A 64.1mW Accurate Real-Time Visual Object Tracking Processor With Spatial Early Stopping on Siamese Network

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 75
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Soyeonko
dc.contributor.authorKim, Sangjinko
dc.contributor.authorKim, Sangyeobko
dc.contributor.authorHan, Donghyeonko
dc.contributor.authorYoo, Hoi-Junko
dc.date.accessioned2021-06-02T06:30:08Z-
dc.date.available2021-06-02T06:30:08Z-
dc.date.created2021-06-01-
dc.date.created2021-06-01-
dc.date.issued2021-05-
dc.identifier.citationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, v.68, no.5, pp.1675 - 1679-
dc.identifier.issn1549-7747-
dc.identifier.urihttp://hdl.handle.net/10203/285453-
dc.description.abstractA low power real-time visual object tracking (VOT) processor using the siamese network (SiamNet) is proposed for mobile devices. Two key features enable a real-time VOT with low power consumption on mobile devices. First, correlation-based spatial early stopping (CSES) is proposed to reduce the computational workload. CSES reduces similar to 56.8% of the overall computation of the SiamNet by gradually eliminating the background. Second, the dual mode reuse core (DMRC) is proposed for supporting both the convolution layer and the cross-correlation layer with high core utilization. Finally, the proposed VOT processor is implemented in 28 nm CMOS technology and occupies 0.42 mm(2). The proposed processor achieves 0.587 for the success rate and 0.778 for the precision in the OTB-100 dataset with SiamRPN++-AlexNet. Compared to previous VOT processors, the proposed processor shows state-of-the-art performance while showing lower power consumption. The proposed processor achieves 64.1 mW peak power and 58.2 mW tracking power consumption at 32.1 frame-per-second (fps) real-time VOT on mobile devices.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.titleA 64.1mW Accurate Real-Time Visual Object Tracking Processor With Spatial Early Stopping on Siamese Network-
dc.typeArticle-
dc.identifier.wosid000645863300024-
dc.identifier.scopusid2-s2.0-85103269922-
dc.type.rimsART-
dc.citation.volume68-
dc.citation.issue5-
dc.citation.beginningpage1675-
dc.citation.endingpage1679-
dc.citation.publicationnameIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS-
dc.identifier.doi10.1109/TCSII.2021.3067351-
dc.contributor.localauthorYoo, Hoi-Jun-
dc.contributor.nonIdAuthorKim, Soyeon-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorFeature extraction-
dc.subject.keywordAuthorIndexes-
dc.subject.keywordAuthorKernel-
dc.subject.keywordAuthorComputer architecture-
dc.subject.keywordAuthorReal-time systems-
dc.subject.keywordAuthorConvolution-
dc.subject.keywordAuthorSearch problems-
dc.subject.keywordAuthorDeep neural network-
dc.subject.keywordAuthorlow-power accelerators-
dc.subject.keywordAuthorsiamese network-
dc.subject.keywordAuthorvisual object tracking-
dc.subject.keywordAuthorvisual attention-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0