App [19], given the restricted computing resources on edge devices and the property of video data being in large volume as enormous 3D matrices.”
Cavigelli, L., & Benini, L. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2903421 · Cited by 32
“Furthermore, collecting large amounts of data at a central site raises privacy concerns and the required high-bandwidth communication channel causes additional reliability problems and potentially prohibitive cost of deployment and during operation [15].”
BackgroundEdge Computing Resource Management for Cross-Camera Video Analytics: Workload and Model Adaptation
Chen, H.-T., Chiang, Y., & Wei, H. (2024) · IEEE Access · doi:10.1109/access.2024.3355815 · Cited by 7
“By processing the application closer to the data source, edge/fog computing reduces the need for data transmission, minimizes latency, and improves overall system performance [1], [5].”
BackgroundA Design Pattern of IAPVS Platform Based on Distributed Edge Computing
Cheng, X., Xu, M., Yan, X., Yang, Y., Xu, Y., & Ruan, Y. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2732/1/012001 · Cited by 6
Online Management for Edge-Cloud Collaborative Continuous Learning: A Two-Timescale Approach
Lin, S., Zhang, X., Li, Y., Joe‐Wong, C., Duan, J., Yu, D., Wu, Y. F., & Chen, X. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3451715 · Cited by 9
“N OWADAYS, a large number of emerging applications, such as human activity recognition (HAR) and video analytics [2], are powered by deep learning (DL) approaches [3].”
BackgroundrunData: Re-distributing Data via Piggybacking for Geo-distributed Data Analytics over Edges
Jin, Y., Qian, Z., Guo, S., Zhang, S., Jiao, L., & Lu, S. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3086274 · Cited by 9
“Servers Servers”
Real-Time Bird’s Eye Surround View System: An Embedded Perspective
Al-Hami, M. A., Casas, R. A., El-Salhi, S., Awwad, S., & Hussein, F. (2021) · Applied Artificial Intelligence · doi:10.1080/08839514.2021.1935587 · Cited by 6
Gao, Y., & Xu, D. (2021) · Mobile Information Systems · doi:10.1155/2021/3019009 · Cited by 6
Decentralized modular architecture for live video analytics at the edge
Rachuri, S. P., Bronzino, F., & Jain, S. (2021) · doi:10.1145/3477083.3480153 · Cited by 6
“In recent years, video analytics have become a key to supporting surveillance, security, traffic control, and multimedia use cases with processing at the edge of the network [1].”
BackgroundA Queueing Model for Video Analytics Applications of Smart Cities
Sharifi, M., Abhari, A., & Taghipour, S. (2021) · Winter Simulation Conference · doi:10.1109/wsc52266.2021.9715373 · Cited by 6
“…smart cities that include a mix of processing powers, such as CPU and GPU-based edge servers and public clouds, infrastructure networks may not provide the required latency when the number of cameras increases to hundreds of thousands to control traffic in big cities (Ananthanarayanan et al. 2017).”
BackgroundVPPlus: Exploring the Potentials of Video Processing for Live Video Analytics at the Edge
Guo, J., Xia, S., & Peng, C. (2022) · International Workshop on Quality of Service · doi:10.1109/iwqos54832.2022.9812896 · Cited by 7
“To this end, edge-assisted video analytics becomes one dominant solution paradigm by offloading compute-intensive analytical tasks to the edge [1].”
BackgroundMethodThe AtLarge Vision on the Design of Distributed Systems and Ecosystems
Iosup, A., Versluis, L., Trivedi, A., van Eyk, E., Toader, L., van Beek, V., Frascaria, G., Musaafir, A., & Talluri, S. (2019) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2019.00175 · Cited by 6
“Datacenters appear in different scales and designs, from multi-cluster deployments like Amazon EC2 and Microsoft Azure to cloud-edge [92] micro-datacenters used for video trans-coding and streaming [93].”
BackgroundGušev, M. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824054-0.00020-4 · Cited by 6
Algorithm and Architecture Design of FAST-C Image Corner Detection Engine
Lee, Y.-H., Chen, T.-C., Liang, H.-C., & Liao, J.-X. (2020) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2020.3031294 · Cited by 6
ViEdge: Video Analytics on Distributed Edge
Hou, X., Guan, Y., & Han, T. (2025) · ACM Transactions on Internet of Things · doi:10.1145/3742794 · Cited by 5
“By allocating tasks among different tiers, these studies reach low latency [1, 18, 48], reduced bandwidth costs [20, 21, 39], improved energy efficiency [46], and privacy [2].”
Real-time Multi-Camera Analytics for Traffic Information Extraction and Visualization
Ghasemi, M., Kleisarchaki, S., Calmant, T., Jiawei, L., Ojha, S. H. K. G. P., Kostić, Z., Gürgen, L., Zussman, G., & Ghaderi, J. (2023) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops56833.2023.10150224 · Cited by 5
“There have been several efforts to use video analytics for traffic surveillance in dense urban areas, including automated detection of helmets on motorcyclists [7], detection of accidents/collisions in traffic videos [8], and alerts following anomalous traffic patterns [9].”
