The Intelligent Classifier’s Building of Typical Vegetation Based on Hyper-Spectral Data

Jie Zhang; Hao Yan Zhao; Min Xia Zhang

doi:10.4028/www.scientific.net/AMR.1073-1076.1972

Paper Titles

Topological Relations between Rivers in Updating Increments
p.1950

Model Establishment Based on Cultivated Land Quality of WebGIS Provincial Level Management Information System Evaluation
p.1955

Study on the Intelligent Extraction Based on Hyper-Spectral Characteristics of Typical Vegetation
p.1960

Study on Tourism Climate Comfort Level in East China Based on GIS
p.1965

The Intelligent Classifier’s Building of Typical Vegetation Based on Hyper-Spectral Data
p.1972

Design and Research of Multiple Data Channels in Solid State Recorder of the Satellite SJ-10
p.1977

Coefficient Feature Extraction and Analysis on SAR Image with Non-Subsampled Contourlet Transform
p.1982

Dynamics of Rift-Opening Calving Dominant Ice Shelves and the Analysis of its Influencing Factors
p.1987

Study on Degradation Mechanism of Stress in Generation Process of Coal-Bed Methane
p.1995

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 1073-1076The Intelligent Classifier’s Building of Typical...

The Intelligent Classifier’s Building of Typical Vegetation Based on Hyper-Spectral Data

Abstract:

With 3S comprehensive analysis on vegetation and the further development of hyper-spectral technology, the dynamic monitor of large area vegetation in long-term has become the trend. Intelligent process, combined the remote sensing data and field data, constructing dynamic monitoring model, plays an important guilding role in ecological security and balance. By using hyper-spectral remote sensing data of desert vegetation, three groups of spectral characteristic parameters were selected as input data of typical desert vegetation in the research, and vegetation types were selected as output data. Typical vegetation classifier was constructed based on the BP neural network model to study the vegetation classification.

You might also be interested in these eBooks

Environmental Protection and Resource Utilization IV

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 1073-1076)

Pages:

1972-1976

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1073-1076.1972

Citation:

Cite this paper

Online since:

December 2014

Authors:

Jie Zhang*, Hao Yan Zhao, Min Xia Zhang

Keywords:

BP Neural Network, Hyper-Spectral Characteristics Extraction, Narrow Spectral

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Paruelo J.M., Golluscio R.A. Range assessment using remote sensing in Northwest Patagonia (Argentina). Journal of Range Management, 1994, 47(6): 498-5021.

DOI: 10.2307/4003005

Google Scholar

[2] Wessman C.A. Imaging spectrometry for remote sensing of eco-system processing. Advances in Space Research, 1992, 12(7): 361-368.

DOI: 10.1016/0273-1177(92)90241-o

Google Scholar

[3] Prince S.D., Astle W.L. Satellite remote sensing of rangelands in Botswama I: Landsat MSS and herbaceous vegetation. International Journal of Remo te Sensing, 1986, 7(11): 1533-1553.

DOI: 10.1080/01431168608948952

Google Scholar

[4] Qian Y., Li J., Yang F. et al. Retrieval of Photosynthetic Pigment Concentration in Festuca arundinacea from Canopy-Scale Reflectance Spectra Using Wavelet Analysis. 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, v4, P1-5.

DOI: 10.1109/csie.2009.31

Google Scholar

[5] Takahata S., Osman A.E. Analysis of rangeland vegetation using remote sensing. Research Highlight-Tropical Agriculture Research Center[C]. 1992: 30-33.

Google Scholar