DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jun-Seok | ko |
dc.contributor.author | Kim, Hyo-Eun | ko |
dc.contributor.author | Kim, Lee-Sup | ko |
dc.date.accessioned | 2013-08-08T06:01:03Z | - |
dc.date.available | 2013-08-08T06:01:03Z | - |
dc.date.created | 2012-09-19 | - |
dc.date.created | 2012-09-19 | - |
dc.date.issued | 2013-05 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, v.23, no.5, pp.832 - 845 | - |
dc.identifier.issn | 1051-8215 | - |
dc.identifier.uri | http://hdl.handle.net/10203/174755 | - |
dc.description.abstract | A pattern-matching based image recognition accelerator (PRA) is presented for embedded vision applications. It is a hardware accelerator that performs interest point detection and matching for image-based recognition applications in real time in both mobile devices and vehicles. The proposed system is implemented as a small IP, and it has eight times higher throughput than state-of-the-art object recognition processors, which are implemented based on a heterogeneous many-core system. PRA has three key features: 1) joint algorithm-architecture optimizations for exploiting bit-level parallelism; 2) a low-power unified hardware platform for interest point detection and matching; and 3) scalable hardware architecture. PRA achieves 9.5x performance improvement with only 30% of logic gates including static random-access memory (SRAM) compared to the state-of-the-art object recognition processors. It consists of 78.3 k logic gates and 128 kB SRAM, which are integrated in a test chip implemented for PRA verification. It achieves 94.3 frames per second (fps) in 1080p full HD resolution at 200-MHz operating frequency while consuming 182mW. Each complete operation for interest point detection and matching requires 2.09 cycles and 8 cycles on average, respectively, based on a unified bit-level matching accelerator, which is implemented only with 680 logic gates. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | ALGORITHM | - |
dc.subject | FEATURES | - |
dc.title | A 182mW 94.3 f/s in Full HD Pattern-Matching Based Image Recognition Accelerator for an Embedded Vision System in 0.13-mu m CMOS Technology | - |
dc.type | Article | - |
dc.identifier.wosid | 000318697600008 | - |
dc.identifier.scopusid | 2-s2.0-84877296740 | - |
dc.type.rims | ART | - |
dc.citation.volume | 23 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 832 | - |
dc.citation.endingpage | 845 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY | - |
dc.identifier.doi | 10.1109/TCSVT.2012.2223873 | - |
dc.contributor.localauthor | Kim, Lee-Sup | - |
dc.contributor.nonIdAuthor | Park, Jun-Seok | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Interest point detection | - |
dc.subject.keywordAuthor | interest point matching | - |
dc.subject.keywordAuthor | scalable hardware architecture | - |
dc.subject.keywordAuthor | unified hardware platform | - |
dc.subject.keywordPlus | ALGORITHM | - |
dc.subject.keywordPlus | FEATURES | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.