Satellite image classification methods and Landsat 5TM bands
This work addresses the problem of selecting optimal classification methods and band combinations for satellite image analysis, but it is incremental as it builds on existing methods and data.
The paper compared three classification methods for satellite imagery and identified the chain method as the most accurate with 79% overall accuracy, outperforming minimum distance (67%) and parallelepiped (65%). It also found that band 4 of Landsat 5TM improves accuracy when combined with other bands for landcover detection.
This paper attempts to find the most accurate classification method among parallelepiped, minimum distance and chain methods. Moreover, this study also challenges to find the suitable combination of bands, which can lead to better results in case combinations of bands occur. After comparing these three methods, the chain method over perform the other methods with 79% overall accuracy. Hence, it is more accurate than minimum distance with 67% and parallelepiped with 65%. On the other hand, based on bands features, and also by combining several researchers' findings, a table was created which includes the main objects on the land and the suitable combination of the bands for accurately detecting of landcover objects. During this process, it was observed that band 4 (out of 7 bands of Landsat 5TM) is the band, which can be used for increasing the accuracy of the combined bands in detecting objects on the land.