Texture feature of image is one of the most important factors in the processing
of information extraction from satellite scene image. In this paper the texture feature
analysis was introduced in the processing of the classification of the objects in coastal
zone. During the texture analysis process, how to extract effectively the texture features is
the key factor. In the experiment of coastal classification, this paper introduced a method
of a set of texture features selection based on step-by-step discriminance. Texture is
described by Gray level co-occurrence matrix in this study, and there are 192 texture
features to describe the characteristics of coastal objects. With the features selection
method presented by this paper, five values were chosen as the representatives to classify
the object texture feature. By means of the neural networks the object classification mode
based on the texture features was defined and the object classifications of the southern
coast of Laizhou Bay were carried out. Results show the step-by-step discriminance not
only can decrease the dimension of the texture feature database, but also ensure and
improve the accuracy of the classification, and the classification accuracy was up to
83.4%. The neural networks mode is the most effective method to account for the
classification of the typical objects in coastal zone.
Shallow water depth extraction by remote sensing is an important research. Optical remote sensing can provide an
alternative means for obtaining bathymetric data in areas where a traditional hydrographic survey may be difficult to
obtain. IKONOS imagery can perform an important function in shallow water depth extraction because of its ability to
provide data within three unique portions of the visible spectrum as well as a high spatial resolution of roughly four
meters. But experiments indicated that, the bathymetric precision of high-resolution imagery is much lower than that of
mid-resolution imagery such as TM imagery. In this paper, the affect factors of bathymetric precision of high-resolution
imagery are presented. Moreover, on the basis of the conventional multi-band linear regression model , we develop an
improved model by introducing a series of techniques including data processing by group averaging, image smooth,
piece wise linear regression, data normalization, etc.. The improved model is more reasonable and accurate and suitable
for high-resolution imagery. Using this improved mode, the shallow underwater topography of Dong-Sha Islands and
nearby sea area is detected by IKONOS image. The results have preferable precision.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.