Graph matching based change detection in satellite images
32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Almanya, 22 - 27 Temmuz 2012, ss.6213-6215, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/igarss.2012.6352677
- Basıldığı Şehir: Munich
- Basıldığı Ülke: Almanya
- Sayfa Sayıları: ss.6213-6215
- İstanbul Medipol Üniversitesi Adresli: Hayır
Özet
Change detection from bitemporal satellite images (taken from the same region in different times) may be used in various applications such as forest monitoring, earthquake damage assessment, and unlawful occupation. There are various approaches, based on different principles, to detect changes from satellite images. In this study, we propose a novel change detection method based on structure information. Therefore, our method can be called as structural change detection. To summarize the structure in an image, we benefit from local features and their graph based representation. Extracting the structure from both images, we benefit from graph matching to detect changes. We tested our method on 18 Ikonos image pairs and discuss its strengths and weaknesses. © 2012 IEEE.