Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지

Effect of Prior Probabilities on the Classification Accuracy under the Condition of Poor Separability

  • Kim, Chang-Jae (Department of Geomatics Engineering, University of Calgary) ;
  • Eo, Yang-Dam (Department of Advanced Technology Fusion, Konkuk University) ;
  • Lee, Byoung-Kil (Department of Civil Engineering, Kyonggi University)
  • Published : 2008.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper shows that the use of prior probabilities of the involved classes improve the accuracy of classification in case of poor separability between classes. Three cases of experiments are designed with two LiDAR datasets while considering three different classes (building, tree, and flat grass area). Moreover, random sampling method with human interpretation is used to achieve the approximate prior probabilities in this research. Based on the experimental results, Bayesian classification with the appropriate prior probability makes the improved classification results comparing with the case of non-prior probability when the ratio of prior probability of one class to that of the other is significantly different to 1.0.

Keywords

References

  1. Ahmet B. Orun (2004), Automated Identification of Man-Made Textural Features on Satellite Imagery by Bayesian Networks, Photogrammetric Engineering and Remote Sensing, ASPRS, Vol. 70, No. 2, pp. 211-216
  2. Alesheikh, Ali A. (2003), Improving Classification Accuracy Using Knowledge Based Approach, Map India Conference 2003, unpaginated CD-ROM
  3. Antonarakis, A., Richards, K., Brasington, J.(2008), Object-based land cover classification using airborne LiDAR, Remote Sensing of Environment, Volume 112, Issue 6, pp. 2988-2998 https://doi.org/10.1016/j.rse.2008.02.004
  4. Axelsson, P. (1999). Processing of laser scanner data - algorithms and applications. ISPRS Journal of Photogrammetry and Remote Sensing, 54, 138-147 https://doi.org/10.1016/S0924-2716(99)00008-8
  5. Choi, S. P. and Yang, I. T. (2003), Extraction of Land Surface Change Information by Using Landsat TM Images, Korean Journal of Geomatics, Korean Society of Surveying, Geodesy, photogrammetry, and cartography, Vol. 21, No. 3, pp. 261-262
  6. Eo, Y. D., Kim, C. J. and Kim. Y. I. (1999), Correlation Analysis between the Multivariate Conditional Probability and the Classification Accuracy in Satellite Image Classification, Journal of Civil Engineering, Korean Society of Civil Engineers, Vol. 19, No. III-5, pp. 935-947
  7. John A. Richards (1993), Remote Sensing Digital Image Analysis: An Introduction, Second Edition, Springer, 340 p
  8. Lillesand T. M. and Kiefer R. W. (1994), Remote Sensing and Image Interpretation, Third edition, John Wiley & Sons, INC, 750 p
  9. Swain, P. H. and Davis, S. M.(1978), Remote Sensing : The Quantitative Approach, McGrow-Hill, pp. 170-173
  10. Van Genderen, J.L. (1978), Remote sensing: statistical testing of thematic map accuracy. In: Remote sensing of environment: an interdisciplinary journal, Vol. 7, Issue 1, pp. 3-14 https://doi.org/10.1016/0034-4257(78)90003-2