{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:06:57Z","timestamp":1765357617200,"version":"build-2065373602"},"reference-count":44,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":171,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171342"],"award-info":[{"award-number":["62171342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011354","name":"State Key Laboratory of Geo-Information Engineering","doi-asserted-by":"publisher","award":["SKLGIE2023-M-3-1"],"award-info":[{"award-number":["SKLGIE2023-M-3-1"]}],"id":[{"id":"10.13039\/501100011354","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Computers &amp;amp; Digital Techniques"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>Convolutional neural networks (CNNs) have been widely used in satellite remote sensing. However, satellites in orbit with limited resources and power consumption cannot meet the storage and computing power requirements of current million\u2010scale artificial intelligence models. This paper proposes a new generation of high flexibility and intelligent CNNs hardware accelerator for satellite remote sensing in order to make its computing carrier more lightweight and efficient. A data quantization scheme for INT16 or INT8 is designed based on the idea of dynamic fixed point numbers and is applied to different scenarios. The operation mode of the systolic array is divided into channel blocks, and the calculation method is optimized to increase the utilization of on\u2010chip computing resources and enhance the calculation efficiency. An RTL\u2010level CNNs field programable gate arrays accelerator with microinstruction sequence scheduling data flow is then designed. The hardware framework is built upon the Xilinx VC709. The results show that, under INT16 or INT8 precision, the system achieves remarkable throughput in most convolutional layers of the network, with an average performance of 153.14 giga operations per second (GOPS) or 301.52 GOPS, which is close to the system\u2019s peak performance, taking full advantage of the platform\u2019s parallel computing capabilities.<\/jats:p>","DOI":"10.1049\/2024\/4415342","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T05:05:13Z","timestamp":1718859913000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Configurable Accelerator for CNN\u2010Based Remote Sensing Object Detection on FPGAs"],"prefix":"10.1049","volume":"2024","author":[{"given":"Yingzhao","family":"Shao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6827-7690","authenticated-orcid":false,"given":"Jincheng","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yueli","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Mingming","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"265","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41377-022-00714-x"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2654822.2541967"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001179"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"ZhangS. DuZ. ZhangL. LanH. LiuS. LiL. GuoQ. ChenT. andChenY. Cambricon-X: an accelerator for sparse neural networks 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) October 2016 IEEE 1\u201312.","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"GokhaleV. JinJ. DundarA. MartiniB. andCulurcielloE. A 240 G-ops\/s mobile coprocessor for deep neural networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops June 2014 IEEE.","DOI":"10.1109\/CVPRW.2014.106"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"WeiX. YuC. H. ZhangP. ChenY. WangY. HuH. LiangY. andCongJ. Automated systolic array architecture synthesis for high throughput CNN inference on FPGAs Proceedings of the 54th Annual Design Automation Conference 2017 June 2017 IEEE 1\u20136.","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_2_9_9_2","first-page":"543","article-title":"The process and experience in the development of Chinese lunar probe","volume":"44","author":"Ye P.","year":"2014","journal-title":"Science China-Technological Sciences"},{"key":"e_1_2_9_10_2","first-page":"1","article-title":"Algorithm\/hardware codesign for real-time on-satellite CNN-based ship detection in SAR imagery","volume":"60","author":"Yang G.","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_2_9_11_2","first-page":"24","article-title":"Structure optimization of convolutional neural networks: a survey","volume":"46","author":"Lin J.","year":"2020","journal-title":"Acta Automatica Sinica"},{"key":"e_1_2_9_12_2","first-page":"776","article-title":"Research on data acquisition technology of chinese high-resolution broadband multispectral satellites in the \u201cthe belt and road initiative\u201d region","volume":"38","author":"Songyan W.","year":"2023","journal-title":"Remote Sensing Technology and Application"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/s19040924"},{"key":"e_1_2_9_14_2","first-page":"179","article-title":"Real-time object detection in remote sensing images based on embedded system","volume":"41","author":"Nong Y.","year":"2021","journal-title":"Acta Optica Sinica"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1051\/jnwpu\/20213930510"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"LiuS.andDengW. Very deep convolutional neural network based image classification using small training sample size 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) November 2015 Kuala Lumpur Malaysia IEEE 730\u2013734.","DOI":"10.1109\/ACPR.2015.7486599"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2016 Las Vegas NV USA IEEE 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"CholletF. Xception: deep learning with depthwise separable convolutions 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 2017 IEEE 1800\u20131807.","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"SandlerM. HowardA. ZhuM. ZhmoginovA. andChenL.-C. MobileNetV2: inverted residuals and linear bottlenecks 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2018 IEEE 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"HowardA. SandlerM. ChenB. WangW. ChenL.