Investigation of SVM and Level Set Interactive Methods for Road Extraction from Google Earth Images |
| |
Authors: | Abolfazl Abdollahi Hamid Reza Riyahi Bakhtiari Mojgan Pashaei Nejad |
| |
Affiliation: | 1.Faculty of Geography,Kharazmi University of Tehran,Tehran,Iran;2.Faculty of Natural Resources and Earth Science,University of Shahrekord,Shahrekord,Iran;3.Faculty of Natural Resources,Ferdowsi University of Mashhad,Mashhad,Iran |
| |
Abstract: | Currently, methods of extracting spatial information from satellite images are mainly based on visual interpretations and drawing the consequences by human factor, which is both costly and time consuming. A large volume of data collected by satellite sensors, and significant improvement in spatial and spectral resolution of these images require the development of new methods for optimal use of these data in order to produce rapid economic and updating road maps. In this study, a new automatic method is proposed for road extraction by integrating the SVM and Level Set methods. The estimated probability of classification by SVM is used as input in Level Set Method. The average of completeness, correctness, and quality was 84.19, 88.69 and 76.06% respectively indicate high performance of proposed method for road extraction from Google Earth images. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|