Image segmentation is the foundation of the object-based and automatic interpretation of remote sensing images , but the
high-resolution remote sensing image data is generally large, for this problem, the traditional approach is generally
processing in sub-block, and then merge the results, but because of the complexity of the nature object, the merging
result is not satisfied, and the segmentation algorithm is often more complex to calculate time-consuming, and it affect
the image automatic interpretation of real-time. In this paper, we propose a parallel segmentation algorithm based on
pyramid image, first of all, we create the pyramid image and segment it with the initial homogeneous regions were got, it
divide the data according to the initial homogeneous regions and segment them from the top of pyramid image to the
bottom with data parallelism, and it improve segmented efficiency, at the same time, it can avoid the problem of
“merging line” when merging of the segmenting results in different image block. Experimental results show that the
result of this algorithm is almost the same as the result of Mean Shift algorithm segmentation case; it says that this
algorithm is correct and reliability, it also shows that this algorithm is efficiency by comparing the use of time between
serial segmentation and parallel segmentation.
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.