Material classification through distance aware multispectral data fusion

Schwaneberg, Oliver (author): Bonn-Rhein-Sieg University of Applied Sciences, St. Augustin, Germany,Department of Computer Science

Köckemann, Uwe (author): Bonn-Rhein-Sieg University of Applied Sciences, St. Augustin, Germany,Department of Computer Science

Steiner, Holger (author): Bonn-Rhein-Sieg University of Applied Sciences, St. Augustin, Germany,Department of Computer Science

Sporrer, S. (author): Bonn-Rhein-Sieg University of Applied Sciences, St. Augustin, Germany

Kolb, Andreas (author): University of Siegen, Siegen, Germany,Computer Graphics and Multimedia Systems Group, Institute for Vision and Graphics

Jung, Norbert (author): Bonn-Rhein-Sieg University of Applied Sciences, St. Augustin, Germany,Department of Computer Science

Bonn-Rhein-Sieg University of Applied Sciences, St Augustin, Germany Department of Computer Science (creator_code:org_t)

2013-02-22
2013
English.
In: Measurement science and technology. - Bristol, United Kingdom : Institute of Physics (IOP). - 0957-0233 .- 1361-6501. ; 24:4

Related links:: https://urn.kb.se/re...; show more...; https://doi.org/10.1...; show less...

Abstract Subject headings

Safety applications require fast, precise and highly reliable sensors at low costs. This paperpresents signal processing methods for an active multispectral optical point sensorinstrumentation for which a first technical implementation exists. Due to the very demandingrequirements for safeguarding equipment, these processing methods are targeted to run on asmall embedded system with a guaranteed reaction time T < 2 ms and a sufficiently lowfailure rate according to applicable safety standards, e.g., ISO-13849. The proposed dataprocessing concept includes a novel technique for distance-aided fusion of multispectral datain order to compensate for displacement-related alteration of the measured signal. Thedistance measuring is based on triangulation with precise results even for low-resolutiondetectors, thus strengthening the practical applicability. Furthermore, standard components,such as support vector machines (SVMs), are used for reliable material classification. Allmethods have been evaluated for variants of the underlying sensor principle. Therefore, theresults of the evaluation are independent of any specific hardware.

By the author/editor: Schwaneberg, Oli ...; Köckemann, Uwe; Steiner, Holger; Sporrer, S.; Kolb, Andreas; Jung, Norbert

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Science ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.