-C. TanM. ChuG. VasudevanV. ZhuY. PangR. AdamH. andLeQ. Searching for mobilenetV3 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) October 2019 Seoul Korea (South) IEEE 1314\u20131324 https:\/\/doi.org\/10.1109\/ICCV.2019.00140.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"RedmonJ.andFarhadiA. YOLO9000: better faster stronger Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition July 2017 IEEE 7263\u20137271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_9_22_2","article-title":"Object detection algorithm based on improved YOLOv3","volume":"9","author":"Liquan Z.","year":"2020","journal-title":"Electronics"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106135"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"AdarshP. RathiP. andKumarM. YOLO v3-Tiny: object detection and recognition using one stage improved model 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS) March 2020 IEEE 687\u2013694.","DOI":"10.1109\/ICACCS48705.2020.9074315"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"CaiY. LiangC. TangZ. LiH. andGongS. AbawajyJ. ChooK.-K. R. andIslamR. Deep neural network with limited numerical precision International Conference on Applications and Techniques in Cyber Security and Intelligence 2018 Cham Springer International Publishing 42\u201350.","DOI":"10.1007\/978-3-319-67071-3_8"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"BoutrosA. EldafrawyM. YazdanshenasS. andBetzV. Math doesn\u2019t have to be hard: logic block architectures to enhance low-precision multiply-accumulate on FPGAs Proceedings of the 2019 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays 2019 New York NY USA Association for Computing Machinery 94\u2013103 FPGA \u201919.","DOI":"10.1145\/3289602.3293912"},{"key":"e_1_2_9_27_2","article-title":"Mixed-precision quantization technology of convolutional neural networks","volume":"44","author":"Sun J.","year":"2020","journal-title":"Information Technology"},{"key":"e_1_2_9_28_2","article-title":"Deep neural network compression and acceleration: an overview","volume":"38","author":"Zeng H.","year":"2022","journal-title":"Journal of Signal Processing"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"CaiY. YaoZ. DongZ. GholamiA. MahoneyM. W. andKeutzerK. ZeroQ: a novel zero shot quantization framework 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020 IEEE 13166\u201313175.","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.3788\/IRLA20200170"},{"key":"e_1_2_9_31_2","unstructured":"LvL. Research on neural network compression for SSDResNet 2019 XIDIAN University Xian Ph.D. thesis."},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"JacobB. KligysS. ChenB. ZhuM. TangM. HowardA. AdamH. andKalenichenkoD. Quantization and training of neural networks for efficient integer-arithmetic-only inference 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2018 IEEE 2704\u20132713.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"GongR. LiuX. JiangS. LiT. HuP. LinJ. YuF. andYanJ. Differentiable soft quantization: bridging full-precision and low-bit neural networks 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) October 2019 IEEE 4851\u20134860.","DOI":"10.1109\/ICCV.2019.00495"},{"key":"e_1_2_9_34_2","doi-asserted-by":"crossref","unstructured":"ZhuF. GongR. YuF. LiuX. WangY. LiZ. YangX. andYanJ. Towards unified INT8 training for convolutional neural network Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 IEEE.","DOI":"10.1109\/CVPR42600.2020.00204"},{"key":"e_1_2_9_35_2","doi-asserted-by":"crossref","unstructured":"MaY. SudaN. CaoY. SeoJ. S. andVrudhulaS. Scalable and modularized RTL compilation of convolutional neural networks onto FPGA International Conference on Field Programmable Logic Applications 2016 IEEE 1\u20138.","DOI":"10.1109\/FPL.2016.7577356"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"WeiX. YuC. H. ZhangP. ChenY. WangY. HuH. LiangY. andCongJ. Automated systolic array architecture synthesis for high throughput CNN inference on FPGAs 2017 54th ACM\/EDAC\/IEEE Design Automation Conference June 2017 IEEE 1\u20136.","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080221"},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"ZhangC. DiW. SunJ. SunG. LuoG. andCongJ. Energy-efficient CNN implementation on a deeply pipelined FPGA cluster Proceedings of the 2016 International Symposium on Low Power Electronics and Design 2016 Association for Computing Machinery 326\u2013331.","DOI":"10.1145\/2934583.2934644"},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"WangD. ShenJ. WenM. andZhangC. An efficient design flow for accelerating complicated-connected CNNs on a multi-FPGA platform Proceedings of the 48th International Conference on Parallel Processing 2019 Association for Computing Machinery 1\u201310.","DOI":"10.1145\/3337821.3337846"},{"key":"e_1_2_9_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"e_1_2_9_41_2","doi-asserted-by":"publisher","DOI":"10.1049\/ell2.12121"},{"key":"e_1_2_9_42_2","doi-asserted-by":"publisher","DOI":"10.1049\/ell2.12435"},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1049\/cds2.12091"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"}],"container-title":["IET Computers &amp; Digital Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/2024\/4415342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T09:14:09Z","timestamp":1762334049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/2024\/4415342"}},"subtitle":[],"editor":[{"given":"Sudarshan K.","family":"Srinivasan","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1049\/2024\/4415342"],"URL":"https:\/\/doi.org\/10.1049\/2024\/4415342","archive":["Portico"],"relation":{},"ISSN":["1751-8601","1751-861X"],"issn-type":[{"type":"print","value":"1751-8601"},{"type":"electronic","value":"1751-861X"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2024-01-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4415342"}}