A Multi-Modal Deep Neural Network Model for Forested Landslide Detection

Objectives : Vegetation widely spread in the southwestern mountainous regions of China. In the remote sensing images of this area, the landslides are usually shaded by vegetation. The error rate of forested landslide detection in remote sensing images is high, which is hard to meet practical needs. Methods : To address this issue, this article uses light detection and ranging (LiDAR)-derived digital elevation mode (DEM) and Hillshade to remove the forest on the landslides. In addition, a new dataset for forested landslide detection is also constructed. On this basis, an intelligent landslide detection model base on multimodal deep learning is proposed. The proposed model uses DEM and hillshade to identify forested landslides, which consists of three neural network models. First, a Transformer network for automatic extraction of DEM features is proposed. Second, a Transformer network for automatically extracting hillshade features is proposed. Third, a convolution neural network with attention mechanism for merging multimodal remote sensing data is proposed. Results . The proposed model is compared with ResU-Net, LandsNet, HRNet and SeaFormer. Experimental results show that the proposed model achieves the highest prediction accuracy. IoU and F1 is improved by 9.3% and 6.8%. Conclusions . LiDAR is able to remove the impact of forest cover, which is suitable for identifying the forested landslides in the southwest mountain areas of China. The proposed LiDAR-based landslide detection model is able to predict the position of landslides, which is useful for deciding the position of landslide monitoring devices.