{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:22:36Z","timestamp":1766067756483,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T00:00:00Z","timestamp":1684454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"\u201cTransilvania\u201d University of Brasov\u2014Romania"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Computer vision algorithms implementations, especially for real-time applications, are present in a variety of devices that we are currently using (from smartphones or automotive applications to monitoring\/security applications) and pose specific challenges, memory bandwidth or energy consumption (e.g., for mobility) being the most notable ones. This paper aims at providing a solution to improve the overall quality of real-time object detection computer vision algorithms using a hybrid hardware\u2013software implementation. To this end, we explore the methods for a proper allocation of algorithm components towards hardware (as IP Cores) and the interfacing between hardware and software. Addressing specific design constraints, the relationship between the above components allows embedded artificial intelligence to select the operating hardware blocks (IP cores)\u2014in the configuration phase\u2014and to dynamically change the parameters of the aggregated hardware resources\u2014in the instantiation phase, similar to the concretization of a class into a software object. The conclusions show the benefits of using hybrid hardware\u2013software implementations, as well as major gains from using IP Cores, managed by artificial intelligence, for an object detection use-case, implemented on a FPGA demonstrator built around a Xilinx Zynq-7000 SoC Mini-ITX sub-system.<\/jats:p>","DOI":"10.3390\/s23104894","type":"journal-article","created":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T10:08:55Z","timestamp":1684490935000},"page":"4894","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Hardware\u2013Software Partitioning for Real-Time Object Detection Using Dynamic Parameter Optimization"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8170-7176","authenticated-orcid":false,"given":"Corneliu","family":"Zaharia","sequence":"first","affiliation":[{"name":"Department of Electronics and Computers, Transilvania University, Bdul Eroilor 29, 500068 Bra\u0219ov, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3421-4544","authenticated-orcid":false,"given":"Vlad","family":"Popescu","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computers, Transilvania University, Bdul Eroilor 29, 500068 Bra\u0219ov, Romania"}]},{"given":"Florin","family":"Sandu","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computers, Transilvania University, Bdul Eroilor 29, 500068 Bra\u0219ov, Romania"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,19]]},"reference":[{"key":"ref_1","unstructured":"Gadepally, V., Goodwin, J., Kepner, J., Reuther, A., Reynolds, H., Samsi, S., Su, J., and Martinez, D. (2019). AI enabling technologies: A survey. arXiv."},{"key":"ref_2","unstructured":"Turley, J. (2014). Introduction to Intel\u00ae Architecture: The Basics, Intel Corporation."},{"key":"ref_3","unstructured":"(2023, February 15). ARM7TDMI Technical Reference Manual r4p1. Available online: https:\/\/developer.arm.com\/documentation\/ddi0210\/c\/Introduction\/Block--core--and-functional-diagrams."},{"key":"ref_4","unstructured":"(2023, February 15). BA22-CE 32-bit Cache-Enabled Embedded Processor. Available online: https:\/\/www.cast-inc.com\/processors\/32-bit\/ba22-ce."},{"key":"ref_5","unstructured":"Waterman, A., Lee, Y., Patterson, D., and Asanovic, K. (2023, February 15). The RISC-V Compressed Instruction Set Manual. Available online: https:\/\/riscv.org\/wp-content\/uploads\/2015\/05\/riscv-compressed-spec-v1.7.pdf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ang, L.M., and Seng, K.P. (2021). GPU-Based Embedded Intelligence Architectures and Applications. Electronics, 10.","DOI":"10.3390\/electronics10080952"},{"key":"ref_7","unstructured":"(2023, February 15). Qualcomm\u2014DSP Processor. Available online: https:\/\/developer.qualcomm.com\/software\/hexagon-dsp-sdk\/dsp-processor."},{"key":"ref_8","unstructured":"Texas Instruments (2023, February 16). Vision-Based Advanced Driver Assistance: TI Hopes You\u2019ll Give Its Latest SoCs a Chance. Available online: https:\/\/www.bdti.com\/InsideDSP\/2013\/10\/23\/TI."},{"key":"ref_9","unstructured":"Vision DSP (2023, February 16). CEVA-XM4\u2014Intelligent Imaging and Vision Processor for Low-Power Embedded Systems. Available online: https:\/\/www.ceva-dsp.com\/product\/ceva-xm4\/."},{"key":"ref_10","unstructured":"Harris, M. (2023, February 16). Inside Pascal: NVIDIA\u2019s Newest Computing Platform. Available online: https:\/\/developer.nvidia.com\/blog\/inside-pascal\/."},{"key":"ref_11","unstructured":"ARM (2023, February 16). Mali-G72\/-470. Available online: https:\/\/developer.arm.com\/Processors\/Mali-G72."},{"key":"ref_12","unstructured":"Beets, K. (2023, February 16). Imagination\u2014Introducing Furian: The Architectural Changes. Available online: https:\/\/blog.imaginationtech.com\/introducing-furian-the-architectural-changes\/."