{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T04:28:32Z","timestamp":1713587312633},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"22","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2021,11,25]]},"DOI":"10.1587\/elex.18.20210323","type":"journal-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T22:16:01Z","timestamp":1634595361000},"page":"20210323-20210323","source":"Crossref","is-referenced-by-count":4,"title":["High-definition object detection technology based on AI inference scheme and its implementation"],"prefix":"10.1587","volume":"18","author":[{"given":"Hiroyuki","family":"Uzawa","sequence":"first","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Shuhei","family":"Yoshida","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Yuukou","family":"Iinuma","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Saki","family":"Hatta","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Daisuke","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Yuya","family":"Omori","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Ken","family":"Nakamura","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]},{"given":"Shuichi","family":"Takada","sequence":"additional","affiliation":[{"name":"ArchiTek Corporation"}]},{"given":"Hassan","family":"Toorabally","sequence":"additional","affiliation":[{"name":"ArchiTek Corporation"}]},{"given":"Kimikazu","family":"Sano","sequence":"additional","affiliation":[{"name":"NTT Device Innovation Center, NTT Corporation"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] X. Wu, <i>et al<\/i>.: \u201cRecent advances in deep learning for object detection,\u201d Neurocomputing <b>396<\/b> (2020) 39 (DOI: 10.1016\/j.neucom.2020.01.085).","DOI":"10.1016\/j.neucom.2020.01.085"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] L. Jiao, <i>et al<\/i>.: \u201cA survey of deep learning-based object detection,\u201d IEEE Access <b>7<\/b> (2019) 128837 (DOI: 10.1109\/access.2019.2939201).","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] J. Redmon, <i>et al<\/i>.: \u201cYou only look once: unified real-time object detection,\u201d IEEE CVPR (2016) 779 (DOI: 10.1109\/cvpr.2016.91).","DOI":"10.1109\/CVPR.2016.91"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] J. Redmon et al.: \u201cYOLO9000: better faster stronger,\u201d IEEE CVPR (2017) 6517 (DOI: 10.1109\/cvpr.2017.690).","DOI":"10.1109\/CVPR.2017.690"},{"key":"5","unstructured":"[5] J. Redmon, <i>et al<\/i>.: \u201cYOLOv3: an incremental improvement,\u201d https:\/\/arxiv.org\/abs\/1804.02767."},{"key":"6","unstructured":"[6] W. Liu, <i>et al<\/i>.: \u201cSSD: single shot multibox detector,\u201d https:\/\/arxiv.org\/abs\/1512.02325."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] H. Nakahara, <i>et al<\/i>.: \u201cA demonstration of FPGA-based you only look once version2 (YOLOv2),\u201d FPL (2018) 457 (DOI: 10.1109\/fpl.2018.00088).","DOI":"10.1109\/FPL.2018.00088"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Y.J. Wai, <i>et al<\/i>.: \u201cFixed point implementation of Tiny-Yolo-v2 using OpenCL on FPGA,\u201d IJACSA <b>9<\/b> (2018) (DOI: 10.14569\/ijacsa.2018.091062).","DOI":"10.14569\/IJACSA.2018.091062"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] D.T. Nguyen, <i>et al<\/i>.: \u201cA high-throughput and power-efficient FPGA implementaion of YOLO CNN for object detection,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>27<\/b> (2019) 1861 (DOI: 10.1109\/tvlsi.2019.2905242).","DOI":"10.1109\/TVLSI.2019.2905242"},{"key":"10","unstructured":"[10] C. Ding, <i>et al<\/i>.: \u201cREQ-YOLO: a resource-aware efficient quantization framework for object detection on FPGAs,\u201d https:\/\/arxiv.org\/abs\/1909.13396v1."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] Y.J. Wai, <i>et al<\/i>.: \u201cA scalable FPGA based accelerator for Tiny-YOLO-v2 using OpenCL,\u201d IJRES <b>8<\/b> (2019) 206 (DOI: 10.11591\/ijres.v8.i3.pp206-214).","DOI":"10.11591\/ijres.v8.i3.pp206-214"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] S. Zhang, <i>et al<\/i>.: \u201cAn FPGA-based reconfigurable CNN accelerator for YOLO,\u201d IEEE ICET (2020) 74 (DOI: 10.1109\/icet49382.2020.9119500).","DOI":"10.1109\/ICET49382.2020.9119500"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Z. Wang, <i>et al<\/i>.: \u201cSparse-YOLO: hardware\/software co-design of an FPGA accelerator for YOLOv2,\u201d IEEE Access <b>8<\/b> (2020) 116569 (DOI: 10.1109\/access.2020.3004198).","DOI":"10.1109\/ACCESS.2020.3004198"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] K. Xu, <i>et