{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:16:23Z","timestamp":1777983383849,"version":"3.51.4"},"reference-count":49,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T00:00:00Z","timestamp":1600041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)\/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent transportation systems, to name a few. However, the real-time processing of collected data on edge in the context of the Internet-of-Drones remains an open challenge because UAVs have limited energy capabilities, while computer vision techniquesconsume excessive energy and require abundant resources. This fact is even more critical when deep learning algorithms, such as convolutional neural networks (CNNs), are used for classification and detection. In this paper, we first propose a system architecture of computation offloading for Internet-connected drones. Then, we conduct a comprehensive experimental study to evaluate the performance in terms of energy, bandwidth, and delay of the cloud computation offloading approach versus the edge computing approach of deep learning applications in the context of UAVs. In particular, we investigate the tradeoff between the communication cost and the computation of the two candidate approaches experimentally. The main results demonstrate that the computation offloading approach allows us to provide much higher throughput (i.e., frames per second) as compared to the edge computing approach, despite the larger communication delays.<\/jats:p>","DOI":"10.3390\/s20185240","type":"journal-article","created":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T09:04:53Z","timestamp":1600074293000},"page":"5240","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":70,"title":["DeepBrain: Experimental Evaluation of Cloud-Based Computation Offloading and Edge Computing in the Internet-of-Drones for Deep Learning Applications"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3787-7423","authenticated-orcid":false,"given":"Anis","family":"Koubaa","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of Computer &amp; Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia"},{"name":"CISTER Research Centre, ISEP, Polytechnic Institute of Porto, 4200-465 Porto, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0795-132X","authenticated-orcid":false,"given":"Adel","family":"Ammar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer &amp; Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahmoud","family":"Alahdab","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer &amp; Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anas","family":"Kanhouch","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer &amp; Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7869-6373","authenticated-orcid":false,"given":"Ahmad Taher","family":"Azar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer &amp; Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia"},{"name":"Faculty of Computers and Artificial Intelligence, Benha University, Banha 13511, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"104932","DOI":"10.1016\/j.compag.2019.104932","article-title":"Semi-supervised learning with convolutional neural networks for UAV images automatic recognition","volume":"164","author":"Amorim","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_2","unstructured":"(2019, December 21). The Global Counter-UAS Market to Reach to $1.97 Billion by 2024. Available online: shorturl.at\/bkmvE."},{"key":"ref_3","unstructured":"(2019, December 21). Deep Learning Market Global Forecast to 2023. Available online: shorturl.at\/AGIXZ."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wani, M.A., Bhat, F.A., Afzal, S., and Khan, A.I. (2020). Advances in Deep Learning. Studies in Big Data, Springer.","DOI":"10.1007\/978-981-13-6794-6"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Benjdira, B., Khursheed, T., Koubaa, A., Ammar, A., and Ouni, K. (2019, January 5\u20137). Car detection using unmanned aerial vehicles: Comparison between faster R-CNN and YOLOv3. Proceedings of the 2019 1st International Conference on Unmanned Vehicle Systems-Oman (UVS), Muscat, Oman.","DOI":"10.1109\/UVS.2019.8658300"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ammar, A., Koubaa, A., Ahmed, M., and Saad, A. (2019). Aerial images processing for car detection using convolutional neural networks: Comparison between faster R-CNN and YoloV3. arXiv.","DOI":"10.20944\/preprints201910.0195.v1"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Benjdira, B., Bazi, Y., Koubaa, A., and Ouni, K. (2019). Unsupervised domain adaptation using generative adversarial networks for semantic segmentation of aerial images. Remote Sens., 11.","DOI":"10.3390\/rs11111369"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ammour, N., Alhichri, H., Bazi, Y., Benjdira, B., Alajlan, N., and Zuair, M. (2017). Deep learning approach for car detection in UAV imagery. Remote Sens., 9.","DOI":"10.3390\/rs9040312"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"98061","DOI":"10.1109\/ACCESS.2019.2927866","article-title":"Multi-task cost-sensitive-convolutional neural network for car detection","volume":"7","author":"Xi","year":"2019","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kyrkou, C., and Theocharides, T. (2019). Deep-Learning-based aerial image classification for emergency response applications using Unmanned Aerial Vehicles. arXiv.","DOI":"10.1109\/CVPRW.2019.00077"},{"key":"ref_11","unstructured":"KUFFNER, J. (2010, January 6\u20138). Cloud-enabled humanoid robots. Proceedings of the 2010 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids), Nashville, TN, USA."