access icon free Composite kernels conditional random fields for remote-sensing image classification

© The Institution of Engineering and Technology
Received 27/05/2014, Published 14/10/2014

The problem of classifying a remote-sensing image by specifically labelling each pixel in the image is addressed. A novel method, named composite kernels conditional random field (CKCRF), which embeds multiple kernels into a classical CRFs model is proposed. Rather than manually selecting kernel-like KCRF, CKCRFs chooses the appropriate kernel by training. Moreover, a genetic programming-based decision-level fusion framework is proposed to tackle the problem of feature selection. It can select the appropriate features suitable to each category. Evaluations show that CKCRFs outperform CRFs and KCRFs, and CKCRFs with the fusion scheme is better than that without the fusion step.

Inspec keywords: image classification; image fusion; remote sensing; geophysical image processing; geophysical techniques

Other keywords: remote-sensing image classification; fusion scheme; GP-based decision-level fusion framework; composite kernels conditional random fields; genetic programming

Subjects: Geophysical techniques and equipment; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Data and information; acquisition, processing, storage and dissemination in geophysics; Optical, image and video signal processing; Computer vision and image processing techniques; Geography and cartography computing

References

    1. 1)
      • 5. Koza, J.R.: ‘A source of information about the field of genetic programming and the field of genetic and evolutionary computation’, 8 July 2007. Available at: www.genetic-programming.org.
    2. 2)
    3. 3)
      • 3. Lafferty, J., Zhu, X., Liu, Y.: ‘Kernel conditional random fields: representation and clique selection’. Proc. 21st Int. Conf. Machine Learning, Alberta, Canada, July 2004, p. 64.
    4. 4)
    5. 5)
      • 1. Hoberg, T., Rottensteiner, F., Heipke, C.: ‘Classification of multitemporal remote sensing data using conditional random fields’. IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS), Istanbul, Turkey, August 2010, pp. 1–4.
    6. 6)
    7. 7)
      • 5. Koza, J.R.: ‘A source of information about the field of genetic programming and the field of genetic and evolutionary computation’, 8 July 2007. Available at: www.genetic-programming.org.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2014.1964
Loading

Related content

content/journals/10.1049/el.2014.1964
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading