| Attributes | Values |
|---|
| rdf:type
| |
| Description
| - Populárním trendem v detekci objektů a rozpoznání vzorů je použití statistických klasifikátorů, zejména AdaBoost and jeho modifikací. Rychlost výpočtu těmito klasifikátory do značné míry závisí na nizkoúrovňových příznacích získaných z obrazu, které klasifikátor využívá: jak na množství informace obsažené v příznaku, tak na výpočetní náročnosti příznaků. Local Rank Differences je obrazový příznak, který je alternativou k obvykle používaným haarovým vlnkám. Je vhodný pro implementaci v programovatelném (FPGA) i specializovaném (ASIC) hardwaru, ale - jak je ukázáno v článku - má velice dobré vlastnosti i na grafickém hardware (GPU). Článek diskutuje příznak LRD, jeho vlastnosti, popisuje experimentální implementaci LRD v grafickém hardware, prezentuje empirické vyhodnocení jeho výkonu ve srovnání s alternativními přístupy, přináší některá doporučení k praktickému použití LRD a navrhuje možnosti dalšího vývo (cs)
- A currently popular trend in object detection and pattern recognition is usage of statistical classifiers, namely AdaBoost and its modifications. The speed performance of these classifiers largely depends on the low level image features they are using: both on the amount of information the feature provides and the executional time of its evaluation. Local Rank Differences is an image feature that is alternative to commonly used haar wavelets. It is suitable for implementation in programmable (FPGA) or specialized (ASIC) hardware, but - as this paper shows - it performs very well on graphics hardware (GPU) as well. The paper discusses the LRD features and their properties, describes an experimental implementation of LRD in graphics hardware, presents its empirical performance measures compared to alternative approaches and suggests several notes on practical usage of LRD and proposes directions for future work.
- A currently popular trend in object detection and pattern recognition is usage of statistical classifiers, namely AdaBoost and its modifications. The speed performance of these classifiers largely depends on the low level image features they are using: both on the amount of information the feature provides and the executional time of its evaluation. Local Rank Differences is an image feature that is alternative to commonly used haar wavelets. It is suitable for implementation in programmable (FPGA) or specialized (ASIC) hardware, but - as this paper shows - it performs very well on graphics hardware (GPU) as well. The paper discusses the LRD features and their properties, describes an experimental implementation of LRD in graphics hardware, presents its empirical performance measures compared to alternative approaches and suggests several notes on practical usage of LRD and proposes directions for future work. (en)
|
| Title
| - %22Local Rank Differences%22 Image Faeture Implemented on GPU
- Obrazový příznak %22Local Rank Differences%22 implementován na GPU (cs)
- %22Local Rank Differences%22 Image Faeture Implemented on GPU (en)
|
| skos:prefLabel
| - %22Local Rank Differences%22 Image Faeture Implemented on GPU
- Obrazový příznak %22Local Rank Differences%22 implementován na GPU (cs)
- %22Local Rank Differences%22 Image Faeture Implemented on GPU (en)
|
| skos:notation
| - RIV/00216305:26230/08:PU76793!RIV09-GA0-26230___
|
| http://linked.open...avai/riv/aktivita
| |
| http://linked.open...avai/riv/aktivity
| - P(GA201/06/1821), P(LC06008), Z(MSM0021630528)
|
| http://linked.open...vai/riv/dodaniDat
| |
| http://linked.open...aciTvurceVysledku
| |
| http://linked.open.../riv/druhVysledku
| |
| http://linked.open...iv/duvernostUdaju
| |
| http://linked.open...titaPredkladatele
| |
| http://linked.open...dnocenehoVysledku
| |
| http://linked.open...ai/riv/idVysledku
| - RIV/00216305:26230/08:PU76793
|
| http://linked.open...riv/jazykVysledku
| |
| http://linked.open.../riv/klicovaSlova
| - local rank differences, object detection, pattern recognition, hardware acceleration<br> (en)
|
| http://linked.open.../riv/klicoveSlovo
| |
| http://linked.open...ontrolniKodProRIV
| |
| http://linked.open...v/mistoKonaniAkce
| |
| http://linked.open...i/riv/mistoVydani
| |
| http://linked.open...i/riv/nazevZdroje
| - Advanced Concepts for Intelligent Vision Systems
|
| http://linked.open...in/vavai/riv/obor
| |
| http://linked.open...ichTvurcuVysledku
| |
| http://linked.open...cetTvurcuVysledku
| |
| http://linked.open...vavai/riv/projekt
| |
| http://linked.open...UplatneniVysledku
| |
| http://linked.open...iv/tvurceVysledku
| - Herout, Adam
- Juránek, Roman
- Zemčík, Pavel
- Jošth, Radovan
- Hradiš, Michal
|
| http://linked.open...vavai/riv/typAkce
| |
| http://linked.open.../riv/zahajeniAkce
| |
| http://linked.open...n/vavai/riv/zamer
| |
| issn
| |
| number of pages
| |
| http://purl.org/ne...btex#hasPublisher
| |
| http://localhost/t...ganizacniJednotka
| |
![[RDF Data]](/fct/images/sw-rdf-blue.png)
![[cxml]](/fct/images/cxml_doc.png)
![[csv]](/fct/images/csv_doc.png)
![[text]](/fct/images/ntriples_doc.png)
![[turtle]](/fct/images/n3turtle_doc.png)
![[ld+json]](/fct/images/jsonld_doc.png)
![[rdf+json]](/fct/images/json_doc.png)
![[rdf+xml]](/fct/images/xml_doc.png)
![[atom+xml]](/fct/images/atom_doc.png)
![[html]](/fct/images/html_doc.png)