The demand for three-dimensional (3D) urban model is growing in Japanese traditional buildings for disaster prevention. Classification of point clouds into structural elements is required for generating 3D models. This paper proposes an algorithm to automatically extract the lattice windows of Japanese traditional buildings from terrestrial LiDAR data for the sake of 3D modeling. First, it extracts edges from three dimensional data. Second, the edges are classified into groups by distance between two points. Finally, lattice windows are extracted from the groups using SVM (support vector machine) classifier. The validation results showed that the accuracy to finally extract lattice windows was 63%. As future tasks, edge extraction processing should be improved, and better features for SVM classifier should be developed.
Wetland monitoring with remote-sensed data is a key issue for planning appropriate wetland managements. We utilized an optical-satellite imagery with high-resolution to recognize where the transitions of dominant plants are appearing associated with the drying of the Senjyogahara-wetland. To infer the development of drying areas in the wetland, we adopted such an interpretation key as the growth in number of young trees and its direction of distributions on the satellite imagery, and obtained ground truth data in the study site relevant to the satellite imagery. The comparison between the satellite imagery approach and the ground truth investigations supported the effectiveness of using the interpretation key on the high-resolution satellite imagery to identify drying symptoms in the wetland.
Many GIS (Geographic Information System) users are willing to remove the shadow from aerial imagery. In order to remove the shadow form aerial imagery, it is necessary to extract the shadow area and convert the luminance value of the shadow area. However, it is difficult to extract the shadow area using only the luminance value of aerial imagery. Therefore, in the background that aerial imagery and airborne laser scanner data is acquired at the same time in recent years, we propose a shadow extraction method from aerial imagery using airborne laser scanner data. We prove the effectiveness of the proposed method through the experiments. Finally, we comment on the respects in which the proposed method is improved and on future prospects.