You have requested a machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Neither SPIE nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied representations or warranties of any kind, including, without limitation, representations and warranties as to the functionality of the translation feature or the accuracy or completeness of the translations.
Translations are not retained in our system. Your use of this feature and the translations is subject to all use restrictions contained in the Terms and Conditions of Use of the SPIE website.
6 August 2015A rapid extraction of landslide disaster information research based on GF-1 image
In recent years, the landslide disasters occurred frequently because of the seismic activity. It brings great harm to people's
life. It has caused high attention of the state and the extensive concern of society. In the field of geological disaster,
landslide information extraction based on remote sensing has been controversial, but high resolution remote sensing image
can improve the accuracy of information extraction effectively with its rich texture and geometry information. Therefore,
it is feasible to extract the information of earthquake- triggered landslides with serious surface damage and large scale.
Taking the Wenchuan county as the study area, this paper uses multi-scale segmentation method to extract the landslide
image object through domestic GF-1 images and DEM data, which uses the estimation of scale parameter tool to determine
the optimal segmentation scale; After analyzing the characteristics of landslide high-resolution image comprehensively
and selecting spectrum feature, texture feature, geometric features and landform characteristics of the image, we can
establish the extracting rules to extract landslide disaster information. The extraction results show that there are 20 landslide
whose total area is 521279.31 ㎡.Compared with visual interpretation results, the extraction accuracy is 72.22%. This
study indicates its efficient and feasible to extract earthquake landslide disaster information based on high resolution
remote sensing and it provides important technical support for post-disaster emergency investigation and disaster
assessment.
The alert did not successfully save. Please try again later.
Sai Wang, Suning Xu, Ling Peng, Zhiyi Wang, Na Wang, "A rapid extraction of landslide disaster information research based on GF-1 image," Proc. SPIE 9669, Remote Sensing of the Environment: 19th National Symposium on Remote Sensing of China, 96690C (6 August 2015); https://doi.org/10.1117/12.2204784