Landslide Detection Based on ResU-Net with Transformer and CBAM Embedded: Two Examples with Geologically Different Environments

Abstract

An efficient method of landslide detection can provide basic scientific data for emergency command and landslide susceptibility mapping. Compared to a traditional landslide detection approach, convolutional neural networks (CNN) have been proven to have powerful capabilities in reducing the time consumed for selecting the appropriate features for landslides. Currently, the success of transformers in natural language processing (NLP) demonstrates the strength of self-attention in global semantic information acquisition. How to effectively integrate transformers into CNN, alleviate the limitation of the receptive field, and improve the model generation are hot topics in remote sensing image processing based on deep learning (DL). Inspired by the vision transformer (ViT), this paper first attempts to integrate a transformer into ResU-Net for landslide detection tasks with small datasets, aiming to enhance the network ability in modelling the global context of feature maps and drive the model to recognize landslides with a small dataset. Besides, a spatial and channel attention module was introduced into the decoder to effectually suppress the noise in the feature maps from the convolution and transformer. By selecting two landslide datasets with different geological characteristics, the feasibility of the proposed model was validated. Finally, the standard ResU-Net was chosen as the benchmark to evaluate the proposed model rationality. The results indicated that the proposed model obtained the highest mIoU and F1-score in both datasets, demonstrating that the ResU-Net with a transformer embedded can be used as a robust landslide detection method and thus realize the generation of accurate regional landslide inventory and emergency rescue.

Classification algorithm for underwater surface cracks in hydroelectric dams

“…After that, CBAM feeds the extracted features into the weight-sharing Multi-Layer Perceptron (MLP) and gets two 1 * C * C channel attention mappings. The final channel attention mapping is obtained by summing the two mappings element-wise and using Sigmoid activation [13] .…”

ShapeFormer: A Shape-Enhanced Vision Transformer Model for Optical Remote Sensing Image Landslide Detection

“…There are 770 labeled images in this dataset, and the spatial sizes of these image are different. Thus, in the experiment, we resized the images to 224 224  pixels, according to [53], for all the comparison methods.…”

“…The vision transformer (ViT) models have also been introduced into the field of remote sensing image processing, for applications such as semantic segmentation [51] and object detection [52], and have achieved competitive results, compared with CNN models. Some researchers have also studied the performance of ViT models in remote sensing image landslide detection [53]. However the ViT structure in [53] used an input of a fixed size, which results in difficulty in exploring some small objects.…”

“…Some researchers have also studied the performance of ViT models in remote sensing image landslide detection [53]. However the ViT structure in [53] used an input of a fixed size, which results in difficulty in exploring some small objects. Landslides display different spectral and spatial characteristics, compared with the artificial features, such as buildings and roads.…”

Semantic segmentation of remote sensing images based on dilated convolution and spatial-channel attention mechanism

“…Semantic segmentation is a critical technology in remote sensing image interpretation, as it enables pixel-by-pixel classification of objects in images. Due to its advanced classification capabilities, semantic segmentation has found wide application in many fields, such as landslide monitoring, 1 , 2 plant disease monitoring, 3 and water quality monitoring, 4 in the field of disaster monitoring. In urban planning, it has been utilized for road detection, 5 building change detection, 6 illegal building detection, 7 3D scene reconstruction 8 , 9 .…”