(A) real-time optical flow estimation processor for action recognition in mobile devices모바일 기기에서의 행동인식을 위한 실시간 광류 추정 프로세서

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 491
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorYoo, Hoi-Jun-
dc.contributor.advisor유회준-
dc.contributor.authorLee, Juhyoung-
dc.date.accessioned2019-09-04T02:43:07Z-
dc.date.available2019-09-04T02:43:07Z-
dc.date.issued2019-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843416&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/266859-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[iii, 21 p. :]-
dc.description.abstractA 99.4 fps optical flow estimation (OFE) processor with image tiling is proposed for action recognition in mobile devices. The OFE is essential for the high action recognition accuracy. However, it is unsuitable for real-time constraint in a mobile computing environment because it requires a huge amount of external memory accesses (EMAs) and matrix computations. For mitigating the external memory bandwidth requirement, this paper proposes the tile-based hierarchical OFE. It divides input images into several tiles and enables intermediate data reusing with 326.4 KB on-chip memory and 175.8 MB/s external memory bandwidth. Moreover, a background decision unit with early termination is proposed to reduce computation workload. It gets rid of unnecessary matrix computation by terminates the computation early for zero optical flow region. As a result, the proposed features reduce external memory bandwidth by 99.3 % and increase throughput by 50.7 %, respectively. The proposed $12.8 mm^2$ OFE processor is implemented in 65 nm CMOS technology, and it achieves the real-time OFE with 99.4 frames-per-second (fps) throughput for an image resolution of QVGA (320 × 240).-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectOptical flow estimation▼aaction recognition▼atile-based processing▼aearly termination▼ahigh throughput ASIC-
dc.subject광류 추정▼a행동 인식▼a타일 기반 처리▼a조기 종료▼a고처리량 ASIC-
dc.title(A) real-time optical flow estimation processor for action recognition in mobile devices-
dc.title.alternative모바일 기기에서의 행동인식을 위한 실시간 광류 추정 프로세서-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
dc.contributor.alternativeauthor이주형-
Appears in Collection
EE-Theses_Master(석사논문)
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