Browse > Article
http://dx.doi.org/10.7780/kjrs.2008.24.5.517

Supervised Classification Using Training Parameters and Prior Probability Generated from VITD - The Case of QuickBird Multispectral Imagery  

Eo, Yang-Dam (Dept. of Advanced Technology Fusion, Konkuk University)
Lee, Gyeong-Wook (Dept. of Civil & Environmental Engineering, Seoul National University)
Park, Doo-Youl (Chung-Ang Aerosurvey Co. Ltd.)
Park, Wang-Yong (Agency for Defense Development)
Lee, Chang-No (Dept. of Civil Engineering, Seoul National University of Technology)
Publication Information
Korean Journal of Remote Sensing / v.24, no.5, 2008 , pp. 517-524 More about this Journal
Abstract
In order to classify an satellite imagery into geospatial features of interest, the supervised classification needs to be trained to distinguish these features through training sampling. However, even though an imagery is classified, different results of classification could be generated according to operator's experience and expertise in training process. Users who practically exploit an classification result to their applications need the research accomplishment for the consistent result as well as the accuracy improvement. The experiment includes the classification results for training process used VITD polygons as a prior probability and training parameter, instead of manual sampling. As results, classification accuracy using VITD polygons as prior probabilities shows the highest results in several methods. The training using unsupervised classification with VITD have produced similar classification results as manual training and/or with prior probability.
Keywords
supervised classification; training sampling; VITD; prior probability; unsupervised classification;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Lee, Y. W., Y. D. Eo, Y. W. Park, B. J. Seo, H. S. Song, and H. M. Yoo, 2004. VITD Specification Analysis (For Military Geographic Information System Technical Support Project), TEDC-508-040353, Agency for Defense Development, pp.4-7
2 Pedroni, L., 2003. Improved classification of Landsat Thematic Mapper data using modified prior probabilities in large and complex landscape, International Journal of Remote Sensing, 24(1): 91-113   DOI   ScienceOn
3 Eo, Y. D., B. W. Cho, Y. W. Lee, and Y. I. Kim, 1999. A Study on the Training Optimization Using Genetic Algorithm-In case of Statistical Classification considering Normal Distribution, Korean Journal of Remote Sensing, 15(3): 195-208   DOI
4 Schowengerdt, R. A., 1983. Techniques for Image Processing and Classification in Remote Sensing, Academic press, Orlando, FL, USA
5 Kim, C. J., Y. D. Eo, and B. K. Lee, 2008. Effect of Effect of Prior Probabilities on the Classification Accuracy under the Condition of Poor Separability, Korean Journal of Geomatics, 26(4): 333-340   과학기술학회마을
6 George H. R., 1982. Sample design for estimating change in Land Use and Land cover, Photogrammetric Engineering and Remote Sensing, 48(5): 793-801
7 Hixon, M., D. Schoez, and N. Fuhs, 1980. Evaluation of several schemes for classification of remotely sensed data, Photogrammetric Engineering and Remote Sensing, 46(12): 1547-1553
8 Manakos, I., T. Schneider, and U. Ammer, 2000. A comparison betwen the ISODATA and the eCognition classification on basis of field data. Proceedings of XIX ISPRS Congress, 16-22 July, Amsterdam
9 Defense Mapping Agency, 1989, Performance Specification Vector Product Interim Terrain Data, MIL-PRF-89040A
10 Schowengerdt, R. A., 1997. Remote Sensing - Models and Methods for Image processing, Academic press, Chestnut Hill, MA, USA
11 Jayakumar, S., A. Ramachandran, Jung Bin Lee, and Joon Heo, 2007. Object-oriented Classification and QuickBird Multi-spectral Imagery in Forest Density Mapping, Korean Journal of Remote Sensing, 23(3): 153-160   과학기술학회마을   DOI