DocumentCode
3219406
Title
Constructing a neural network for the interpretation of the species of trees in aerial photographs
Author
Pinz, Axel J. ; Bischof, Horst
Author_Institution
Inst. of Surveying & Remote Sensing, Univ of Agric., Wien, Austria
Volume
i
fYear
1990
fDate
16-21 Jun 1990
Firstpage
755
Abstract
A neural network with a three-layer feedforward architecture was used to interpret the species of trees in aerial photographs. Weight-visualization (WV) diagrams were developed to interpret the weights and the behavior of the hidden units easily. Several networks that were trained on different parameter settings were combined to construct a better-performing network using the WV diagrams as a tool
Keywords
biology computing; computerised pattern recognition; computerised picture processing; neural nets; aerial photographs; neural network; three-layer feedforward architecture; tree species interpretation; weight-visualisation diagrams; Agriculture; Degradation; Feedforward neural networks; Feeds; Humans; Intelligent networks; Neural networks; Remote sensing; Shape; Visualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location
Atlantic City, NJ
Print_ISBN
0-8186-2062-5
Type
conf
DOI
10.1109/ICPR.1990.118210
Filename
118210
Link To Document