Abstract:

Based on the edge and the local region information，this paper proposes a new active contour model, which can process multi-spectral image, and it is used to extract the building roof boundary from LiDAR data. The input image of our model is processed by Microstation software，we first classify the LiDAR point cloud and then convert the classified results to raster format. Our model is solved by variational level set method, and the minimal solution is the exact building roof boundary. It can eliminate the restrictions on the initialization and the image types of ACM, and it is suitable for the automatic extraction of any shape of building roof boundaries. In addition，we reduce the computational time of our model by adding the level set rules. Building roof boundary extraction experiment result indicates that our model can obtain higher accuracy in matched rate、shape similarity and positional accuracy than the IAC model and the GACcolor model.

Key words: Active contour model, LiDAR point cloud, IAC model, RSF model, Building boundary extraction, Level set method