},{"key":"ref_13","unstructured":"(2023, February 16). Movidius\u2014VPU Product Brief. Available online: https:\/\/static6.arrow.com\/aropdfconversion\/5a53549959ba1304f155469049d98b3ade903558\/1463156689-2016-04-29_vpu_productbrief.pdf."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jang, J.W., Lee, S., Kim, D., Park, H., Ardestani, A.S., Choi, Y., Kim, C., Kim, Y., Yu, H., and Abdel-Aziz, H. (2021, January 14\u201318). Sparsity-aware and re-configurable NPU architecture for Samsung flagship mobile SoC. Proceedings of the ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), Valencia, Spain.","DOI":"10.1109\/ISCA52012.2021.00011"},{"key":"ref_15","unstructured":"Schiesser, T. (2023, February 16). AMD Launches RYZEN 6000 Series for Laptops: What\u2019s New with the Zen 3+ Architecture?. Available online: https:\/\/www.techspot.com\/news\/93424-amd-launches-ryzen-6000-mobile-what-new-zen.html."},{"key":"ref_16","unstructured":"(2023, February 16). Verisilicon\u2014Neural Network Processor IP Series for AI Vision and AI Voice. Available online: https:\/\/verisilicon.com\/en\/IPPortfolio\/VivanteVIP9000."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1007\/s11554-020-01035-1","article-title":"FPGA-based architecture for bi-cubic interpolation: The best trade-off between precision and hardware resource consumption","volume":"18","author":"Boukhtache","year":"2021","journal-title":"J. Real-Time Image Process."},{"key":"ref_18","unstructured":"(2023, February 16). Xilinx Zynq\u00ae-7000 SoC First Generation Architecture. Available online: https:\/\/www.mouser.co.uk\/new\/xilinx\/xilinx-zynq-7000-socs\/."},{"key":"ref_19","unstructured":"(2023, February 16). Intel\u00ae Arria\u00ae 10 FPGAs & SoCs. Available online: https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga.html."},{"key":"ref_20","unstructured":"(2023, February 16). Xilinx\u2014Flexible DSP Solutions. Available online: https:\/\/www.xilinx.com\/products\/technology\/dsp.html."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jouppi, N.P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., and Borchers, A. (2017, January 24\u201328). In-datacenter performance analysis of a tensor processing unit. Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA), Toronto, CA, USA.","DOI":"10.1145\/3079856.3080246"},{"key":"ref_22","unstructured":"(2023, February 17). IBM\u2014The Brain\u2019s Architecture, Efficiency\u2026 on a Chip. Available online: www.ibm.com\/blogs\/research\/2016\/12\/the-brains-architecture-efficiency-on-a-chip."},{"key":"ref_23","unstructured":"(2023, February 16). Intel\u2014Lake Crest\/Spring Crest\/Spring Hill\u2014Microarchitectures. Available online: https:\/\/en.wikichip.org\/wiki\/intel\/microarchitectures\/spring_hill."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Buckler, M., Jayasuriya, S., and Sampson, A. (2017, January 22\u201329). Reconfiguring the imaging pipeline for computer vision. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.111"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hansen, P., Vilkin, A., Krustalev, Y., Imber, J., Talagala, D., Hanwell, D., Mattina, M., and Whatmough, P.N.J. (2021, January 10\u201315). ISP4ML: The Role of Image Signal Processing in Efficient Deep Learning Vision Systems. Proceedings of the 25th IEEE International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9411985"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ao, H., Guoyi, Y., Qianjin, W., Dongxiao, H., Shilun, Z., Bingqiang, L., Yu, Y., Yuwen, L., Chao, W., and Xuecheng, Z. (2022). Efficient Hardware Accelerator Design of Non-Linear Optimization Correlative Scan Matching Algorithm in 2D LiDAR SLAM for Mobile Robots. Sensors, 22.","DOI":"10.3390\/s22228947"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Merolla, P., Arthur, J., Akopyan, F., Imam, N., Manohar, R., and Modha, D.S. (2011, January 19\u201321). A digital neurosynaptic core using embedded crossbar memory with 45pJ per spike in 45nm. Proceedings of the IEEE Custom Integrated Circuits Conference (CICC), San Jose, CA, USA.","DOI":"10.1109\/CICC.2011.6055294"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"eabl8419","DOI":"10.1126\/scirobotics.abl8419","article-title":"Neuromorphic computing hardware and neural architectures for robotics","volume":"7","author":"Sandamirskaya","year":"2022","journal-title":"Sci. Robot."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"101839","DOI":"10.1016\/j.sysarc.2020.101839","article-title":"A survey on hardware accelerators and optimization techniques for RNNs","volume":"112","author":"Mittal","year":"2021","journal-title":"J. Syst. Archit."