Image segmentation is essential for information extraction from remote sensing image, but it remains the lacks of a
general mathematical theory, object merging for poor object boundary localization, dealing with object fragmentation
and sensitivity of current procedures to noise. This paper focuses on hyper-spectral image segmentation using
probabilistic neural networks (PNN). The methodology, implementation and optimization of a PNN are studied, and a
constructed PNN is applied to segment hyper-spectral image. The experience demonstrates main advantage of a PNN
that it has quick training and learning, gives a measurement of confidence associated with an output, and has the ability
to process large data set. It is concluded that the PNN is superior in image segmentation and the obtained results are
satisfied.
This study put forward an integrated evaluation model. Bases on a framework of fuzzy set theory and entropy theory, we firstly complete the classification using fuzzy surveillance approach, taking it as a formalized description of classification uncertainty. Then introduce hybrid entropy model for classification uncertainty evaluation, which can meet the requirement of comprehensive reflection of both random and fuzzy uncertainty, meanwhile construct evaluation index from pixel scale with the full consideration of different contribution to error rate of each pixel. Finally, we use such method to evaluate land-use classification result of remote sensing image, which is in Huangshi city, Hubei province of China, by using hybrid entropy evaluation model, the classification quality can be fully reflected, and pixelscale evaluation indexes were easier constructed.
The geological survey was used to a common method before, in which the representation form of the survey results also was very old, especially aspects of location distributing, growth dimensions for hazard bodies, etc. It is thought a lack of veracity in work. This paper, by the geological hazards survey in Fengjie-Badong sect (case study) regarded as an example, illuminates to be capable of rightly drawing the size and position of hazard bodies with application of satellite remote sensing technology and assistant aerial images. It will most important for externally showing the status of geological hazard growth and for truly expressing the disserving of the whole Sanxia immigrant project caused by geological hazard. This remote sensing application has established foundation for carrying through geological hazard survey in the whole Sanxia reservoir areas.
Image fusion is a very useful technique of obtaining high-resolution multi-spectral images from low spatial resolution multi-spectral and high-resolution panchromatic images. Nowadays many fusion techniques are available. However, those conventional fusion techniques existed also some shortcomings, which could not keep balance for preserving spectral information very well in a fused image with high-resolution spatial information. Hence, in this research a recent and efficient technique of fusion based on wavelet transformation was applied. The results presented the wavelet transform method is proved to be the best option for visual appreciation, preserving most 93% of the spectral information content, and as well improving the interpretability of low-resolution multi-spectral image classification. Meanwhile the results also further show the application potentiality of fusion technique based on wavelet transform for improving urban land classes in urban fringe.
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.