{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T21:32:41Z","timestamp":1776547961229,"version":"3.51.2"},"reference-count":53,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2020,12,31]],"date-time":"2020-12-31T00:00:00Z","timestamp":1609372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2015\/24144-7"],"award-info":[{"award-number":["2015\/24144-7"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["06747\/2018-9"],"award-info":[{"award-number":["06747\/2018-9"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In smart city scenarios, the huge proliferation of monitoring cameras scattered in public spaces has posed many challenges to network and processing infrastructure. A few dozen cameras are enough to saturate the city\u2019s backbone. In addition, most smart city applications require a real-time response from the system in charge of processing such large-scale video streams. Finding a missing person using facial recognition technology is one of these applications that require immediate action on the place where that person is. In this paper, we tackle these challenges presenting a distributed system for video analytics designed to leverage edge computing capabilities. Our approach encompasses architecture, methods, and algorithms for: (i) dividing the burdensome processing of large-scale video streams into various machine learning tasks; and (ii) deploying these tasks as a workflow of data processing in edge devices equipped with hardware accelerators for neural networks. We also propose the reuse of nodes running tasks shared by multiple applications, e.g., facial recognition, thus improving the system\u2019s processing throughput. Simulations showed that, with our algorithm to distribute the workload, the time to process a workflow is about 33% faster than a naive approach.<\/jats:p>","DOI":"10.3390\/info12010014","type":"journal-article","created":{"date-parts":[[2020,12,31]],"date-time":"2020-12-31T10:10:37Z","timestamp":1609409437000},"page":"14","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Leveraging Edge Intelligence for Video Analytics in Smart City Applications"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1531-1488","authenticated-orcid":false,"given":"Aluizio","family":"Rocha Neto","sequence":"first","affiliation":[{"name":"Department of Informatics and Applied Mathematics, Federal University of RN (UFRN), Natal 59078-970, Brazil"},{"name":"Digital Metropolis Institute, Federal University of RN (UFRN), Natal 58078-970, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3353-053X","authenticated-orcid":false,"given":"Thiago P.","family":"Silva","sequence":"additional","affiliation":[{"name":"Department of Informatics and Applied Mathematics, Federal University of RN (UFRN), Natal 59078-970, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3558-1450","authenticated-orcid":false,"given":"Thais","family":"Batista","sequence":"additional","affiliation":[{"name":"Department of Informatics and Applied Mathematics, Federal University of RN (UFRN), Natal 59078-970, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5334-8279","authenticated-orcid":false,"given":"Fl\u00e1via C.","family":"Delicato","sequence":"additional","affiliation":[{"name":"Computer Science Department, Fluminense Federal University (UFF), Niteroi 24220-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulo F.","family":"Pires","sequence":"additional","affiliation":[{"name":"Computer Science Department, Fluminense Federal University (UFF), Niteroi 24220-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frederico","family":"Lopes","sequence":"additional","affiliation":[{"name":"Digital Metropolis Institute, Federal University of RN (UFRN), Natal 58078-970, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,31]]},"reference":[{"key":"ref_1","unstructured":"Ashton, K. (2020, June 24). That \u2018Internet of Things\u2019 Thing. Available online: https:\/\/www.rfidjournal.com\/articles\/view?4986."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.adhoc.2015.04.006","article-title":"Internet of multimedia things: Vision and challenges","volume":"33","author":"Alvi","year":"2015","journal-title":"Ad Hoc Netw."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"8202","DOI":"10.1109\/ACCESS.2020.2964280","article-title":"Multimedia Internet of Things: A Comprehensive Survey","volume":"8","author":"Nauman","year":"2020","journal-title":"IEEE Access"},{"key":"ref_4","unstructured":"Barnett, T., Jain, S., Andra, U., and Khurana, T. (2020, December 14). Cisco Visual Networking Index (VNI) Complete Forecast Update, 2017\u20132022. Cisco Systems. Available online: https:\/\/bit.ly\/385BAhJ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1049\/ip-vis:20041147","article-title":"Intelligent distributed surveillance systems: A review","volume":"152","author":"Valera","year":"2005","journal-title":"IEE Proc. Vision Image Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.cviu.2015.10.014","article-title":"A scalable and flexible framework for smart video surveillance","volume":"144","author":"Nazare","year":"2016","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_7","unstructured":"Gualtieri, M., and Curran, R. (2020, December 14). The Forrester WaveTM: Big Data Streaming Analytics, Q1 2016. Available online: https:\/\/bit.ly\/3oR3ftA."