- 期刊
- OpenAccess
Land Features Extraction from Landsat TM Image Using Decision Tree Method
摘要
In this paper we presented a method based on the decision tree to extract land feature information for an urban area of Taiyuan City in China. One Landsat TM image obtained on September 23, 2010 covering the entire city of Taiyuan was obtained and processed to extract information. Digital elevation model (DEM) and some derived index images about water, vegetation, and crop land were used to develop and construct the decision tree. Six general land categories including water body, developed land, bare land, grass land, forest land, and crop land of the study area were classified using the established decision tree. The results were evaluated using high resolution satellite imagery and reported in a confusion matrix table. An overall accuracy of 89.52% with a kappa statistic of 0.87 were obtained using our method, which is higher than those from other traditional methods.
延伸閱讀
- Lee, S., Cho, M., & Lee, C. (2016). An Effective Gap Filtering Method for Landsat ETM+ SLC-Off Data. Terrestrial, Atmospheric and Oceanic Sciences, 27(6), 921-932. https://doi.org/10.3319/TAO.2016.07.18.02
- Yang, C. C. (2019). Deep Learning-Based Land Cover Classification Using Airborne Lidar and Aerial Imagery [master's thesis, National Chiao Tung University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0030-0306202016332560
- Avdan, U., & Jovanovska, G. (2016). Algorithm for Automated Mapping of Land Surface Temperature Using LANDSAT 8 Satellite Data. Journal of Sensors, 2016(), 208-215-020. https://doi.org/10.1155/2016/1480307
- Sulong, G., Sadiq, A., & LoayEdwar (2015). Single and Multi-source Methods for Reconstruction the Gaps in Landsat 7 ETM+ SLC-off Images. Research Journal of Applied Sciences, Engineering and Technology, 11(4), 423-428. https://www.airitilibrary.com/Article/Detail?DocID=20407467-201510-201512090025-201512090025-423-428
- Teo, T. A., & Huang, C. H. (2016). Object-Based Land Cover Classification Using Airborne Lidar and Different Spectral Images. Terrestrial, Atmospheric and Oceanic Sciences, 27(4), 491-504. https://doi.org/10.3319/TAO.2016.01.29.01(ISRS)