},{"key":"ref_12","unstructured":"Koubaa, A. (2019). Service-oriented software architecture for cloud robotics. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, B., Min, H., Heo, J., and Jung, J. (2018). Dynamic computation offloading scheme for drone-based surveillance systems. Sensors, 18.","DOI":"10.3390\/s18092982"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4027","DOI":"10.1109\/TVT.2019.2901761","article-title":"QoS-aware cooperative computation offloading for robot swarms in cloud robotics","volume":"68","author":"Hong","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4964","DOI":"10.1109\/TVT.2019.2902318","article-title":"A game theory based efficient computation offloading in an UAV network","volume":"68","author":"Messous","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1109\/JSAC.2019.2906789","article-title":"Space\/aerial-assisted computing offloading for IoT applications: A learning-based approach","volume":"37","author":"Cheng","year":"2019","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Van Le, D., and Tham, C. (2018, January 15\u201319). A deep reinforcement learning based offloading scheme in ad-hoc mobile clouds. Proceedings of the IEEE INFOCOM 2018\u2014IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Honolulu, HI, USA.","DOI":"10.1109\/INFCOMW.2018.8406881"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rahman, A., Jin, J., Cricenti, A., Rahman, A., and Panda, M. (2017, January 4\u20138). Motion and connectivity aware offloading in cloud robotics via genetic algorithm. Proceedings of the GLOBECOM 2017\u20142017 IEEE Global Communications Conference, Singapore.","DOI":"10.1109\/GLOCOM.2017.8255040"},{"key":"ref_19","unstructured":"(2020, February 08). The DeepBrain Project Demo Page. Available online: https:\/\/www.riotu-lab.org\/deepbrain.php."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1145\/3093337.3037698","article-title":"Neurosurgeon: Collaborative intelligence between the cloud and mobile edge","volume":"45","author":"Kang","year":"2017","journal-title":"SIGARCH Comput. Archit. News"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wamser, F., Loh, F., Seufert, M., Tran-Gia, P., Bruschi, R., and Lago, P. (2017, January 8\u201312). Dynamic cloud service placement for live video streaming with a remote-controlled drone. Proceedings of the 2017 IFIP\/IEEE Symposium on Integrated Network and Service Management (IM), Lisbon, Portugal.","DOI":"10.23919\/INM.2017.7987400"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10190","DOI":"10.1109\/TVT.2018.2867191","article-title":"Mobility-aware edge caching and computing in vehicle networks: A deep reinforcement learning","volume":"67","author":"Tan","year":"2018","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1109\/TII.2018.2883991","article-title":"Traffic and computation co-offloading with reinforcement learning in fog computing for industrial applications","volume":"15","author":"Wang","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chaari, R., Cheikhrouhou, O., Koubaa, A., Youssef, H., and Hmam, H. (2019, January 24\u201328). Towards a distributed computation offloading architecture for cloud robotics. Proceedings of the 2019 15th International Wireless Communications Mobile Computing Conference (IWCMC), Tangier, Morocco.","DOI":"10.1109\/IWCMC.2019.8766504"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"67734","DOI":"10.1109\/ACCESS.2019.2918585","article-title":"A heuristic offloading method for deep learning edge services in 5G networks","volume":"7","author":"Xu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4192","DOI":"10.1109\/TVT.2019.2894437","article-title":"Knowledge-driven service offloading decision for vehicular edge computing: A deep reinforcement learning approach","volume":"68","author":"Qi","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.jpdc.2019.01.003","article-title":"An efficient method of computation offloading in an edge cloud platform","volume":"127","author":"Alelaiwi","year":"2019","journal-title":"J. Parallel Distrib. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.future.2018.07.050","article-title":"Autonomic computation offloading in mobile edge for IoT applications","volume":"90","author":"Alam","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/MVT.2018.2882873","article-title":"Mobile edge computing-enabled 5g vehicular networks: Toward the integration of communication and computing","volume":"14","author":"Ning","year":"2019","journal-title":"IEEE Veh. Technol. Mag."