Research on the SVM Classification of Active and Passive Remote Sensing Data Based on the Feature Per-Parcel

Shuang Ting Wang; Chun Lai Wang; Wei Bing Du; Le Le Tong; Fei Wang

doi:10.4028/www.scientific.net/AMM.405-408.3001

Paper Titles

Numerical Simulation Analysis of Composite Air Purifying Device
p.2980

Research on City Gas Load Forecasting Method
p.2986

The Study of the Ventilation Influence to Gas-Based Direct Reduction Shaft Furnace Flow Field
p.2990

Basic Research of Solar Seasonal Thermal Storage Capacity Increase to Existing Heating System
p.2994

Research on the SVM Classification of Active and Passive Remote Sensing Data Based on the Feature Per-Parcel
p.3001

The Application of Network RTK Technology in Road Construction Survey
p.3007

Richt Equation Arithmetic Used on Mixed Filter of Monitored Slope Deformation Data
p.3011

Based on Inclinometer to Measure Dynamic Deflection of High-Speed Railway Bridge
p.3019

Analysis and Research of Single Base Station CORS Precision
p.3027

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 405-408Research on the SVM Classification of Active and...

Research on the SVM Classification of Active and Passive Remote Sensing Data Based on the Feature Per-Parcel

Abstract:

Pepper and Salt" phenomenon and misclassification phenomenon are serious and the accuracy is low based on pixel classification, when only use a single remote sensing image. In this article, joint LiDAR data and high resolution image together based on feature per-parcel classification,and in the image segmentation stage, texture feature is introduced, these can full use of spectral informationtexture feature and elevation information in classification, to solve same object with different spectra and same spectrum with different objects. Compared with the classification based on pixel, only use a single remote sensing image, the method based on feature per-parcel with spectrumtexture and elevation information achieved a high accuracy,96.94%, improved the classification result.

You might also be interested in these eBooks

Progress in Industrial and Civil Engineering II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 405-408)

Pages:

3001-3006

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.405-408.3001

Citation:

Cite this paper

Online since:

September 2013

Authors:

Shuang Ting Wang*, Chun Lai Wang, Wei Bing Du, Le Le Tong, Fei Wang

Keywords:

Feature Per-Parcel, LiDAR, Resolution Remote Sensing, Support Vector Machine (SVM), Wavelet Transform-Mean Shift

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] LOBO A, CHIC O, CASTERAD A: Internationl Journal of Remote Sensing. Vol. 17(1996),P. 2385.

Google Scholar

[2] Aplin P, Atkinson P, Curran P. Per-field: Advances in Remote Sensing and GIS Analysis. Chichester: Wiley and Son. Vol. 9(1999),P. 219.

Google Scholar

[3] Blaschke T, Lang S, Lorup E, Strobl J, Zeil P: Metropolis Verlag, Marburg. (2000),P. 555.

Google Scholar

[4] TAO Chao, TAN Yihua: Acta Geodaetica et Cartographica Sinica, In Chinese. Vol. 39(1)(2010):P. 39.

Google Scholar

[5] LIU Chun-ping: Computer Application, In Chinese. Vol. 27(8)(2007),P. (2004).

Google Scholar

[6] JIANG Yun, WANG Jun: Engineering of surveying and mapping, In Chinese. Vol. 19(4)(2010),P. 34.

Google Scholar

[7] XING Li-xin, MENG Zhi-guo: Journal of Jilin University, In Chinese. Vol. 34(3)(2004),P. 481.

Google Scholar

[8] BO Shukui, DING Lin: Journal of image and Graphics, In Chinese. Vol. 15(7)(2010),P. 1106.

Google Scholar