Our dataset comprises a collection of high-resolution satellite imagery annotated for landslide detection using the Fast RCNN (Region-based Convolutional Neural Network) model. Each image in the dataset is meticulously labeled to identify regions prone to landslides, providing crucial insights for disaster prevention and mitigation efforts. Leveraging the Fast RCNN architecture, which excels in accurately delineating object boundaries, our dataset offers precise localization of landslide-prone areas, aiding researchers and policymakers in proactive risk assessment and management strategies. By sharing this dataset with the ISPRS community, we aim to foster collaboration and facilitate advancements in landslide detection methodologies for enhanced disaster resilience.