Selection of Landsat8 Image Classification Bands Based on MLC–RFE
- 14 Downloads
In remote sensing image classifications, a reasonable selection of bands can help improve classification accuracy. At present, problems occur in artificial subjective selection of bands in image classifications, thereby resulting in ineffective expression of classification accuracy. In this study, 10 bands of Landsat8 fusion data were used as information sources, and recursive feature elimination based on maximum likelihood classification (MLC–RFE) was conducted to select the most important bands and analyse the classification results of the various band combinations. Results showed that green, red and blue were the three unimportant bands, which had the lowest classification accuracy (92.2312%). Coastal blue, near infrared and short-wave infrared 1 were the three important bands, which had a high classification accuracy (97.5000%). The coastal blue, near infrared, short-wave infrared 1, cirrus, short-wave infrared 2, thermal infrared 1 and thermal infrared 2 constituted the recursive optimal band set in all multi-band combinations and had the highest classification accuracy (99.1667%). The classifications of the 2–7 bands and all 10 bands had an overall accuracy of 95.3495% and 96.9624%, respectively. Additional experiments showed that the Landsat8 band elimination order and optimal band set have certain differences, but the optimal band combinations with high classification accuracies can be coupled from all of them. Our findings confirmed that various band combinations had different classification accuracies, which indicated that selecting the participating bands in a classification was crucial. Furthermore, the MLC–RFE method used in this study selected the optimal classification bands and played an important role in solving the band selection problem.
KeywordsLandsat8 Image classification Maximum likelihood classification Recursive feature elimination Band selection
This work was supported by the National Nature Science Foundation of China (Grant No. 61502219) and the Intergovernmental International Cooperation on Science and Technology Innovation (Grant No. 2016YFE0104600). We want to provide our gratitude to the editors and the anonymous reviewers.
- Li, F., Liang, H. D., Mi, X. N., & Wei, A. X. (2015b). A multi-subregions decision tree land cover classification approach using Landsat8 image. Infrared and Laser Engineering, 44(7), 2224–2230.Google Scholar
- Liu, H. P., An, H. J., Wang, B., & Zhang, Q. L. (2015a). Tree species classification using WorldView-2 images based on recursive texture feature elimination. Journal of Beijing Forestry University, 37(8), 53–59.Google Scholar
- Liu, J., Heiskanen, J., Aynekulu, E., & Pellikka, P. K. E. (2015b). Seasonal variation of land cover classification accuracy of Landsat8 images in Burkina Faso. ISPRS—International Archives of the Photogrammetry. Remote Sensing and Spatial Information Sciences, XL-7/W3(7), 455–460.Google Scholar
- Ning, L. L., & Zhang, X. L. (2014). A preliminary study on vegetation classification based on texture information of Landsat-8 images. Journal of Central South University of Forestry & Technology, 34(9), 60–64.Google Scholar
- Wang, M., Gao, X. H., Chen, S. Y., Feng, Q. S., & Liang, T. G. (2015a). The land use classification based on Landsat8 Remote sensing image- A case study of Anquilar community in Hongyuan County of Sichuan Province. Pratacultural Science, 32(5), 694–701.Google Scholar
- Wang, T. T., Li, S. S., Li, A., Feng, X. X., & Wu, Y. W. (2015b). Land cover classification in Beijing using Landsat8 image. Journal of Image and Graphics, 20(9), 1275–1284.Google Scholar
- Yang, B. L., & Zhang, G. L. (2015). The application of improved spectral angle mapper in land use classification using Landsat-8 OLI image. Spacecraft Recovery & Remote Sensing, 36(6), 80–86.Google Scholar