al<\/i>.: \u201cA dedicated hardware accelerator for real-time acceleration of YOLOv2,\u201d J. Real-Time Image Proc. <b>18<\/b> (2021) 481 (DOI: 10.1007\/s11554-020-00977-w).","DOI":"10.1007\/s11554-020-00977-w"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] H. Fan, <i>et al<\/i>.: \u201cA real-time object detection accelerator with compressed SSDLite on FPGA,\u201d FPT (2018) 14 (DOI: 10.1109\/fpt.2018.00014).","DOI":"10.1109\/FPT.2018.00014"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] F. Sun, <i>et al<\/i>.: \u201cA high-performance accelerator for large-scale convolutional neural networks,\u201d IEEE ISPA\/IUCC (2017) (DOI: 10.1109\/ispa\/iucc.2017.00099).","DOI":"10.1109\/ISPA\/IUCC.2017.00099"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] A. Maki, <i>et al<\/i>.: \u201cWeight compression MAC accelerator for effective inference of deep learning,\u201d IEICE Trans. Electron. <b>E103-C<\/b> (2020) 514 (DOI: 10.1587\/transele.2019ctp0007).","DOI":"10.1587\/transele.2019CTP0007"},{"key":"18","unstructured":"[18] A. Zhou, <i>et al<\/i>.: \u201cIncremental network quantization: towards lossless CNNs with low-precision weights,\u201d https:\/\/arxiv.org\/abs\/1702.03044."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Jo, <i>et al<\/i>.: \u201cDSIP: a scalable inference accelerator for convolutional neural networks,\u201d IEEE J. Solid-State Circuits <b>53<\/b> (2018) 605 (DOI: 10.1109\/jssc.2017.2764045).","DOI":"10.1109\/JSSC.2017.2764045"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] B. Zimmer, <i>et al<\/i>.: \u201cA 0.11pJ\/Op, 0.32-128 TOPS, scalable multi-chip-module-based deep neural network accelerator with ground-reference signaling in 16nm,\u201d VLSI Circuits (2019) (DOI: 10.23919\/vlsic.2019.8778056).","DOI":"10.23919\/VLSIC.2019.8778056"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] V. Ruzicka, <i>et al<\/i>.: \u201cFast and accurate object detection in high resolution 4K and 8K video using GPUs,\u201d IEEE HPEC (2018) (DOI: 10.1109\/hpec.2018.8547574).","DOI":"10.1109\/HPEC.2018.8547574"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] G. Plastiras, <i>et al<\/i>.: \u201cEfficient ConvNet-based object detection for unmanned aerial vehicles by selective tile processing,\u201d ICDSC (2018) (DOI: 10.1145\/3243394.3243692)","DOI":"10.1145\/3243394.3243692"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] D. Vorobjov, <i>et al<\/i>.: \u201cAn effective object detection algorithm for high resolution video by using convolutional neural network,\u201d LNCS <b>10878<\/b> (2019) 503 (DOI: 10.1007\/978-3-319-92537-0_58).","DOI":"10.1007\/978-3-319-92537-0_58"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] R. Bohush, <i>et al<\/i>.: \u201cObject detection algorithm for high resolution images based on convolutional neural network and multiscale processing,\u201d CMIS-2021 (2021).","DOI":"10.32782\/cmis\/2864-12"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] M. Gao, <i>et al<\/i>.: \u201cDynamic zoom-in network for fast object detection in large images,\u201d IEEE CVPR (2018) (DOI: 10.1109\/cvpr.2018.00724).","DOI":"10.1109\/CVPR.2018.00724"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] C. Tang, <i>et al<\/i>.: \u201cMulti-view object detection based on deep learning,\u201d Applied Sciences <b>8<\/b> (2018) 1423 (DOI: 10.3390\/app8091423).","DOI":"10.3390\/app8091423"},{"key":"27","unstructured":"[27] ArchiTek Corporation: \u201caIPE: the new blueprint for AI,\u201d https:\/\/architek.ai"},{"key":"28","unstructured":"[28] https:\/\/pjreddie.com\/darknet\/yolo\/"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] T.Y. Lin, <i>et al<\/i>.: \u201cMicrosoft coco: common objects in context,\u201d European Conference on Computer Vision (2014) 740 (DOI: 10.1007\/978-3-319-10602-1_48).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"30","unstructured":"[30] P. Zhu, <i>et al<\/i>.: \u201cVision meets drones: a challenge,\u201d arXive-prints, page arXiv: 1804.07437, April 2018."}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/18\/22\/18_18.20210323\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T18:29:27Z","timestamp":1673548167000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/18\/22\/18_18.20210323\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,25]]},"references-count":30,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.18.20210323","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,25]]},"article-number":"18.20210323"}}