{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:50:51Z","timestamp":1780599051955,"version":"3.54.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4202063"],"award-info":[{"award-number":["4202063"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2019YFB2204200"],"award-info":[{"award-number":["2019YFB2204200"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s00521-023-09078-8","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T07:02:15Z","timestamp":1699858935000},"page":"1067-1089","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["End-to-end acceleration of the YOLO object detection framework on FPGA-only devices"],"prefix":"10.1007","volume":"36","author":[{"given":"Dezheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aibin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruchan","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0068-8824","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"9078_CR1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.neucom.2021.04.001","volume":"449","author":"M Carranza-Garc\u00eda","year":"2021","unstructured":"Carranza-Garc\u00eda M, Lara-Ben\u00edtez P, Garc\u00eda-Guti\u00e9rrez J, Riquelme JC (2021) Enhancing object detection for autonomous driving by optimizing anchor generation and addressing class imbalance. Neurocomputing 449:229\u2013244. https:\/\/doi.org\/10.1016\/j.neucom.2021.04.001","journal-title":"Neurocomputing"},{"issue":"3","key":"9078_CR2","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1109\/TMI.2021.3122835","volume":"41","author":"EH Nguyen","year":"2022","unstructured":"Nguyen EH, Yang H, Deng R, Lu Y, Zhu Z, Roland JT, Lu L, Landman BA, Fogo AB, Huo Y (2022) Circle representation for medical object detection. IEEE Trans Med Imaging 41(3):746\u2013754. https:\/\/doi.org\/10.1109\/TMI.2021.3122835","journal-title":"IEEE Trans Med Imaging"},{"key":"9078_CR3","doi-asserted-by":"publisher","unstructured":"Angelo TD, Mendes M, Keller B, Ferreira R, Delabrida S, Rabelo R, Azpurua H, Bianchi A (2019) Deep learning-based object detection for digital inspection in the mining industry. In: 2019 18th ieee international conference on machine learning and applications (ICMLA), pp 633\u2013640. https:\/\/doi.org\/10.1109\/ICMLA.2019.00116","DOI":"10.1109\/ICMLA.2019.00116"},{"key":"9078_CR4","doi-asserted-by":"crossref","unstructured":"Zhang J, Cheng L, Li C, Li Y, He G, Xu N, Lian Y (2021) A low-latency FPGA implementation for real-time object detection. In: 2021 IEEE international symposium on circuits and systems (ISCAS), pp 1\u20135","DOI":"10.1109\/ISCAS51556.2021.9401577"},{"issue":"8","key":"9078_CR5","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1109\/TVLSI.2019.2905242","volume":"27","author":"DT Nguyen","year":"2019","unstructured":"Nguyen DT, Nguyen TN, Kim H, Lee H-J (2019) A high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection. IEEE Trans Very Large Scale Integr (VLSI) Syst 27(8):1861\u20131873. https:\/\/doi.org\/10.1109\/TVLSI.2019.2905242","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"key":"9078_CR6","doi-asserted-by":"publisher","unstructured":"Ahmad A, Pasha MA, Raza GJ (2020) Accelerating tiny YOLOv3 using FPGA-based hardware\/software co-design. In: 2020 IEEE international symposium on circuits and systems (ISCAS), pp 1\u20135. https:\/\/doi.org\/10.1109\/ISCAS45731.2020.9180843","DOI":"10.1109\/ISCAS45731.2020.9180843"},{"issue":"4","key":"9078_CR7","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/TCAD.2019.2897701","volume":"39","author":"Y Liang","year":"2020","unstructured":"Liang Y, Lu L, Xiao Q, Yan S (2020) Evaluating fast algorithms for convolutional neural networks on FPGAs. IEEE Trans Comput Aided Des Integr Circuits Syst 39(4):857\u2013870","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"issue":"5","key":"9078_CR8","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/TCSII.2020.2983648","volume":"67","author":"A Capotondi","year":"2020","unstructured":"Capotondi A, Rusci M, Fariselli M, Benini L (2020) CMix-NN: mixed low-precision CNN library for memory-constrained edge devices. IEEE Trans Circuits Syst II Express Briefs 67(5):871\u2013875. https:\/\/doi.org\/10.1109\/TCSII.2020.2983648","journal-title":"IEEE Trans Circuits Syst II Express Briefs"},{"issue":"19","key":"9078_CR9","doi-asserted-by":"publisher","first-page":"16989","DOI":"10.1007\/s00521-022-07351-w","volume":"34","author":"Z