| Autor: |
Soni, Ashish, Koner, Radhakanta, Villuri, Vasant Govind Kumar |
| Předmět: |
|
| Zdroj: |
Journal of Spatial Science; Sep2024, Vol. 69 Issue 3, p745-771, 27p |
| Abstrakt: |
The recent advancement in the pattern recognition technique has demonstrated the superiority of remote sensing technology. Deep neural networks use spatial feature representations such as convolution neural networks (CNN) to provide better generalisation capability. Our aim is two-fold: firstly, increase the reliability feature by performing the Dual-scale fusion via a modified Markov random field known as DuCNN-MMRF. Secondly, an integration framework was introduced to combine the multispectral image classification produced by DuCNN-MMRF and Normalised-Digital Surface Model (nDSM) information, using a novel approach known as constraint-based Dempster Shafer theory (C-DST). C-DST targeted DuCNN-MMRF's uncertain information (ambiguous information) and rectified it with complementary information. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
