Various methods have been developed to detect and assess building's damages due to earthquakes using remotely sensed data.After the launch of the high resolution sensors such as IKONOS and QuickBird,it becomes rea...Various methods have been developed to detect and assess building's damages due to earthquakes using remotely sensed data.After the launch of the high resolution sensors such as IKONOS and QuickBird,it becomes realistic to identify damages on the scale of individual building.However the low accuracy of the results has often led to the use of visual interpretation techniques.Moreover,it is very difficult to estimate the degree of building damage(e.g.slight damage,moderate damage,or severe damage) in detail using the existing methods.Therefore,a novel approach integrating LiDAR data and high resolution optical imagery is proposed for evaluating building damage degree quantitatively.The approach consists of two steps:3D building model reconstruction and rooftop patch-oriented 3D change detection.Firstly,a method is proposed for automatically reconstructing 3D building models with precise geometric position and fine details,using pre-earthquake LiDAR data and high resolution imagery.Secondly,focusing on each rooftop patch of the 3D building models,the pre- and post-earthquake LiDAR points belonging to the patch are collected and compared to detect whether it was destroyed or not,and then the degree of building damage can be identified based on the ratio of the destroyed rooftop patches to all rooftop patches.The novelty of the proposed approach is to detect damages on the scale of building's rooftop patch and realize quantitative estimation of building damage degree.展开更多
Rapid building damage assessment following an earthquake is important for humanitarian relief and disaster emergency responses.In February 2023,two magnitude-7.8 earthquakes struck Turkey in quick succession,impacting...Rapid building damage assessment following an earthquake is important for humanitarian relief and disaster emergency responses.In February 2023,two magnitude-7.8 earthquakes struck Turkey in quick succession,impacting over 30 major cities across nearly 300 km.A quick and comprehensive understanding of the distribution of building damage is essential for e fficiently deploying rescue forces during critical rescue periods.This article presents the training of a two-stage convolutional neural network called BDANet that integrated image features captured before and after the disaster to evaluate the extent of building damage in Islahiye.Based on high-resolution remote sensing data from WorldView2,BDANet used predisaster imagery to extract building outlines;the image features before and after the disaster were then combined to conduct building damage assessment.We optimized these results to improve the accuracy of building edges and analyzed the damage to each building,and used population distribution information to estimate the population count and urgency of rescue at different disaster levels.The results indicate that the building area in the Islahiye region was 156.92 ha,with an affected area of 26.60 ha.Severely damaged buildings accounted for 15.67%of the total building area in the affected areas.WorldPop population distribution data indicated approximately 253,297,and 1,246 people in the collapsed,severely damaged,and lightly damaged areas,respectively.Accuracy verification showed that the BDANet model exhibited good performance in handling high-resolution images and can be used to directly assess building damage and provide rapid information for rescue operations in future disasters using model weights.展开更多
基金Supported by the National Natural Science Foundation of China (Grant No.40701117)Research Foundation for the Doctoral Program of Higher Education of China (Grant No.20070284001)+2 种基金the National Basic Research Program of China ("973" Program) (Grant No.2006CB701300)Foundation for University Key Teacher by the Chinese Ministry of Educationthe "985" Project of Nanjing University
文摘Various methods have been developed to detect and assess building's damages due to earthquakes using remotely sensed data.After the launch of the high resolution sensors such as IKONOS and QuickBird,it becomes realistic to identify damages on the scale of individual building.However the low accuracy of the results has often led to the use of visual interpretation techniques.Moreover,it is very difficult to estimate the degree of building damage(e.g.slight damage,moderate damage,or severe damage) in detail using the existing methods.Therefore,a novel approach integrating LiDAR data and high resolution optical imagery is proposed for evaluating building damage degree quantitatively.The approach consists of two steps:3D building model reconstruction and rooftop patch-oriented 3D change detection.Firstly,a method is proposed for automatically reconstructing 3D building models with precise geometric position and fine details,using pre-earthquake LiDAR data and high resolution imagery.Secondly,focusing on each rooftop patch of the 3D building models,the pre- and post-earthquake LiDAR points belonging to the patch are collected and compared to detect whether it was destroyed or not,and then the degree of building damage can be identified based on the ratio of the destroyed rooftop patches to all rooftop patches.The novelty of the proposed approach is to detect damages on the scale of building's rooftop patch and realize quantitative estimation of building damage degree.
基金supported by the Third Xinjiang Scientific Expedition Program(Grant 2022xjkk0600)。
文摘Rapid building damage assessment following an earthquake is important for humanitarian relief and disaster emergency responses.In February 2023,two magnitude-7.8 earthquakes struck Turkey in quick succession,impacting over 30 major cities across nearly 300 km.A quick and comprehensive understanding of the distribution of building damage is essential for e fficiently deploying rescue forces during critical rescue periods.This article presents the training of a two-stage convolutional neural network called BDANet that integrated image features captured before and after the disaster to evaluate the extent of building damage in Islahiye.Based on high-resolution remote sensing data from WorldView2,BDANet used predisaster imagery to extract building outlines;the image features before and after the disaster were then combined to conduct building damage assessment.We optimized these results to improve the accuracy of building edges and analyzed the damage to each building,and used population distribution information to estimate the population count and urgency of rescue at different disaster levels.The results indicate that the building area in the Islahiye region was 156.92 ha,with an affected area of 26.60 ha.Severely damaged buildings accounted for 15.67%of the total building area in the affected areas.WorldPop population distribution data indicated approximately 253,297,and 1,246 people in the collapsed,severely damaged,and lightly damaged areas,respectively.Accuracy verification showed that the BDANet model exhibited good performance in handling high-resolution images and can be used to directly assess building damage and provide rapid information for rescue operations in future disasters using model weights.