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s13634-016-0355-x","article-title":"A survey of machine learning for big data processing","volume":"2016","author":"Qiu","year":"2016","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1109\/COMST.2018.2844341","article-title":"Deep Learning for IoT Big Data and Streaming Analytics: A Survey","volume":"20","author":"Mohammadi","year":"2018","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1145\/2831347.2831354","article-title":"Edge-centric Computing: Vision and Challenges","volume":"45","author":"Montresor","year":"2015","journal-title":"SIGCOMM Comput. Commun. Rev."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"9-es","DOI":"10.1145\/1267070.1267073","article-title":"Information Fusion for Wireless Sensor Networks: Methods, Models, and Classifications","volume":"39","author":"Nakamura","year":"2007","journal-title":"ACM Comput. Surv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1109\/JIOT.2015.2411227","article-title":"A Practical Evaluation of Information Processing and Abstraction Techniques for the Internet of Things","volume":"2","author":"Ganz","year":"2015","journal-title":"IEEE Internet Things J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/MCI.2019.2937613","article-title":"Distributing Intelligence to the Edge and Beyond [Research Frontier]","volume":"14","author":"Ramos","year":"2019","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_14","first-page":"89","article-title":"An Architecture for Distributed Video Stream Processing in IoMT Systems","volume":"6","author":"Silva","year":"2020","journal-title":"Open J. Internet Things (OJIOT)"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1007\/s42979-020-00359-w","article-title":"A Systematic Review on Software Architectures for IoT Systems and Future Direction to the Adoption of Microservices Architecture","volume":"1","author":"Razzaq","year":"2020","journal-title":"SN Comput. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Rocha Neto, A., Delicato, F.C., Batista, T.V., and Pires, P.F. (2020, October 16). Distributed Machine Learning for IoT Applications in the Fog. Available online: https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/9781119551713.ch12.","DOI":"10.1002\/9781119551713.ch12"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1016\/j.compeleceng.2017.11.011","article-title":"Video surveillance systems-current status and future trends","volume":"70","author":"Tsakanikas","year":"2018","journal-title":"Comput. Electr. Eng."},{"key":"ref_18","unstructured":"Forret, P. (2020, November 06). Toolstud.io. Available online: https:\/\/toolstud.io\/video\/bitrate.php."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Garofalakis, M.N., Gehrke, J., and Rastogi, R. (2016). Data Stream Management\u2014Processing High-Speed Data Streams, Springer. Data-Centric Systems and Applications.","DOI":"10.1007\/978-3-540-28608-0"},{"key":"ref_20","unstructured":"Rosebrock, A. (2020, December 14). Deep Learning for Computer Vision with Python, 1.3.0 ed. Available online: https:\/\/www.pyimagesearch.com\/static\/cv_dl_resource_guide.pdf."},{"key":"ref_21","unstructured":"Etzion, O., and Niblett, P. (2010). Event Processing in Action, Manning Publications Company."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Dautov, R., Distefano, S., Bruneo, D., Longo, F., Merlino, G., and Puliafito, A. (2017, January 21\u201323). Pushing Intelligence to the Edge with a Stream Processing Architecture. Proceedings of the 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Exeter, UK.","DOI":"10.1109\/iThings-GreenCom-CPSCom-SmartData.2017.121"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_24","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: https:\/\/mitpress.mit.edu\/books\/deep-learning."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ali, M., Anjum, A., Yaseen, M.U., Zamani, A.R., Balouek-Thomert, D., Rana, O.F., and Parashar, M. (2018, January 1\u20133). Edge Enhanced Deep Learning System for Large-Scale Video Stream Analytics. Proceedings of the 2018 IEEE 2nd International Conference on Fog and Edge Computing (ICFEC), Washington, DC, USA.","DOI":"10.1109\/CFEC.2018.8358733"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ledakis, I., Bouras, T., Kioumourtzis, G., and Skitsas, M. (2018, January 23\u201325). Adaptive Edge and Fog Computing Paradigm for Wide Area Video and Audio Surveillance. Proceedings of the 2018 9th International Conference on Information, Intelligence, Systems and Applications (IISA), Zakynthos, Greece.","DOI":"10.1109\/IISA.2018.8633626"},{"key":"ref_27","unstructured":"NVIDIA (2020, December 14). NVIDIA Metropolis. Available online: https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/intelligent-video-analytics-platform."},{"key":"ref_28","unstructured":"Google (2019, December 03). Coral. Available online: https:\/\/coral.ai."},{"key":"ref_29","unstructured":"Movidius (2020, April 14). Applications for the Intel NCS 2 (or Original NCS) with OpenVINO Toolkit. Available online: https:\/\/github.com\/movidius\/ncappzoo\/blob\/master\/apps\/README.md."},{"key":"ref_30","unstructured":"NVIDIA (2020, February 10). TensorFlow\/TensorRT Models on Jetson. Available online: https:\/\/github.com\/NVIDIA-AI-IOT\/tf_trt_models."},{"key":"ref_31","unstructured":"Google (2019, October 13). Models Built for the Edge TPU. Available online: https:\/\/coral.ai\/models."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Mittal, G., Yagnik, K.B., Garg, M., and Krishnan, N.C. (2016, January 12\u201316). SpotGarbage: Smartphone App to Detect Garbage Using Deep Learning. