DocumentCode :
786381
Title :
Application of neural networks to AVHRR cloud segmentation
Author :
Yhann, Stephan R. ; Simpson, James J.
Author_Institution :
Digital Image Anal. Lab., California Univ., San Diego, La Jolla, CA, USA
Volume :
33
Issue :
3
fYear :
1995
fDate :
5/1/1995 12:00:00 AM
Firstpage :
590
Lastpage :
604
Abstract :
The application of neural networks to cloud screening of AVHRR data over the ocean is investigated. Two approaches are considered, interactive cloud screening and automated cloud screening. In interactive cloud screening a neural network is trained on a set of data points which are interactively selected from the image to be screened. Because the data variability is limited within a single image, a very simple neural network topology is sufficient to generate an effective cloud screen. Consequently, network training is very quick and only a few training samples are required. In automated cloud screening, where a general network is designed to handle all images, the data variability can be significant and the resulting neural network topology is more complex. The latitudinal, seasonal and spatial dependence of cloud screening large AVHRR data sets is studied using an extensive data set spanning 7 years. A neural network and associated feature set are designed to cloud screen this data set. The sensitivity of the thermal infrared bands to high atmospheric water vapor concentration was found to limit the accuracy of cloud screening methods which rely solely on data from these channels. These limitations are removed when the visible channel data is used in combination with the thermal infrared data. A post processing algorithm is developed to improve the cloud screening results of the network in the presence of high atmospheric water vapor concentration. Post processing also is effective in identifying pixels contaminated by subpixel clouds and/or amplifier hysteresis effects at cloud-ocean boundaries. The neural network, when combined with the post processing algorithm, produces accurate cloud screens for the large, regionally distributed AVHRR data set
Keywords :
clouds; feedforward neural nets; geophysical signal processing; geophysical techniques; geophysics computing; image processing; image segmentation; infrared imaging; oceanographic techniques; remote sensing; AVHRR cloud segmentation; automated method; cloud screening; geophysical measurement technique; image processing; interactive cloud screening; land surface terrain mapping; marine atmosphere; meteorology; neural net; neural network; ocean SST; optical imaging; patter recognition; post processing algorithm; remote sensing; sea surface temperature; training; visible infrared IR method; Clouds; Hysteresis; Image analysis; Image segmentation; Network topology; Neural networks; Ocean temperature; Satellite broadcasting; Sea surface; Water pollution;
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
Publisher :
ieee
ISSN :
0196-2892
Type :
jour
DOI :
10.1109/36.387575
Filename :
387575
Link To Document :
بازگشت