Remote Sensing Image Classification Based on Object-Oriented Method and Support Vector Machine: A Case Study in Harbin City

Abstract:

Remote sensing classification, as an important means of urban planning and construction, has been widely concerned. Urban land use classification is extremely challenging tasks because of some land covers are spectrally too similar to be separated using only the spectral information of remote sensing image. Object-oriented remote sensing image classification method overcomes the drawbacks of traditional pixel-based classification method. It combines the spectral, special structure and texture features of the images, can effectively avoid the phenomenon of "different objects share the same spectrum" or "the same objects differ in spectrum. Support Vector Machine (SVM) is an excellent tool for remote sensing classification. Combination of both can develop their own advantages to do high-resolution remote sensing image classification. Using a public image in Harbin city as an example, classification based on object-oriented method and SVM has achieved better results than traditional pixel-based classification method.

• Periodical: Advanced Materials Research (Volumes 912-914)
• Pages: 1331-1334
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.912-914.1331
• Online since: April 2014
• Authors: Qiu Xia Yang*, Chuan Wen Luo, Tian Kai Chen
• Keywords: Image Classification, Object-Oriented, Remote Sensing Image, Support Vector Machine (SVM)

References

[1] Salehi, Bahram, et al. Object-based classification of urban areas using VHR imagery and height points ancillary data., Remote Sensing 4. 8 (2012): 2256-2276.

DOI: 10.3390/rs4082256

[2] Gutiérrez, Jesus Aguirre, Arie Seijmonsbergen, and Joost Duivenvoorden. Optimizing land cover change detection using combined pixel-based and object-based image classification in a mountainous area in Mexico., Anais XV Simpósio Brasileiro de Sensoriamento Remoto-SBSR, Curitiba, PR, Brasil 30 (2011).

DOI: 10.1016/j.apgeog.2011.10.010

[3] Mengmeng, Wu, et al. An Extraction Method of Urban Ecological Types Based on Object-oriented Classification-A Case Study on Wuhan City., 2013 International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE 2013). Atlantis Press, (2013).

DOI: 10.2991/rsete.2013.222

[4] Kamal, Muhammad, and Stuart Phinn. Hyperspectral data for mangrove species mapping: A comparison of pixel-based and object-based approach., Remote Sensing 3. 10 (2011): 2222-2242.

DOI: 10.3390/rs3102222

[5] Shixin, Wang, et al. Object-oriented Classification Technique for Extracting Abandoned Farmlands by Using Remote Sensing Images., 3rd International Conference on Multimedia Technology (ICMT-13). Atlantis Press, (2013).

DOI: 10.2991/icmt-13.2013.183