Journal
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
Volume 28, Issue 13, Pages 16152-16164Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s11356-020-11791-z
Keywords
Tibetan Plateau; High altitude; Evidence theory; Landsat OLI; Land cover
Categories
Funding
- National Natural Science Foundation of China [41801332]
Ask authors/readers for more resources
This study investigated the extraction of land cover on the Tibetan Plateau using a combined classifier based on D-S evidence theory. The results showed that while combining multiple classifiers can significantly improve classification results, the maximum belief level does not necessarily indicate the accuracy of the combined classifier.
The Tibetan Plateau (TP) is a region with high altitudes and complicated terrain conditions. Due to the special conditions of this region, it is also regarded as the third pole of the Earth. The land cover and vegetation in this region have not been extensively studied, so this study investigated the possibility of using a combined classifier that was established based on D-S evidence theory to extract the land cover of the TP. Multiple feature images were obtained based on a single classification rule, and the feature images were normalized to obtain the basic probability assignment (BPA). The BPA was used as the evidence source to represent the belief level of each type of land cover. The information for the different belief levels was combined based on the D-S evidence theory. The maximum belief level of the combination results was used to identify the land cover types on the TP. The results of this study indicate that based on the D-S evidence theory, multiple classifiers can effectively be combined to improve the classification results. This study has also revealed that more classifiers fused together to make a combined classifier did not result in the combined classifier's accuracy being higher than those of the original classifiers. Higher accuracies were only obtained when more high accuracy evidence theory was used in the classifier combination, in which case, the combined classifier's classification accuracy was also high.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available