Classification of lidar waveforms by neural networks

Author

Bhattacharya, D. ; Pillai, R. ; Antoniou, A.

Author_Institution

Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada

Volume

3

fYear

1996

fDate

12-15 May 1996

Firstpage

309

Abstract

A neural network scheme for the classification of lidar waveforms for the LARSEN 500 airborne system is proposed. It uses a single layer of linear neurons for classification of waveforms containing milt of various densities into a number of clusters. Both unsupervised and supervised learning algorithms have been employed to demonstrate the spatial distribution of milt in near-shore waters. The spatial distribution of waveforms obtained from real-world data provided by the LARSEN 500 system was found to be consistent with that obtained from observed data

Keywords

aquaculture; geophysical signal processing; learning (artificial intelligence); neural nets; oceanographic techniques; optical radar; pattern classification; remote sensing by laser beam; unsupervised learning; LARSEN 500 airborne system; clusters; fish population; lidar waveform classification; linear neurons; near-shore waters; neural network scheme; sea-bed topography; spatial distribution; supervised learning algorithms; unsupervised learning algorithms; Clustering algorithms; Laser radar; Marine animals; Marine technology; Neural networks; Neurons; Oceans; Optical pulses; Optical reflection; Sea measurements;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1996. ISCAS '96., Connecting the World., 1996 IEEE International Symposium on

Conference_Location

Atlanta, GA

Print_ISBN

0-7803-3073-0

Type

conf

DOI

10.1109/ISCAS.1996.541595

Filename

541595