Logo des Repositoriums
 

Acceleration of Optical Flow Computations on Tightly-Coupled Processor Arrays

Kurzanzeige
dc.contributor.authorSousa, Éricles
dc.contributor.authorTanase, Alexandru
dc.contributor.authorLari, Vahid
dc.contributor.authorHannig, Frank
dc.contributor.authorTeich, Jürgen
dc.contributor.authorPaul, Johny
dc.contributor.authorStechele, Walter
dc.contributor.authorKröhnert, Manfred
dc.contributor.authorAsfour, Tamin
dc.date.accessioned2017-12-06T09:07:46Z
dc.date.available2017-12-06T09:07:46Z
dc.date.issued2013
dc.description.abstractOptical flow is widely used in many applications of portable mobile devices and automotive embedded systems for the determination of motion of objects in a visual scene. Also in robotics, it is used for motion detection, object segmentation, time-to-contact information, focus of expansion calculations, robot navigation, and automatic parking for vehicles. Similar to many other image processing algorithms, optical flow processes pixel operations repeatedly over whole image frames. Thus, it provides a high degree of fine-grained parallelism which can be efficiently exploited on massively parallel processor arrays. In this context, we propose to accelerate the computation of complex motion estimation vectors on programmable tightly-coupled processor arrays, which offer a high flexibility enabled by coarse-grained reconfiguration capabilities. Novel is also that the degree of parallelism may be adapted to the number of processors that are available to the application. Finally, we present an implementation that is 18 times faster when compared to (a) an FPGA-based soft processor implementation, and (b) may be adapted regarding different QoS requirements, hence, being more flexible than a dedicated hardware implementation.en
dc.identifier.doi10.1007/BF03354240
dc.identifier.pissn0177-0454
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/8607
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofPARS: Parallel-Algorithmen, -Rechnerstrukturen und -Systemsoftware: Vol. 30, No. 1
dc.relation.ispartofseriesPARS: Parallel-Algorithmen, -Rechnerstrukturen und -Systemsoftware
dc.subjectOptical Flow
dc.subjectImage Processing Algorithm
dc.subjectHardware Cost
dc.subjectProcessor Array
dc.subjectProcessor Element
dc.titleAcceleration of Optical Flow Computations on Tightly-Coupled Processor Arraysen
dc.typeText/Journal Article
gi.citation.endPage89
gi.citation.startPage80

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
40731_2014_Article_BF03354240.pdf
Größe:
245.91 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

PARS-Mitteilungen 2013