Zhang","year":"2022","unstructured":"Zhang Z, Mahmud MAP, Kouzani AZ (2022) Resource-constrained FPGA implementation of YOLOv2. Neural Comput Appl 34(19):16989\u201317006. https:\/\/doi.org\/10.1007\/s00521-022-07351-w","journal-title":"Neural Comput Appl"},{"key":"9078_CR10","doi-asserted-by":"publisher","unstructured":"Anupreetham A, Ibrahim M, Hall M, Boutros A, Kuzhively A, Mohanty A, Nurvitadhi E, Betz V, Cao Y, Seo J-s (2021) End-to-end FPGA-based object detection using pipelined CNN and non-maximum suppression. In: 2021 31st international conference on field-programmable logic and applications (FPL), pp 76\u201382. https:\/\/doi.org\/10.1109\/FPL53798.2021.00021. ISSN: 1946-1488","DOI":"10.1109\/FPL53798.2021.00021"},{"issue":"11","key":"9078_CR11","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.1109\/TCSII.2019.2893527","volume":"66","author":"M Shi","year":"2019","unstructured":"Shi M, Ouyang P, Yin S, Liu L, Wei S (2019) A fast and power-efficient hardware architecture for non-maximum suppression. IEEE Trans Circuits Syst II Express Briefs 66(11):1870\u20131874. https:\/\/doi.org\/10.1109\/TCSII.2019.2893527","journal-title":"IEEE Trans Circuits Syst II Express Briefs"},{"key":"9078_CR12","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 6517\u20136525. https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"9078_CR13","doi-asserted-by":"publisher","unstructured":"Li Y, Gong R, Tan X, Yang Y, Hu P, Zhang Q, Yu F, Wang W, Gu S (2021) BRECQ: pushing the limit of post-training quantization by block reconstruction. arXiv. arXiv:2102.05426 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2102.05426. Accessed 18 Apr 2023","DOI":"10.48550\/arXiv.2102.05426"},{"key":"9078_CR14","unstructured":"Nagel M, Amjad RA, Baalen MV, Louizos C, Blankevoort T (2020) Up or down? adaptive rounding for post-training quantization. In: Hal I, Aarti S (eds.) Proceedings of the 37th international conference on machine learning, vol 119. PMLR, pp 7197\u20137206. https:\/\/proceedings.mlr.press\/v119\/nagel20a.html"},{"issue":"11","key":"9078_CR15","doi-asserted-by":"publisher","first-page":"5784","DOI":"10.1109\/TNNLS.2018.2808319","volume":"29","author":"P Gysel","year":"2018","unstructured":"Gysel P, Pimentel J, Motamedi M, Ghiasi S (2018) Ristretto: a framework for empirical study of resource-efficient inference in convolutional neural networks. IEEE Trans Neural Netw Learn Syst 29(11):5784\u20135789. https:\/\/doi.org\/10.1109\/TNNLS.2018.2808319","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"9078_CR16","doi-asserted-by":"crossref","unstructured":"Wang D, Xu K, Jiang D (2017) PipeCNN: an opencl-based open-source FPGA accelerator for convolution neural networks. In: 2017 international conference on field programmable technology (ICFPT), pp 279\u2013282","DOI":"10.1109\/FPT.2017.8280160"},{"key":"9078_CR17","doi-asserted-by":"publisher","unstructured":"V\u00e9stias M, Duarte RP, Sousa JTd, Neto H (2017) Parallel dot-products for deep learning on FPGA. In: 2017 27th international conference on field programmable logic and applications (FPL), pp 1\u20134. https:\/\/doi.org\/10.23919\/FPL.2017.8056863","DOI":"10.23919\/FPL.2017.8056863"},{"key":"9078_CR18","unstructured":"Fu Y, Wu E, Sirasao A, Attia S, Khan K, Wittig R (2016) Deep learning with int8 optimization on xilinx devices"},{"key":"9078_CR19","unstructured":"Xilinx: UltraScale architecture and product data sheet: overview (2020). https:\/\/www.xilinx.com\/support\/documentation\/data_sheets\/ds890-ultrascale-overview.pdf"},{"key":"9078_CR20","doi-asserted-by":"publisher","unstructured":"Guo L, Lau J, Chi Y, Wang J, Yu CH, Chen Z, Zhang Z, Cong J (2020) Analysis and optimization of the implicit broadcasts in FPGA HLS to improve maximum frequency. In: 2020 57th ACM\/IEEE design automation conference (DAC), pp 1\u20136. https:\/\/doi.org\/10.1109\/DAC18072.2020.9218718","DOI":"10.1109\/DAC18072.2020.9218718"},{"issue":"12","key":"9078_CR21","doi-asserted-by":"publisher","first-page":"4867","DOI":"10.1109\/TCAD.2020.2968023","volume":"39","author":"D Wang","year":"2020","unstructured":"Wang D, Xu K, Guo J, Ghiasi S (2020) DSP-efficient hardware acceleration of convolutional neural network inference on FPGAs. IEEE Trans Comput Aided Des Integr Circuits Syst 39(12):4867\u20134880","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"key":"9078_CR22","doi-asserted-by":"publisher","unstructured":"Obeidat F, Klenke