Remote sensing image based on the complexity of the background features, has a wealth of spatial information, how to
extract huge amounts of data in the region of interest is a serious problem. Image segmentation refers to certain
provisions in accordance with the characteristics of the image into different regions, and it is the key of remote sensing
image recognition and information extraction. Reasonably fast image segmentation algorithm is the base of image
processing; traditional segmentation methods have a lot of the limitations. Traditional threshold segmentation method in
essence is an ergodic process, the low efficiency impacts on its application. The ant colony algorithm is a populationbased
evolutionary algorithm heuristic biomimetic, since proposed, it has been successfully applied to the TSP, job-shop
scheduling problem, network routing problem, vehicle routing problem, as well as other cluster analysis. Ant colony
optimization algorithm is a fast heuristic optimization algorithm, easily integrates with other methods, and it is robust.
Improved ant colony algorithm can greatly enhance the speed of image segmentation, while reducing the noise on the
image. The research background of this paper is land cover classification experiments according to the SPOT images of
Qinling area. The image segmentation based on ant colony algorithm is carried out and compared with traditional
methods. Experimental results show that improved the ant colony algorithm can quickly and accurately segment target,
and it is an effective method of image segmentation, it also has laid a good foundation of image classification for the
follow-up work.
Linear features are usually extracted from SAR imagery by a few edge detectors derived from the contrast ratio edge
detector with a constant probability of false alarm. On the other hand, the Hough Transform is an elegant way of
extracting global features like curve segments from binary edge images. Randomized Hough Transform can reduce the
computation time and memory usage of the HT drastically. While Randomized Hough Transform will bring about a
great deal of cells invalid during the randomized sample. In this paper, we propose a new approach to extract linear
features on SAR imagery, which is an almost automatic algorithm based on edge detection and Randomized Hough
Transform. The presented improved method makes full use of the directional information of each edge candidate points
so as to solve invalid cumulate problems. Applied result is in good agreement with the theoretical study, and the main
linear features on SAR imagery have been extracted automatically. The method saves storage space and computational
time, which shows its effectiveness and applicability.
KEYWORDS: Geographic information systems, Decision support systems, Computer programming, Databases, Remote sensing, Agriculture, Data modeling, Roads, Global Positioning System, Geography
Tobacco enterprise is a special enterprise, which has strong correlation to regional geography. But in the past research and application, the combination between tobacco and GIS is limited to use digital maps to assist cigarette distribution. How to comprehensively import 3S technique taking GIS as representation to construct spatial decision support system of tobacco enterprise is the main research aspect in this paper. The paper concretely analyzes the GIS requirements in tobacco enterprise for planning location of production, monitoring production management and product sale at the beginning. Then holistic solution is presented and frame design for tobacco enterprise spatial decision is given. At last the example of tobacco enterprise spatial CRM (client relation management) system is set up.
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.