Neural Object Classification Using Ultrasonic Spectrum Analysis

Klahold J, Jürgens H, Rückert U (2003)
In: Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE). Brisbane, Australia: 219-228.

Conference Paper | Published | English

No fulltext has been uploaded

Author
; ;
Abstract
This paper describes how reflected broadband sound signals are marked by interference phenomena if the surface of the ensonified object is structured. For an efficient extraction of features of the signal that relate to the surface structure of the object, the calculation of the cepstrum is introduced. A cylindrical test object is presented, which shows an angle independent and an angle dependent structure. This allows to specify the accuracy of the discrimination of structure sizes, that is based on a selected part of the cepstrum. In addition, the object can be used as a landmark for ultrasonic sensing. Classification of the cepstra is done by the statistical ‘One Nearest Neighbour’ (1NN) method as well as by a ‘Kohonen Self-Organising Feature Map’ (SOM). The results show, that changes in structure size down to 0.1mm are detectable.
Publishing Year
PUB-ID

Cite this

Klahold J, Jürgens H, Rückert U. Neural Object Classification Using Ultrasonic Spectrum Analysis. In: Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE). Brisbane, Australia; 2003: 219-228.
Klahold, J., Jürgens, H., & Rückert, U. (2003). Neural Object Classification Using Ultrasonic Spectrum Analysis. Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE), 219-228.
Klahold, J., Jürgens, H., and Rückert, U. (2003). “Neural Object Classification Using Ultrasonic Spectrum Analysis” in Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE) (Brisbane, Australia), 219-228.
Klahold, J., Jürgens, H., & Rückert, U., 2003. Neural Object Classification Using Ultrasonic Spectrum Analysis. In Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE). Brisbane, Australia, pp. 219-228.
J. Klahold, H. Jürgens, and U. Rückert, “Neural Object Classification Using Ultrasonic Spectrum Analysis”, Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE), Brisbane, Australia: 2003, pp.219-228.
Klahold, J., Jürgens, H., Rückert, U.: Neural Object Classification Using Ultrasonic Spectrum Analysis. Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE). p. 219-228. Brisbane, Australia (2003).
Klahold, Jürgen, Jürgens, Hartmut, and Rückert, Ulrich. “Neural Object Classification Using Ultrasonic Spectrum Analysis”. Proceedings of the 2nd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE). Brisbane, Australia, 2003. 219-228.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar