Search

Although many scholars have realized that deep learning methods have great advantages in hyperspectral lithology classification now, most of them use simple convolutional neural networks for discussion, which are difficult to effectively extract spectral sequence information from hyperspectral image (HSI). To address this issue, we propose a double-branch multiscale dual-attention (DBMSDA) network using two HSIs multiple different rock types as data sources. This network utilizes the multiscale spectral residual self-attention structure and dense connections in the spectral branch to extract diagnostic multiscale spectral information from HSIs, improving the ability to reuse spectral information. In the spatial branch, dense connections are used to fully extract diagnostic spatial information, and finally, the two are fused for classification. We compare the DBMSDA network with several traditional machine learning and deep learning methods. Experimental results show that the DBMSDA network has the best lithology classification performance and robustness. Its OA on the ZCD1 and HCD2 datasets is 85.08% and 90.80%, respectively, representing an improvement of 5.95% and 2.4% over the lowest OA, confirming that the DBMSDA network can effectively improve accuracy and is superior to other methods. Meanwhile, the experiment also showed that the DBMSDA network has good classification performance on HSIs of various rock types and HSIs from different data sources. Finally, ablation experiments were conducted to demonstrate that the DBMSDA network relies more on large training samples compared with traditional machine learning models, and that the DBMSDA network has better applicability and stability under the same sufficient training samples.

Existing algorithms based on remote sensing for landslide displacement estimation, such as C2C, C2M, DOD, and M3C2, are sensitive to errors generated in data processing, and further improving their accuracy is difficult. To address this issue, given that redundant observations may occur in landslide monitoring, we proposed a robust estimation method of landslide displacement from multitemporal unmanned aerial vehicle (UAV) photogrammetry-derived point clouds. The proposed method first establishes the relevant graph to manage the trajectory of error propagation for landslide displacement estimation for all possible paths. Two modules, namely intra- and inter-estimates, are explored to reduce the impact of outliers and high surface roughness in point clouds derived by UAV photogrammetry. Individually, the intraestimate operation is used to calculate landslide displacement between two temporal point clouds by robust estimation considering outlier constraint, and the interestimate operation is used to obtain the optimal calculation of landslide displacement by minimizing a given objective function using IGG robust estimation proposed by the Institute of Geodesy and Geophysics at the Chinese Academy of Sciences. Experimental results show that the proposed method is significantly superior to conventional methods, such as C2C, C2M, and M3C2, with an accuracy improvement of at least 8%.