Automatic recognition of damaged town buildings caused by earthquake using remote sensing informatio

• 作 者: 柳稼航 单新建 尹京苑
• 机 构: Institute of Geology, China Earthquake Administration, Beijing 100029, China,Xi′an Institute of Opti
• 出 处: Acta Seismologica Sinica(English Edition)
• 发表日期: 2004年06期
• 关键词: region analysis damage recognition image comprehension Bhuj earthquake Tangshan

In the high-resolution images, the undamaged buildings generally show a natural textural feature, while the dam- aged or semi-damaged buildings always exhibit some low-grayscale blocks because of their coarsely damaged sections. If we use a proper threshold to classify the grayscale of image, some independent holes will appear in the damaged regions. By using such statistical information as the number of holes in every region, or the ratio between the area of holes and that of the region, etc, the damaged buildings can be separated from the undamaged, thus automatic detection of damaged buildings can be realized. Based on these characteristics, a new method to auto- matically detect the damage buildings by using regional structure and statistical information of texture is presented in the paper. In order to test its validity, 1-m-resolution iKonos merged image of the 2001 Bhuj earthquake and grayscale aerial photos of the 1976 Tangshan earthquake are selected as two examples to automatically detect the damaged buildings. Satisfied results are obtained.

In the high-resolution images, the undamaged buildings generally show a natural textural feature, while the dam- aged or semi-damaged buildings always exhibit some low-grayscale blocks because of their coarsely damaged sections. If we use a proper threshold to classify the By using such statistical information as the number of holes in every region, or the ratio between the area of ​​holes and that of the region, etc, the damaged buildings can be separated from the undamaged, thus automatic detection of damaged buildings can be realized. based on these characteristics, a new method to auto-matically detect the damage buildings by using regional structure and statistical information of texture is presented in the paper. validity, 1-m-resolution iKonos merged image of the 2001 Bhuj earthquake and grayscale aerial photos of the 1976 Tangshan earthquake are selected as two examples to automatically detect the damaged buildings. Satisfied results are obtained.