| Grant number: | 14/15332-1 |
| Support Opportunities: | Scholarships abroad - Research Internship - Doctorate |
| Start date: | December 08, 2014 |
| End date: | December 07, 2015 |
| Field of knowledge: | Physical Sciences and Mathematics - Geosciences |
| Principal Investigator: | Aluir Porfírio Dal Poz |
| Grantee: | Henrique Cândido de Oliveira |
| Supervisor: | Ayman F. Habib |
| Host Institution: | Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil |
| Institution abroad: | Purdue University, United States |
| Associated to the scholarship: | 13/21647-2 - THE USAGE OF LASER DATA FOR OCCLUSION DETERMINATION USING HEIGHT GRADIENT FROM A POLYHEDRIC SURFACE, FOR TRUE-ORTHOPHOTO GENERATION., BP.DR |
Abstract High quality orthophotos are essential elements in cartographic databases for many projects. Urban areas usually have many tall buildings that cause occlusion in aerial images. These occlusions can be severe depending on the height of the buildings, image acquisition viewpoint and also due to geometry. A product where no occlusion areas appear is called true-orthophoto. Occlusion detection is a key step in true-orthophoto generation. This process requires a set of aerial images and a surface representation, together with metadata and acquisition system information. In this project, a LASER (Light Amplification by Stimulated Emission of Radiation) point cloud provides a detailed description of the terrain and aboveground objects, resulting in a surface representation (i.e., a polyhedron) that is the base for occlusion detection. Analysis of the surface height gradient at certain sampled directions allows the identification of the occluded regions in aerial images. The main goals of this internship with the Geomatics Engineering Group - Purdue University are: to improve the proposed novel method for occlusion detection in aerial images; to accomplish a complete experimental evaluation of the proposed method, using different data sets; and to gain international experience. Specifically, quality assessment of the results to be obtained by applying the proposed method will be based on well-used quantitative indexes (such as completeness and correctness, for example) and comparisons with other methods for occlusion detection in aerial images. | |
| News published in Agência FAPESP Newsletter about the scholarship: | |
| More itemsLess items | |
| TITULO | |
| Articles published in other media outlets ( ): | |
| More itemsLess items | |
| VEICULO: TITULO (DATA) | |
| VEICULO: TITULO (DATA) | |