Magenta
residential area
vegetable plot
130.7625
7
3
115.3787
Blue
residential area
glebe
5.0828
2
0
0
Cyan
paddy field
residential area
61.8504
4
2
55.5003
Green
glebe
vegetable plot
1041.4520
9
3
698.4803
I
29437.7717
312
21
1265.8236
Table 2 the results of the change detection in land use
From the above experiment results, we can know that the
monitoring results of land use changing could not only rely on
the analysis results of computer, and should integrate with
manual optical interpretation. It is the better effective method
for now to extract the land use changing information utilizing
the computer automatic processing and the manual optical
interpretation.
5. CONCLUSION
This paper utilizes the Maximum Likelihood Classification into
the SPOT5 multi-spectral image, and obtains a better classified
effect. The calculated total classification precision is
86.20%,and the Kappa coefficient is 0.8275. According to the
classification results, this paper researches a remote sensing
changing detection method based on the land use vector graph.
This method uses the vector frame attribute of the land
utilization chart, meanwhile carries on a very good use of its
category attribute. Additionally this method also avoids the
effects caused by the different sensors of satellites, the
incidence angles in imaging, and so on. And this method fully
excavates the various attributes of the land utilization vector
chart, then participates the category attributes of land utilization
chart into the change detection, and obtains the comparatively
high accuracy monitor results.
ACKNOWLEDGEMENTS
Our research project was supported by the “Excellent Youth
Research Fund Program of Liaoning Technical University
(N0.O6AOI)”, and the “Open Research Fund Program of the
Geomatics and Applications Laboratory of Liaoning Technical
University (No. 2006008)”.
REFERENCES
1. Zeng Zhiyuan, 2004. Computer Classification and
Geoscience Applied Research of Satellite Remote Sensing
Image. Publishing House of Science, Beijing.
2. Tang Guoan, et al, 2004. Remote Sensing Digital Image
Processing. Publishing House of Science, Beijing.
3. Qin Yong, 2005. Feature extraction and selection and
Application in the RS Image Classification. Liaoning Technical
University Master Dissertation.
4. Hu Peng et al, 2003. Geographic Information System
Tutorial. Publishing House of Wuhan University, Wuhan.
5. Li Xiangjun, 2006. Study on Remote Sensing Land use
Change Detection Methods. CAS Institute of Graduate Student
Ph.D Dissertation. 6
6. Ding Yuan, Chris Elvidge, 1998. NALC Land Cover Change
Detection Pilot study: Washington D. C. Area Experiments,
Remote Sensing of Environment. (66): 166-178.
246