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp \u201916, Heidelberg, Germany.","DOI":"10.1145\/2971648.2971731"},{"key":"ref_33","first-page":"1","article-title":"Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory","volume":"10","author":"Ma","year":"2015","journal-title":"PLoS ONE"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tian, Y., and Pan, L. (2015, January 19\u201321). Predicting Short-Term Traffic Flow by Long Short-Term Memory Recurrent Neural Network. Proceedings of the 2015 IEEE International Conference on Smart City\/SocialCom\/SustainCom (SmartCity), Chengdu, China.","DOI":"10.1109\/SmartCity.2015.63"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ling, X., Sheng, J., Baiocchi, O., Liu, X., and Tolentino, M.E. (2017, January 6\u20139). Identifying parking spaces detecting occupancy using vision-based IoT devices. Proceedings of the 2017 Global Internet of Things Summit (GIoTS), Geneva, Switzerland.","DOI":"10.1109\/GIOTS.2017.8016227"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.eswa.2016.10.055","article-title":"Deep learning for decentralized parking lot occupancy detection","volume":"72","author":"Amato","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Rocha Neto, A., Soares, B., Barbalho, F., Santos, L., Batista, T., Delicato, F.C., and Pires, P.F. (2018). Classifying Smart IoT Devices for Running Machine Learning Algorithms. 45o\u0320 Semin\u00e1rio Integrado de Software e Hardware 2018 (SEMISH 2018), SBC.","DOI":"10.5753\/semish.2018.3429"},{"key":"ref_38","unstructured":"de Assun\u00e7 ao, M.D., Veith, A.D.S., and Buyya, R. (2019, July 15). Resource Elasticity for Distributed Data Stream Processing: A Survey and Future Directions. Available online: https:\/\/arxiv.org\/abs\/1709.01363."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"R\u00f6ger, H., and Mayer, R. (2019). A Comprehensive Survey on Parallelization and Elasticity in Stream Processing. ACM Comput. Surv., 52.","DOI":"10.1145\/3303849"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"91745","DOI":"10.1109\/ACCESS.2019.2927895","article-title":"YAFS: A Simulator for IoT Scenarios in Fog Computing","volume":"7","author":"Lera","year":"2019","journal-title":"IEEE Access"},{"key":"ref_41","unstructured":"University of Essex (2019, May 05). Face Recognition Data. Available online: https:\/\/cswww.essex.ac.uk\/mv\/allfaces\/."},{"key":"ref_42","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017, January 21\u201326). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Proceedings of the Computer Vision and Pattern Recognition (cs.CV), Honolulu, HI, USA."},{"key":"ref_43","unstructured":"Schroff, F., Kalenichenko, D., and Philbin, J. (2019, May 26). FaceNet: A Unified Embedding for Face Recognition and Clustering. Available online: https:\/\/arxiv.org\/abs\/1503.03832."},{"key":"ref_44","unstructured":"Geitgey, A. (2019, October 19). Face Recognition Library. Available online: https:\/\/github.com\/ageitgey\/face_recognition."},{"key":"ref_45","unstructured":"OpenCV.org (2019, April 17). Open Source Computer Vision Library. Available online: https:\/\/opencv.org\/."},{"key":"ref_46","unstructured":"Bass, J. (2019, September 04). imageZMQ: Transporting OpenCV Images. Available online: https:\/\/github.com\/jeffbass\/imagezmq."},{"key":"ref_47","unstructured":"ZeroMQ.org (2019, September 04). ZeroMQ\u2014An Open-Source Universal Messaging Library. Available online: https:\/\/zeromq.org\/."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/MC.2017.3641638","article-title":"Real-Time Video Analytics: The Killer App for Edge Computing","volume":"50","author":"Ananthanarayanan","year":"2017","journal-title":"Computer"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"James, A., Sirakoulis, G.C., and Roy, K. (2019, January 27\u201329). Smart cameras everywhere: AI vision on edge with emerging memories. Proceedings of the 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS), Genoa, Italy.","DOI":"10.1109\/ICECS46596.2019.8965029"},{"key":"ref_50","unstructured":"Apache.org (2018, October 06). Apache NiFi\u2014An Easy to Use, Powerful, And Reliable System To Process and Distribute Data. Available online: https:\/\/nifi.apache.org\/."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Ben Sada, A., Bouras, M.A., Ma, J., Runhe, H., and Ning, H. (2019, January 5\u20138). A Distributed Video Analytics Architecture Based on Edge-Computing and Federated Learning. Proceedings of the 2019 IEEE International Conference Dependable, Autonomic and Secure Computing, Fukuoka, Japan.","DOI":"10.1109\/DASC\/PiCom\/CBDCom\/CyberSciTech.2019.00047"},{"key":"ref_52","first-page":"1","article-title":"A Smart, Efficient, and Reliable Parking Surveillance System With Edge Artificial Intelligence on IoT Devices","volume":"90","author":"Ke","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_53","unstructured":"Yau, S. (2019, August 07). Battle of Edge AI\u2014 Nvidia vs. Google vs. Intel. Available online: https:\/\/medium.com\/p\/8a3b87243028."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/12\/1\/14\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:48:30Z","timestamp":1760179710000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/12\/1\/14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,31]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["info12010014"],"URL":"https:\/\/doi.org\/10.3390\/info12010014","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,31]]}}}