{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T23:11:03Z","timestamp":1778886663891,"version":"3.51.4"},"reference-count":30,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T00:00:00Z","timestamp":1653955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union\u2019s Horizon 2020 research and innovation program","doi-asserted-by":"publisher","award":["957391"],"award-info":[{"award-number":["957391"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Object detection is an essential capability for performing complex tasks in robotic applications. Today, deep learning (DL) approaches are the basis of state-of-the-art solutions in computer vision, where they provide very high accuracy albeit with high computational costs. Due to the physical limitations of robotic platforms, embedded devices are not as powerful as desktop computers, and adjustments have to be made to deep learning models before transferring them to robotic applications. This work benchmarks deep learning object detection models in embedded devices. Furthermore, some hardware selection guidelines are included, together with a description of the most relevant features of the two boards selected for this benchmark. Embedded electronic devices integrate a powerful AI co-processor to accelerate DL applications. To take advantage of these co-processors, models must be converted to a specific embedded runtime format. Five quantization levels applied to a collection of DL models are considered; two of them allow the execution of models in the embedded general-purpose CPU and are used as the baseline to assess the improvements obtained when running the same models with the three remaining quantization levels in the AI co-processors. The benchmark procedure is explained in detail, and a comprehensive analysis of the collected data is presented. Finally, the feasibility and challenges of the implementation of embedded object detection applications are discussed.<\/jats:p>","DOI":"10.3390\/s22114205","type":"journal-article","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T21:43:42Z","timestamp":1654119822000},"page":"4205","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Benchmarking Object Detection Deep Learning Models in Embedded Devices"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0396-4644","authenticated-orcid":false,"given":"David","family":"Cantero","sequence":"first","affiliation":[{"name":"TEKNIKER, Basque Research and Technology Alliance (BRTA), 20600 Eibar, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6542-2878","authenticated-orcid":false,"given":"Iker","family":"Esnaola-Gonzalez","sequence":"additional","affiliation":[{"name":"TEKNIKER, Basque Research and Technology Alliance (BRTA), 20600 Eibar, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-322X","authenticated-orcid":false,"given":"Jose","family":"Miguel-Alonso","sequence":"additional","affiliation":[{"name":"Department of Computer Architecture and Technology, University of the Basque Country UPV\/EHU, 20018 San Sebastian, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-9326","authenticated-orcid":false,"given":"Ekaitz","family":"Jauregi","sequence":"additional","affiliation":[{"name":"Department of Languages and Information Systems, University of the Basque Country UPV\/EHU, 20018 San Sebastian, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Merenda, M., Porcaro, C., and Iero, D. (2020). Edge machine learning for ai-enabled iot devices: A review. Sensors, 20.","DOI":"10.3390\/s20092533"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3469029","article-title":"Machine learning at the network edge: A survey","volume":"54","author":"Murshed","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_4","unstructured":"Pena, D., Forembski, A., Xu, X., and Moloney, D. (2017, January 15\u201316). Benchmarking of CNNs for low-cost, low-power robotics applications. Proceedings of the RSS 2017 Workshop: New Frontier for Deep Learning in Robotics, Rhodes, Greece."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hossain, S., and Lee, D. (2019). Deep learning-based real-time multiple-object detection and tracking from aerial imagery via a flying robot with GPU-based embedded devices. Sensors, 19.","DOI":"10.3390\/s19153371"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lonsdale, D., Zhang, L., and Jiang, R. (2020, January 2). 3D printed brain-controlled robot-arm prosthetic via embedded deep learning from sEMG sensors. Proceedings of the 2020 International Conference on Machine Learning and Cybernetics (ICMLC), Adelaide, Australia.","DOI":"10.1109\/ICMLC51923.2020.9469532"},{"key":"ref_7","first-page":"462","article-title":"Real-time human detection using deep learning on embedded platforms: A review","volume":"2","author":"Rahmaniar","year":"2021","journal-title":"J. Robot. Control"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1016\/j.future.2013.01.010","article-title":"Internet of Things (IoT): A vision, architectural elements, and future directions","volume":"29","author":"Gubbi","year":"2013","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s12599-014-0334-4","article-title":"Industry 4.0","volume":"6","author":"Lasi","year":"2014","journal-title":"Bus. Inf. Syst. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"V\u00e9stias, M.P., Duarte, R.P., de Sousa, J.T., and Neto, H.C. (2020). Moving deep learning to the edge. Algorithms, 13.","DOI":"10.3390\/a13050125"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: Vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An overview on edge computing research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Branco, S., Ferreira, A.G., and Cabral, J. (2019). Machine learning in resource-scarce embedded systems, FPGAs, and end-devices: A survey. Electronics, 8.","DOI":"10.3390\/electronics8111289"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ajani, T.S., Imoize, A.L., and Atayero, A.A. (2021). An overview of machine learning within embedded and mobile devices\u2013optimizations and applications. Sensors, 21.","DOI":"10.3390\/s21134412"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"64270","DOI":"10.1109\/ACCESS.2018.2877890","article-title":"Benchmark analysis of representative deep neural network architectures","volume":"6","author":"Bianco","year":"2018","journal-title":"IEEE Access"},{"key":"ref_16","unstructured":"Imran, H.A., Mujahid, U., Wazir, S., Latif, U., and Mehmood, K. (2020). Embedded development boards for edge-AI: A comprehensive report. arXiv."},{"key":"ref_17","unstructured":"Zacharias, J., Barz, M., and Sonntag, D. (2018). A survey on deep learning toolkits and libraries for intelligent user interfaces. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dai, W., and Berleant, D. (2019, January 12\u201314). Benchmarking contemporary deep learning hardware and frameworks: A survey of qualitative metrics. Proceedings of the 2019 IEEE First International Conference on Cognitive Machine Intelligence (CogMI), Los Angeles, CA, USA.","DOI":"10.1109\/CogMI48466.2019.00029"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: A review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","article-title":"Region-based convolutional networks for accurate object detection and segmentation","volume":"38","author":"Girshick","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_22","unstructured":"Zhou, X., Wang, D., and Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., and Belongie, S.J. (2016, January 21\u201326). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 13\u201319). Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_26","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"106838","DOI":"10.1109\/ACCESS.2019.2932731","article-title":"An Improved Faster R-CNN for Small Object Detection","volume":"7","author":"Cao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"19959","DOI":"10.1109\/ACCESS.2018.2815149","article-title":"Object Detection Based on Multi-Layer Convolution Feature Fusion and Online Hard Example Mining","volume":"6","author":"Chu","year":"2018","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R.B. (2017, January 22\u201329). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chu, J., Leng, L., and Miao, J. (2020). Mask-Refined R-CNN: A Network for Refining Object Details in Instance Segmentation. Sensors, 20.","DOI":"10.3390\/s20041010"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/11\/4205\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:22:58Z","timestamp":1760138578000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/11\/4205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,31]]},"references-count":30,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["s22114205"],"URL":"https:\/\/doi.org\/10.3390\/s22114205","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,31]]}}}