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ghaffari, S., Soleimani, P., Li, K.F., and Capson, D. (2019, January 21\u201323). FPGA-based implementation of HOG algorithm: Techniques and challenges. Proceedings of the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM), Victoria, BC, Canada.","DOI":"10.1109\/PACRIM47961.2019.8985056"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Long, X., Hu, S., Hu, Y., Gu, Q., and Ishii, I. (2019). An FPGA-Based Ultra-High-Speed Object Detection Algorithm with Multi-Frame Information Fusion. Sensors, 19.","DOI":"10.3390\/s19173707"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Rzaev, E., Khanaev, A., and Amerikanov, A. (2021, January 17\u201321). Neural Network for Real-Time Object Detection on FPGA. Proceedings of the 2021 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), Sochi, Russia.","DOI":"10.1109\/ICIEAM51226.2021.9446384"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Shimoda, M., Sada, Y., Kuramochi, R., and Nakahara, H. (2019, January 8\u201312). An FPGA Implementation of Real-time Object Detection with a Thermal Camera. Proceedings of the 29th IEEE International Conference on Field Programmable Logic and Applications (FPL), Barcelona, Spain.","DOI":"10.1109\/FPL.2019.00072"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"G\u00fcnay, B., Okcu, S.B., and Bilge, H.S. (2022). LPYOLO: Low Precision YOLO for Face Detection on FPGA. arXiv.","DOI":"10.11159\/mvml22.108"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"116569","DOI":"10.1109\/ACCESS.2020.3004198","article-title":"Sparse-YOLO: Hardware\/software co-design of an FPGA accelerator for YOLOv2","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2021, January 20\u201325). Scaled-YOLOv4: Scaling cross stage partial network. Proceedings of the IEEE\/cvf Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Shi, P., and Pan, D. (2020, January 30\u201331). A Survey of Super-Resolution Based on Deep Learning. Proceedings of the 2020 International Conference on Culture-Oriented Science Technology (ICCST), Beijing, China.","DOI":"10.1109\/ICCST50977.2020.00106"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Talab, M.A., Awang, S., and Najim, S.A.D.M. (2019, January 29). Super-Low Resolution Face Recognition using Integrated Efficient Sub-Pixel Convolutional Neural Network (ESPCN) and Convolutional Neural Network (CNN). Proceedings of the 2019 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), Selangor, Malaysia.","DOI":"10.1109\/I2CACIS.2019.8825083"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Kang, J.S., Kang, J.K., Kim, J.J., Jeon, K.W., Chung, H.J., and Park, B.H. (2023). Neural Architecture Search Survey: A Computer Vision Perspective. Sensors, 23.","DOI":"10.3390\/s23031713"},{"key":"ref_40","first-page":"4178","article-title":"Instance-invariant domain adaptive object detection via progressive disentanglement","volume":"44","author":"Wu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wu, A., Han, Y., Zhu, L., and Yang, Y. (2021, January 11\u201317). Universal-prototype enhancing for few-shot object detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00943"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wu, A., and Deng, C. (2022, January 18\u201324). Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00092"},{"key":"ref_43","unstructured":"Jain, V., and Learned-Miller, E. (2023, February 23). FDDB: A Benchmark for Face Detection in Unconstrained Settings\u2014UMass Amherst Technical Report. Available online: http:\/\/crowley-coutaz.fr\/jlc\/Courses\/2020\/PRML\/fddb-DataBasePaper.pdf."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Putro, M.D., Priadana, A., Nguyen, D.L., and Jo, K.H. (2022, January 11\u201315). A Faster Real-time Face Detector Support Smart Digital Advertising on Low-cost Computing Device. Proceedings of the IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Sapporo, Japan.","DOI":"10.1109\/AIM52237.2022.9863289"},{"key":"ref_45","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201325). Histograms of Oriented Gradients for Human Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2223","DOI":"10.1007\/s00371-021-02280-6","article-title":"A novel backbone architecture for pedestrian detection based on the human visual system","volume":"38","author":"Saeidi","year":"2021","journal-title":"Vis. Comput."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Lan, W., Dang, J., Wang, Y., and Wang, S. (2018, January 5\u20139). Pedestrian Detection Based on YOLO Network Model. Proceedings of the IEEE International Conference on Mechatronics and Automation ICMA 2018, Changchun, China.","DOI":"10.1109\/ICMA.2018.8484698"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Li, R., and Zu, Y. (2023). Research on Pedestrian Detection Based on the Multi-Scale and Feature-Enhancement Model. Information, 14.","DOI":"10.3390\/info14020123"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Davis, J., and Goadrich, M. (2006, January 25\u201329). The relationship between Precision-Recall and ROC curves. Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, USA.","DOI":"10.1145\/1143844.1143874"},{"key":"ref_50","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, January 6\u201312). Microsoft coco: Common objects in context. Proceedings of the Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 20\u201325). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00075"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/10\/4894\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:38:22Z","timestamp":1760125102000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/10\/4894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,19]]},"references-count":51,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["s23104894"],"URL":"https:\/\/doi.org\/10.3390\/s23104894","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,5,19]]}}}