R (2011) Introducing MicroBlaze as an infrastructure for performance modeling. In: 2011 IEEE international conference on microelectronic systems education, pp 90\u201393. https:\/\/doi.org\/10.1109\/MSE.2011.5937101","DOI":"10.1109\/MSE.2011.5937101"},{"key":"9078_CR23","doi-asserted-by":"publisher","unstructured":"Xu M, Yao H, Huan X (2012) Performance test of dual-core processor system based on NIOS II. In: 2012 IEEE symposium on electrical & electronics engineering (EEESYM), pp 82\u201385. https:\/\/doi.org\/10.1109\/EEESym.2012.6258593","DOI":"10.1109\/EEESym.2012.6258593"},{"issue":"4","key":"9078_CR24","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams S, Waterman A, Patterson D (2009) Roofline: an insightful visual performance model for multicore architectures. Commun ACM 52(4):65\u201376. https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun ACM"},{"key":"9078_CR25","doi-asserted-by":"publisher","unstructured":"Zhang C, Li P, Sun G, Guan Y, Xiao B, Cong J (2015) Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM\/SIGDA international symposium on field-programmable gate arrays, pp 161\u2013170. Association for Computing Machinery, Monterey California USA. https:\/\/doi.org\/10.1145\/2684746.2689060","DOI":"10.1145\/2684746.2689060"},{"key":"9078_CR26","unstructured":"Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X, Sun S, Feng W, Liu Z, Xu J, Zhang Z, Cheng D, Zhu C, Cheng T, Zhao Q, Li B, Lu X, Zhu R, Wu Y, Dai J, Wang J, Shi J, Ouyang W, Loy CC, Lin D (2019) MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"issue":"2","key":"9078_CR27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The PASCAL visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int J Comput Vis"},{"issue":"11","key":"9078_CR28","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1109\/TVLSI.2022.3151788","volume":"30","author":"S Li","year":"2022","unstructured":"Li S, Wang Q, Jiang J, Sheng W, Jing N, Mao Z (2022) An efficient CNN accelerator using inter-frame data reuse of videos on FPGAs. IEEE Trans Very Large Scale Integr (VLSI) Syst 30(11):1587\u20131600. https:\/\/doi.org\/10.1109\/TVLSI.2022.3151788","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"key":"9078_CR29","unstructured":"Intel neural compute stick 2. https:\/\/www.intel.com\/content\/www\/cn\/zh\/developer\/articles\/tool\/neural-compute-stick.html Accessed 10 May 2023"},{"key":"9078_CR30","unstructured":"Jetson nano developer kit for AI and robotics | NVIDIA. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-nano\/ Accessed 10 May 2023"},{"key":"9078_CR31","doi-asserted-by":"publisher","unstructured":"Herrmann V, Knapheide J, Steinert F, Stabernack B (2022) A YOLO v3-tiny FPGA architecture using a reconfigurable hardware accelerator for real-time region of interest detection. In: 2022 25th Euromicro conference on digital system design (DSD), pp 84\u201392. https:\/\/doi.org\/10.1109\/DSD57027.2022.00021. ISSN: 2771-2508","DOI":"10.1109\/DSD57027.2022.00021"},{"key":"9078_CR32","doi-asserted-by":"publisher","unstructured":"Zhang H, Wu W, Ma Y, Wang Z (2020) Efficient hardware post processing of anchor-based object detection on FPGA. In: 2020 IEEE computer society annual symposium on VLSI (ISVLSI). IEEE, Limassol, Cyprus, pp 580\u2013585. https:\/\/doi.org\/10.1109\/ISVLSI49217.2020.00089. https:\/\/ieeexplore.ieee.org\/document\/9155076\/ Accessed 15 Nov 2022","DOI":"10.1109\/ISVLSI49217.2020.00089"},{"key":"9078_CR33","doi-asserted-by":"publisher","first-page":"141890","DOI":"10.1109\/ACCESS.2021.3120629","volume":"9","author":"T Adiono","year":"2021","unstructured":"Adiono T, Putra A, Sutisna N, Syafalni I, Mulyawan R (2021) Low latency YOLOv3-Tiny accelerator for low-cost FPGA using general matrix multiplication principle. IEEE Access 9:141890\u2013141913. https:\/\/doi.org\/10.1109\/ACCESS.2021.3120629","journal-title":"IEEE Access"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09078-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-09078-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09078-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T08:12:10Z","timestamp":1704442330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-09078-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["9078"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-09078-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"23 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}