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1109\/TII.2019.2937079","article-title":"When deep reinforcement learning meets 5G-enabled vehicular networks: A distributed offloading framework for traffic big data","volume":"16","author":"Ning","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, S., Luo, S., Wang, Q., Cao, B., and Li, X. (2020). An intelligent task offloading algorithm (iTOA) for UAV edge computing network. Digit. Commun. Netw., in press.","DOI":"10.1109\/GCWkshps45667.2019.9024682"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1016\/j.comcom.2019.11.037","article-title":"Energy efficient for UAV-enabled mobile edge computing networks: Intelligent task prediction and offloading","volume":"150","author":"Wu","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.comcom.2019.10.021","article-title":"Agent-enabled task offloading in UAV-aided mobile edge computing","volume":"149","author":"Wang","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"107273","DOI":"10.1016\/j.comnet.2020.107273","article-title":"UAVs for traffic monitoring: A sequential game-based computation offloading\/sharing approach","volume":"177","author":"Alioua","year":"2020","journal-title":"Comput. Netw."},{"key":"ref_35","unstructured":"Yu, S., and Langar, R. (2019, January 8\u201312). Collaborative computation offloading for multi-access edge computing. Proceedings of the 2019 IFIP\/IEEE Symposium on Integrated Network and Service Management (IM), Arlington, VA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Alshareef, H.N., and Grigoras, D. (2017, January 3\u20136). Multi-service cloud of drones for multi-purpose applications. Proceedings of the 2017 16th International Symposium on Parallel and Distributed Computing (ISPDC), Innsbruck, Austria.","DOI":"10.1109\/ISPDC.2017.28"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.adhoc.2018.09.013","article-title":"Dronemap Planner: A service-oriented cloud-based management system for the Internet-of-Drones","volume":"86","author":"Koubaa","year":"2019","journal-title":"Ad Hoc Netw."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Koub\u00e2a, A., Qureshi, B., Sriti, M., Javed, Y., and Tovar, E. (2017, January 26\u201328). A service-oriented Cloud-based management system for the Internet-of-Drones. Proceedings of the 2017 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), Coimbra, Portugal.","DOI":"10.1109\/ICARSC.2017.7964096"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"107496","DOI":"10.1016\/j.comnet.2020.107496","article-title":"A survey on the computation offloading approaches in mobile edge computing: A machine learning-based perspective","volume":"182","author":"Shakarami","year":"2020","journal-title":"Comput. Netw."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"102781","DOI":"10.1016\/j.jnca.2020.102781","article-title":"A survey on computation offloading modeling for edge computing","volume":"169","author":"Lin","year":"2020","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"13810","DOI":"10.1109\/ACCESS.2018.2811762","article-title":"DroneTrack: Cloud-based real-time object tracking using unmanned aerial vehicles over the Internet","volume":"6","author":"Koubaa","year":"2018","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Koubaa, A. (2016). Robot Operating System (ROS): The Complete Reference, Springer Publishing Company, Incorporated. [1st ed.].","DOI":"10.1007\/978-3-319-26054-9"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/978-3-319-54927-9_8","article-title":"ROSLink: Bridging ROS with the Internet-of-Things for Cloud Robotics","volume":"Volume 2","author":"Koubaa","year":"2017","journal-title":"Robot Operating System (ROS): The Complete Reference"},{"key":"ref_44","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_45","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"44125","DOI":"10.1109\/ACCESS.2020.2976122","article-title":"Node and edge drone surveillance problem with consideration of required observation quality and battery replacement","volume":"8","author":"Singgih","year":"2020","journal-title":"IEEE Access"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Wang, J., Feng, Z., Chen, Z., George, S., Bala, M., Pillai, P., Yang, S., and Satyanarayanan, M. (2018, January 25\u201327). Bandwidth-efficient live video analytics for drones via edge computing. Proceedings of the 2018 IEEE\/ACM Symposium on Edge Computing (SEC), Seattle, WA, USA.","DOI":"10.1109\/SEC.2018.00019"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/MIC.2019.2909713","article-title":"Edge-based live video analytics for drones","volume":"23","author":"Wang","year":"2019","journal-title":"IEEE Internet Comput."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5240\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:09:48Z","timestamp":1760177388000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,14]]},"references-count":49,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20185240"],"URL":"https:\/\/doi.org\/10.3390\/s20185240","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,14]]}}}