The invention discloses a building intelligent three-dimensional mapping method based on multi-source remote sensing data, and the method comprises the steps: obtaining a building roof vector contourof a target measurement region and a structured building group three-dimensional wireframe model through employing aerial remote sensing image data and laser point cloud data of the target measurementregion. According to the invention, aerial remote sensing image data is utilized to generate image three-dimensional point cloud, and high-precision registration fusion of the image point cloud and laser point cloud is completed; high-precision DSM, DEM, traditional DOM and OESM models are generated by using the fused three-dimensional point cloud; building boundaries are extracted through three-dimensional point cloud, contour lines are extracted on a DOM, the boundaries and the DOM are fused to extract and screen building two-dimensional vector contours, and high-precision extraction of building roof contours is achieved; and a building structured wireframe three-dimensional model is quickly generated based on the building roof two-dimensional vector contour and the high-precision OESMmodel. According to the method, manual intervention is not needed, and full-automatic building three-dimensional mapping is achieved.