DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yang, Hyun-Seung | - |
dc.contributor.advisor | 양현승 | - |
dc.contributor.author | Lee, Su-Won | - |
dc.contributor.author | 이수원 | - |
dc.date.accessioned | 2013-09-12T01:49:23Z | - |
dc.date.available | 2013-09-12T01:49:23Z | - |
dc.date.issued | 2012 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=509484&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/180466 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학과, 2012.8, [ iv, 27 p. ] | - |
dc.description.abstract | In many applications which require real-time keypoint recognition such as Augmented Reality, Random Ferns (RF) is widely used due to its runtime performance. It relies on an offline training phase during which runtime computational burdens are delegated. This leads to robust, accurate, and frame-rate performance. However, it requires significant amounts of memory, and this has been an obstacle to its use in industry, especially in mobile environments. In this paper, I propose Lightweight Random Ferns to reduce the memory requirements of RF by modifying the representation of probabilities used in ferns to a single bit from floating point. As a result, the total memory requirements of RF are significantly reduced. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | random ferns | - |
dc.subject | binary representation | - |
dc.subject | 랜덤펀스 | - |
dc.subject | 이진화 표현 | - |
dc.subject | 경량화된 랜덤펀스 | - |
dc.subject | lightweight random ferns | - |
dc.title | Lightweight random ferns using binary representation | - |
dc.title.alternative | 이진화 표현을 이용한 경량화된 랜덤펀스 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 509484/325007 | - |
dc.description.department | 한국과학기술원 : 전산학과, | - |
dc.identifier.uid | 020104387 | - |
dc.contributor.localauthor | Yang, Hyun-Seung | - |
dc.contributor.localauthor | 양현승 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.