An 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory

Cited 30 time in webofscience Cited 28 time in scopus
  • Hit : 93
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Donghyunko
dc.contributor.authorKim, Kwanhoko
dc.contributor.authorKim, Joo-Youngko
dc.contributor.authorLee, Seungjinko
dc.contributor.authorYoo, Hoi-Junko
dc.date.accessioned2020-10-23T02:55:42Z-
dc.date.available2020-10-23T02:55:42Z-
dc.date.created2020-10-12-
dc.date.created2020-10-12-
dc.date.issued2007-09-16-
dc.identifier.citation29th Annual IEEE Custom Integrated Circuits Conference, CICC 2007, pp.443 - 446-
dc.identifier.urihttp://hdl.handle.net/10203/276954-
dc.description.abstractAn 81.6 GOPS object recognition processor is developed by using NoC and Visual Image Processing (VIP) memory. SIFT (Scale Invariant Feature Transform) object recognition requires huge computing power and data transactions among tasks. The chip integrates 10 SIMD PEs for data/task level parallelism while the NoC facilitates inter-PE communications. The VIP memory searches local maximum pixel inside a 3×3 window in a single cycle providing 65.6 GOPS. The proposed processor achieves 15.9fps SIFT feature extraction at 200 MHz.-
dc.languageEnglish-
dc.publisherIEEE-
dc.titleAn 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory-
dc.typeConference-
dc.identifier.wosid000252233200100-
dc.identifier.scopusid2-s2.0-84938594928-
dc.type.rimsCONF-
dc.citation.beginningpage443-
dc.citation.endingpage446-
dc.citation.publicationname29th Annual IEEE Custom Integrated Circuits Conference, CICC 2007-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationDouble Tree Hotel, San Jose-
dc.identifier.doi10.1109/CICC.2007.4405769-
dc.contributor.localauthorKim, Joo-Young-
dc.contributor.localauthorYoo, Hoi-Jun-
dc.contributor.nonIdAuthorKim, Donghyun-
dc.contributor.nonIdAuthorKim, Kwanho-
dc.contributor.nonIdAuthorLee, Seungjin-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 30 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0