Timing-Predictable Vision Processing for Autonomous Systems

Tanya Amert, Michael Balszun, Martin Geier, F. Donelson Smith, James H. Anderson, Samarjit Chakraborty

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

2 Zitate (Scopus)

Abstract

Vision processing for autonomous systems today involves implementing machine learning algorithms and vision processing libraries on embedded platforms consisting of CPUs, GPUs and FPGAs. Because many of these use closed-source proprietary components, it is very difficult to perform any timing analysis on them. Even measuring or tracing their timing behavior is challenging, although it is the first step towards reasoning about the impact of different algorithmic and implementation choices on the end-to-end timing of the vision processing pipeline. In this paper we discuss some recent progress in developing tracing, measurement and analysis infrastructure for determining the timing behavior of vision processing pipelines implemented on state-of-the-art FPGA and GPU platforms.

OriginalspracheEnglisch
TitelProceedings of the 2021 Design, Automation and Test in Europe, DATE 2021
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten1739-1744
Seitenumfang6
ISBN (elektronisch)9783981926354
DOIs
PublikationsstatusVeröffentlicht - 1 Feb. 2021
Extern publiziertJa
Veranstaltung2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021 - Virtual, Online
Dauer: 1 Feb. 20215 Feb. 2021

Publikationsreihe

NameProceedings -Design, Automation and Test in Europe, DATE
Band2021-February
ISSN (Print)1530-1591

Konferenz

Konferenz2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021
OrtVirtual, Online
Zeitraum1/02/215/02/21

Fingerprint

Untersuchen Sie die Forschungsthemen von „Timing-Predictable Vision Processing for Autonomous Systems“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren