RIPF-Unet for regional landslides detection: a novel deep learning model boosted by reversed image pyramid features

Rapid detection of landslides using remote sensing images plays a key role in hazard assessment and mitigation. Many deep convolutional neural network-based models have been proposed for this purpose; however, for small-scale landslide detection, excessive convolution and pooling process may cause potential texture information loss, which can lead to misclassification of landslide target. In this paper, we present a novel UNet model for the automatic detection of landslides, wherein the reversed image pyramid features (RIPFs) are adapted to mitigate the information loss caused by a succession of convolution and pooling. The proposed RIPF-Unet model is trained and validated using the open-source landslides dataset of the Bijie area, Guizhou Province, China, wherein the precision of the proposed model is observed to increase by 3.5% and 4.0%, compared to the conventional UNet and UNet + + model, respectively. The proposed RIPF-Unet model is further applied to the case of the Longtoushan region after the 2014 Ms.6.5 Ludian earthquake. Results show that the proposed model achieves a 96.63% accuracy for detecting landslides using remote sensing images. And the RIPF-Unet model is also advanced in its compact parameter size; notably, it is 31% lighter compared to the UNet + + model.