عنوان انگلیسی: Earthquake-Induced Building Damage Detection with Post-Event Sub-Meter VHR TerraSAR-X Staring Spotlight Imagery
سال نشر: ۲۰۱۶
نویسنده: Lixia Gong,Chao Wang,Fan Wu,Jingfa Zhang,Hong Zhang,Qiang Li
تعداد صفحه فارسی: ۳۸ – تعداد صفحه انگلیسی: ۲۱
دانشگاه: Institute of Crustal Dynamics, China Earthquake Administration, Beijing 100085, China;
نشریه: Process Safety and Environmental Protection
کیفیت ترجمه: ترجمه پلاس
چکیده
چکیده: در مقایسه با حسگرهای نوری، رادارهای دهانه ترکیبی (SAR) به دلیل توانایی آن ها در تهیه نقشه مناطقی که تحت تاثیر زلزله قرار گرفته اند به طور مستقل از شرایط آب و هوایی و روشنایی خورشید، می توانند اطلاعات مهمی درباره خرابی مهیا نمایند. در سال ۲۰۱۳، حالت جدیدی از TerraSAR-X تحت عنوان نورافکن خیره (ST) که دقت آزیموت آن تا ۰.۲۴ متر افزایش یافته بود، برای استفاده در کاربرد های مختلف معرفی گردید. این منبع داده ها استخراج اطلاعات جزئی درباره تک تک ساختمان ها را ممکن نمود. در این مقاله، ما مفهوم جدیدی برای ارزیابی خرابی ساختمان ها با استفاده از تصاویر SAR بعد از وقوع با وضوح بسیار زیاد (VHR) با دقت زیر متر و نقشه رد پای ساختمان ارائه می دهیم. با داشتن نقشه رد پای ساختمان، رد پای اصلی ساختمان در تصاویر SAR می تواند مکان یابی شود. بر اساس تحلیل تصویر یک ساختمان در تصاویر SAR، ویژگی های ردپای یک ساختمان می تواند به منظور شناسایی ساختمان های سر پا و تخریب شده استخراج شود. سه رده بندی کننده یادگیری ماشین، شامل جنگل تصادفی (RF)، ماشین بردار پشتیبانی (SVM)، و K نزدیک ترین همسایه (K-NN) در آزمایشات
Abstract
Compared with optical sensors, Synthetic Aperture Radar (SAR) can provide important
damage information due to its ability to map areas affected by earthquakes independently from
weather conditions and solar illumination. In 2013, a new TerraSAR-X mode named staring spotlight
(ST), whose azimuth resolution was improved to 0.24 m, was introduced for various applications.
This data source made it possible to extract detailed information from individual buildings. In this
paper, we present a new concept for individual building damage assessment using a post-event
sub-meter very high resolution (VHR) SAR image and a building footprint map. With the building
footprint map, the original footprints of buildings can be located in the SAR image. Based on the
building imaging analysis of a building in the SAR image, the features in the building footprint can be
extracted to identify standing and collapsed buildings. Three machine learning classifiers, including
random forest (RF), supp
damage information due to its ability to map areas affected by earthquakes independently from
weather conditions and solar illumination. In 2013, a new TerraSAR-X mode named staring spotlight
(ST), whose azimuth resolution was improved to 0.24 m, was introduced for various applications.
This data source made it possible to extract detailed information from individual buildings. In this
paper, we present a new concept for individual building damage assessment using a post-event
sub-meter very high resolution (VHR) SAR image and a building footprint map. With the building
footprint map, the original footprints of buildings can be located in the SAR image. Based on the
building imaging analysis of a building in the SAR image, the features in the building footprint can be
extracted to identify standing and collapsed buildings. Three machine learning classifiers, including
random forest (RF), supp
محصولات مشابه
امتیاز شما:
(No Ratings Yet)
(No Ratings Yet) 2016a new TerraSAR-X mode named staring spotlight (ST)Compared with optical sensorsincluding random forest (RF)support vectorSynthetic Aperture Radar (SAR) can provide important damage information due to its ability to map areas affected by earthquakes independently from weather conditions and solar illumination. In 2013the features in the building footprint can be extracted to identify standing and collapsed buildings. Three machine learning classifiersthe original footprints of buildings can be located in the SAR image. Based on the building imaging analysis of a building in the SAR imagewas introduced for various applications. This data source made it possible to extract detailed information from individual buildings. In this paperwe present a new concept for individual building damage assessment using a post-event sub-meter very high resolution (VHR) SAR image and a building footprint map. With the building footprint mapwhose azimuth resolution was improved to 0.24 m