000 02432naa a22003738i 4500
999 _c5320
_d5320
001 00005320
003 FR-PaOEC
005 20211006062617.0
006 a o d i
007 cr || |||m|n||
008 190601s2017 ||| o i|0| 0 eng d
035 _a(FR-PaOEC)
040 _aFR-PaOEC
_cES-MaONT
100 1 _aWang, Yu
_93339
245 1 0 _aReconfigurable processor for deep learning in autonomous vehicles /
_cYu Wang ... [el al.]
260 _aGeneva :
_bInternational Telecommunication Union,
_c2017.
300 _a13 p.
336 _atexto (visual)
_2isbdcontent
337 _aelectrónico
_2isbdmedia
338 _arecurso en línea
_2rdacarrier
520 3 _aThe rapid growth of civilian vehicles has stimulated the development of advanced driver assistance systems (ADASs) to be equipped in-car. Real-time autonomous vision (RTAV) is an essential part of the overall system, and the emergence of deep learning methods has greatly improved the system quality, which also requires the processor to offer a computing speed of tera operations per second (TOPS) and a power consumption of no more than 30 W with programmability. This article gives an overview of the trends of RTAV algorithms and different hardware solutions, and proposes a development route for the reconfigurable RTAV accelerator. We propose our field programmable gate array (FPGA) based system Aristotle, together with an all-stack software-hardware co design workflow including compression, compilation, and customized hardware architecture. Evaluation shows that our FPGA system can realize real-time processing on modern RTAV algorithms with a higher efficiency than peer CPU and GPU platforms. Our outlook based on the ASIC-based system design and the ongoing implementation of next generation memory would target a 100 TOPS performance with around 20 W power.
650 0 _aTecnologías habilitadoras digitales
_918
653 4 _aScience and Technology
700 1 _aLiang, Shuang
_93340
700 1 _aYao, Song
_93341
700 1 _aShan, Yi
_93342
700 1 _aHan, Song
_93343
700 1 _aPeng, Jinzhang
_93344
700 1 _aLuo, Hong
_93345
773 0 _04843
_tITU Journal: ICT Discoveries
_gVol. 2018, no. 1, p. 9-21
_q2018:1<9
_x2616-8375
856 4 0 _aitu-ilibrary.org
_uhttps://www.itu.int/dms_pub/itu-s/opb/journal/S-JOURNAL-ICTS.V1I1-2017-2-PDF-E.pdf
_yAcceso al documento
_x0
_qpdf
942 _cART
_2udc