Under the background of rapid urban development and continuous climate change, frequent floods around the world have caused serious economic losses and social problems, which has become the main reason for the sustainable development of cities. Flood disaster risk assessment is an important non-engineering measure in urban disaster prevention and mitigation, and scientific flood disaster risk assessment is the premise and foundation of flood disaster risk management. This paper summarizes the current situation of flood risk assessment by analyzing the international literature in recent 20 years. The mechanism of flood disaster is mainly discussed. The flood disaster assessment methods are summarized, including historical disaster statistics method, multi-criteria index system method, remote sensing and GIS (Geographic Information System) coupling method, scenario simulation evaluation method and machine learning method. Furthermore, the development status of flood risk analysis and forecasting is summarized. Finally, the development trend and direction of flood risk assessment are put forward.

In urban point cloud scenarios, due to the diversity of different feature types, it becomes a primary challenge to effectively obtain point clouds of building categories from urban point clouds. Therefore, this paper proposes the Enhanced Local Feature Aggregation Semantic Segmentation Network (ELFA-RandLA-Net) based on RandLA-Net, which enables ELFA-RandLA-Net to perceive local details more efficiently by learning geometric and semantic features of urban feature point clouds to achieve end-to-end building category point cloud acquisition. Then, after extracting a single building using clustering, this paper utilizes the RANSAC algorithm to segment the single building point cloud into planes and automatically identifies the roof point cloud planes according to the point cloud cloth simulation filtering principle. Finally, to solve the problem of building roof reconstruction failure due to the lack of roof vertical plane data, we introduce the roof vertical plane inference method to ensure the accuracy of roof topology reconstruction. The experiments on semantic segmentation and building reconstruction of Dublin data show that the IoU value of semantic segmentation of buildings for the ELFA-RandLA-Net network is improved by 9.11% compared to RandLA-Net. Meanwhile, the proposed building reconstruction method outperforms the classical PolyFit method.