The influence of autocorrelation in signature extraction—an example from a geobotanical investigation of Cotter Basin, Montana
作者:
M. L. LABOVITZ,
E. J. MASUOKA,
期刊:
International Journal of Remote Sensing
(Taylor Available online 1984)
卷期:
Volume 5,
issue 2
页码: 315-332
ISSN:0143-1161
年代: 1984
DOI:10.1080/01431168408948811
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
The presence of positive serial correlation (autocorrelation) in remotely sensed data results in an underestimate of the variance-covariance matrix when calculated using contiguous pixels. This underestimate produces an inflation inFstatistics. For a set of Thematic Mapper Simulator data (TMS), used to test the ability to discriminate a known geobotanical anomaly from its background, the inflation inFstatistics related to serial correlation is between 7 and 70 times. This means that significance tests of means of the special bands initially appear to suggest that the anomalous site is very different in spectral reflectance and emitance from its background sites. However, this difference often disappears and is always dramatically reduced when compared to frequency distributions of test statistics produced by the comparison of simulated training sets possessing equal means, but which are composed of autocorrelated observations.
点击下载:
PDF (545KB)
返 回