Abstract: High-altitude geohazards pose severe threats to human lives and property, critical infrastructure safety, and regional sustainable development. Traditional manual UAV remote sensing interpretation is highly subjective, time-consuming, and inefficient, which can hardly meet the practical demands of rapid emergency response for geohazards. To address these issues, an automatic identification method for high-altitude geohazards using UAV remote sensing is proposed based on the lightweight YOLOv11n-seg model, and a corresponding software system is developed. First, a deep learning-oriented sample dataset for high-altitude geohazard identification is established using high-resolution UAV images. Subsequently, an automatic identification method is constructed with the lightweight segmentation model YOLOv11n-seg as the core framework, achieving high-precision, high-efficiency, and automated geohazard identification. A software system is developed using the PyQt5 Python GUI framework. Finally, the extremely high-altitude mountainous area in the southeastern Tibetan Plateau is selected as the study area to verify the proposed method and system, and the identification results of high-altitude geohazards are generated. Experimental results show that the proposed method has high computing efficiency and reliable identification results. The developed software system features a user-friendly interface and simple operation, realizing end-to-end intelligent interpretation of UAV images. It can automatically complete geohazard location detection, boundary extraction, and result visualization, with an identification accuracy higher than 91%. This study integrates an advanced lightweight segmentation model with UAV remote sensing technology, providing efficient and reliable technical support for rapid survey, risk assessment, and emergency decision-making of high-altitude geohazards with important practical application value.