BackgroundChandrasekaran, S., Athinarayanan, S., Masthan, M., Kakkar, A., Bhatnagar, P., & Samad, A. (2024) · Advances in computer and electrical engineering book series · doi:10.4018/979-8-3693-3739-4.ch001 · Cited by 7
Middleware para Aplicações Distribuídas de Vídeo com Suporte à Computação na Borda na Indústria 4.0
Neto, O. D. A. R., Chaves, R. C., do Nascimento, A. P., & Gomes, R. D. (2024) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia.2024.242927 · Cited by 6
Liu, M., Geißler, D., Bian, S., Zhou, B., & Lukowicz, P. (2025) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops65533.2025.00083 · Cited by 9
“However, mainstream ANNs powering such intelligent mobile systems typically assume a uniform time granularity of input samples [11]–[13], an assumption which is often over-optimistic when developing on GPU-based infrastructure with pre-processed datasets that do not reflect the reality of mobile…”
Twinned power: formations of cloud-edge control
Munn, L. (2020) · Information Communication & Society · doi:10.1080/1369118x.2020.1808043 · Cited by 6
“…science articles attest (Bailas et al., 2018; Nastic et al., 2017; Ning et al., 2019), some of the greatest promises of edge computing swirl around its real-time capabilities, with one paper describing real-time video analysis as the edge ’ s ‘ killer application ’ (Ananthanarayanan et al., 2017).”
BackgroundEdge artificial intelligence camera network: an efficient object detection and tracking framework
Chen, Y., Wang, C., & Lou, S. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.3.033030 · Cited by 6
Energy-Efficient Edge Caching and Task Deployment Algorithm Enabled by Deep Q-Learning for MEC
Ma, L., Wang, P., Du, C., & Li, Y. (2022) · Electronics · doi:10.3390/electronics11244121 · Cited by 5
Evaluating Kubernetes at the Edge for Fault Tolerant Multi-Camera Computer Vision Applications
Heckmann, O., & Ravindran, A. (2023) · doi:10.1109/ccgridw59191.2023.00054 · Cited by 5
“Research partially supported by the National Science Foundation (Award 1831795) offers a solution to the above challenges [4].”
BackgroundDecoupled Access-Execute Enabled DVFS for TinyML Deployments on STM32 Microcontrollers
Alvanaki, E. L., Katsaragakis, M., Masouros, D., Xydis, S., & Soudris, D. (2024) · Design, Automation, and Test in Europe · doi:10.23919/date58400.2024.10546540 · Cited by 10
“Furthermore, the increasing demand for edge-centric digital signal processing applications, such as video analytics [2], mobile visual tasks [3] and others has established Convolutional Neural Networks (CNNs) as the go-to technology for efficiently handling these tasks at the edge.”
BackgroundVideoJam: Self-Balancing Architecture for Live Video Analytics
Faye, Y., Faticanti, F., Jain, S., & Bronzino, F. (2024) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec62691.2024.00020 · Cited by 6
“However, the increasing amounts of video data produced by available cameras has forced the community to move away from centralized cloud-based architectures [9], [4].”
Mystique: User-Level Adaptation for Real-Time Video Analytics in Edge Networks via Meta-RL
Shi, X., Zhang, S., Liu, M., Meng, L., Liu, W., Gu, Y., Liu, K., Cheng, H., Song, Y., Lei, T., et al. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3514088 · Cited by 8
“D EEP neural network (DNN)-based real-time video analytics techniques have enabled a wide range of vital applications, such as augmented reality (AR), aerial analysis, and traffic management [1], [2], [3], [4].”
Adaptive Offloading and Enhancement for Low-Light Video Analytics on Mobile Devices
He, Y., Yang, P., Qin, T., Hou, J., & Zhang, N. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901311 · Cited by 5
“The advancement of computer vision technology has become indispensable across various domains of Internet of Things (IoT) applications [1], [2].”
MEFS: Mobile Edge File System for Edge-Assisted Mobile Apps
Scotece, D., Paiker, N. R., Foschini, L., Bellavista, P., Ding, X., & Borcea, C. (2019) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom.2019.8792987 · Cited by 5
“According to Ananthanarayanan et al [38], large-scale video analytics may well represent the killer application for edge computing.”
BackgroundA Scalable Testbed for Task Offloading and Deployment of Heterogeneous Edge Computing
Diao, B., Yang, K., Mei, Y., Wang, Q., Li, C., An, Z., & Xu, Y. (2019) · International Conference on Ubiquitous Computing and Communications (IUCC) · doi:10.1109/iucc/dsci/smartcns.2019.00123 · Cited by 6
“Besides CPUs, edge networks add dissimilar coprocessors to improve system performance or energy efficiency, including low-power GPUs [15], FPGAs [16], ASIC [17], and etc.”
Background
Metadata
- Authors
- Ananthanarayanan, G., Bahl, P., Bodik, P., Chintalapudi, K., Philipose, M., Ravindranath, L., & Sinha, S.
- Affiliations
- Microsoft (United States) (US)
- Venue
- Computer
- Published
- 2017
- Volume
- 50
- Issue
- 10
- Pages
- 58-67
- ISSN
- 0018-9162 (ISSN-L)
- OpenAlex
- W2678047256
- Cited by
- 496
- References
- 11
- Citations by year
- 2026: 9 · 2025: 43 · 2024: 51 · 2023: 53 · 2022: 78 · 2021: 77 · 2020: 91 · 2019: 56 · 2018: 37 · 2017: 1
- FWCI
- 33.70
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Computer (publishedVersion)
- 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 Networks and Communications › Caching and Content Delivery
- Keywords
- real-time video processing, edge computing, edge-cloud computing, distributed architecture, video cameras
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.