Training strategies for neural network soft classification of remotely-sensed imagery
作者:
A. C. Bernard,
G. G. Wilkinson,
I. Kanellopoulos,
期刊:
International Journal of Remote Sensing
(Taylor Available online 1997)
卷期:
Volume 18,
issue 8
页码: 1851-1856
ISSN:0143-1161
年代: 1997
DOI:10.1080/014311697218160
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
Recently the 'soft' classification approach has gained in popularity against the discrete (hard) classification of land cover from remotely-sensed imagery. An empirical study is presented to test training procedures with neural networks for soft (mixture) classification. The results show thatland cover mixtures are best recognized following training with two-component mixed pixels, and that linearly re-scaled or binned target vector representations are equally satisfactory. Interestingly, dominant classes within pixels are also better recognized by training with wider varieties of class mixtures.
点击下载:
PDF (150KB)
返 回