Neural Network-Based Detection of Ultrasonic Targets with Respect to Noise and Number of Sampling Positions

Kroh P, Simon R, Rupitsch S (2019)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2019

Pages Range: 1870 - 1873

Conference Proceedings Title: 2019 IEEE International Ultrasonics Symposium (IUS)

Event location: Glasgow, Scotland, UK GB

ISBN: 978-1-7281-4596-9

URI: https://ieeexplore.ieee.org/document/8926202

DOI: 10.1109/ULTSYM.2019.8926202

Abstract

A neural network-based approach for detection of sonar targets in air is presented in this contribution. Our approach may facilitate autonomous mobile systems to reliably detect and classify objects in their surrounding by using sonar information. This task might be extremely important in changing as well as unorganized environments. We perform target identification with long short-term memory networks as classifiers. Such are capable of dealing with variable numbers of echoes from multiple positions per input sequence, which facilitates more flexible operation. The impact of the number of recording positions per sequence and of noise is investigated. Furthermore, we demonstrate the improvement in classification performance in comparison to previously obtained results from multilayer perceptrons.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Kroh, P., Simon, R., & Rupitsch, S. (2019). Neural Network-Based Detection of Ultrasonic Targets with Respect to Noise and Number of Sampling Positions. In IEEE (Eds.), 2019 IEEE International Ultrasonics Symposium (IUS) (pp. 1870 - 1873). Glasgow, Scotland, UK, GB.

MLA:

Kroh, Patrick, Ralph Simon, and Stefan Rupitsch. "Neural Network-Based Detection of Ultrasonic Targets with Respect to Noise and Number of Sampling Positions." Proceedings of the 2019 IEEE International Ultrasonics Symposium (IUS), Glasgow, Scotland, UK Ed. IEEE, 2019. 1870 - 1873.

BibTeX: Download