Identification of multi-scale corresponding object-set pairs between two polygon datasets with hierarchical co-clustering |
| |
| Institution: | 1. Master''s Student in Engineering and Environmental Management, Universidad Surcolombiana, Neiva, Huila, Colombia;2. Research Group of Science, Engineering and Innovation, Crimarpez S.A.S, Calle 12 Sur N° 6-45, Neiva, Huila, Colombia;3. Corporación Universitaria Minuto de Dios, Programa de Administración en Seguridad y Salud en el Trabajo, Grupo de Investigación en Seguridad y Salud en el Trabajo, Neiva, Huila, Colombia;4. Universidad Surcolombiana, Faculty of Engineering, Agricultural Engineering Program, Hydro Engineering and Agricultural Development Research Group (GHIDA), Avenida Pastrana Borrero - Carrera 1, Neiva, Huila, Colombia;5. Universidad Nacional de Colombia, Bogotá Campus, Faculty of Sciences, Department of Pharmacy, Pharmaceutical-Physical-Chemical Research Group, Carrera 30 No. 45-03, Bogotá D.C., Colombia;6. Pharmaceutical Analysis Research Center and Faculty of Pharmacy, Tabriz University of Medical Sciences, Tabriz 51664, Iran;7. Kimia Idea Pardaz Azarbayjan (KIPA) Science Based Company, Tabriz University of Medical Sciences, Tabriz 51664, Iran;8. Universidad Cooperativa de Colombia, Department of Engineering, Industrial Engineering Program, GRIAUCC Research Group, Calle 11 No. 1 - 51, Neiva, Huila, Colombia;1. School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China;2. School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China;3. School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing 210042, China |
| |
| Abstract: | In this paper, we propose a means of finding multi-scale corresponding object-set pairs between two polygon datasets by means of hierarchical co-clustering. This method converts the intersection-ratio-based similarities of two objects from two datasets, one from each dataset, into the objects’ proximity in a geometric space using a Laplacian-graph embedding technique. In this space, the method finds hierarchical object clusters by means of agglomerative hierarchical clustering and separates each cluster into object-set pairs according to the datasets to which the objects belong. These pairs are evaluated with a matching criterion to find geometrically corresponding object-set pairs. We applied the proposed method to the segmentation result of a composite image with 6 NDVI images and a forest inventory map. Regardless of the different origins of the datasets, the proposed method can find geometrically corresponding object-set pairs which represent hierarchical distinctive forest areas. |
| |
| Keywords: | Multi-scale object-set matching Laplacian-graph embedding Hierarchical co-clustering Composite NDVI image Forest inventory map Geographic object-based image analysis |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
