Object-Oriented Information Extraction of Farmland Shelterbelts from Remote Sensing Image

Abstract:

It has become an important means of shelterbelts surveying using high resolution remote sensing image to access the distribution of farmland shelterbelts. However, traditional classifications of remote sensing image based on spectrum characteristics of single pixel, and didn’t consider the factors including relativity and structure characteristics of the neighboring pixels, which will lead to lower accuracy of feature extraction for high resolution remote sensing image. On the basis of object-oriented classification method and the module of ENVI Feature Extraction, the paper extracted the shelterbelts distribution through image segmentation and rules establishment for the Spot5 high resolution remote sensing image in the Midwest of Jilin Province, and the extraction accuracy is 91.3%.The result shows that the method can accurately extract farmland shelterbelts from high resolution remote sensing image.

• Periodical: Key Engineering Materials (Volume 500)
• Pages: 500-505
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.500.500
• Online since: January 2012
• Authors: Xiao Liang Shi, Ying Li, Rong Xin Deng
• Keywords: ENVI Feature Extraction, Farmland Shelterbelts, Object-Oriented (OO), Rules, Segmentation

References

[1] BrandleJR. WindbreakTechnology. Proceedins of an International Symposium on Windbreak Technology. 1986 Lincoln, Nebraska, pp.23-27.

[2] CaoXinsun. Windbreaks and shelterbelts. Beijing: Chinese Forestry Publishing House, (1983).

[3] Fan Zhiping, Guan Wenbin, Zeng Dehui, Jiang Fengqi. Indices and criteria of highly effective and multi-functional management of windbreaks/shelterbelts in northeast China. Chinese Journal of Applied Ecology, 2001, pp.701-705.

[4] Liu Bing, Hong Jiayi. Application of using Landsat7 ETM + Remote Sensing image in forest resources investigation of county level in the Three North Shelterbelt Project. Protection Forest Science and Technology, 2005, pp.24-27.

[5] Chen Jianjun, Zhang Shuwen, Tang Junmei, Zhang Yangzhen. Remote Sensing Survey of Shelterbelt Based on Landsat 7 ETM + Image in Daqing City , China. Journal of Northeast Forestry University, 2003, pp.101-102.

[6] Cao Bao, Qin Qiming, Ma Haijian, Qiu Yunfeng. Application of object - oriented approach to SPOT5 image classification: a case study in Haidian District, Beijing City. Geography and Geo-Information Science, 2006, pp.46-49.

[7] Metzler. V.T. Aaeh.C. Object-oriented image analysis by evaluating the causal object hierarchy of a partitioned reconstructive scale-space. Proceedings of ISMM2002 Redistribution rights reserved CSIRO Publishin, ed. By Talbot H. and Beare R., 2002, pp.265-276.

[8] Michael A. O'Brien, John M. Irvine. Information fusion for feature extraction and the development of geospatial information[C]. 7thInternational Conference on Information Fusion, (2004).

[9] Niu Vhunying, Jiang Wanshou, Huang Xianfeng, Xie Junfeng. Analysis and comparison between two object-oriented information extraction software of feature analyst and eCognition. Remote Sensing Information, 2007, pp.66-70.

[10] Yin Zuoxia, Du Peijun. Study on object-oriented image classification for hyperspectral remote sensing. Remote Sensing Information , 2007, pp.29-32.

[11] Robinson D. J., Redding, N. J., and Crisp, D. J. Implementation of a fast algorithm for segmenting SAR imagery[R]. Scientific and Technical Report, 2002, Australia: Defense Science and Technology Organization.

[12] Zhou Chunyan, Wang Ping, Zhang Zhenyong, Qi Chengtao. Classification of urban land based on object-oriented information extraction technology. Remote Sensing Technology and application, 2008, pp.31-35.