结合PolSAR影像纹理特征分析提取倒塌建筑物

利用震后1景极化SAR影像提取倒塌建筑物是一种快速有效的灾害调查手段。倒塌建筑和倾斜建筑物在PolSAR影像中的散射特征相似,易造成建筑物倒塌率的过度评估。由于倒塌建筑和倾斜建筑的纹理特征有较大差异,将利用这种纹理差异来解决倒塌建筑和倾斜建筑的混分问题。通过实验发现均值、同质性、熵及相关性4种基于灰度共生矩阵(Gray-Level Co-occurrence Matrix,GLCM)的纹理特征能够有效区分倾斜建筑和倒塌建筑,故利用这4种纹理特征提取倒塌建筑中混杂的倾斜建筑,从而降低倒塌建筑的虚警率。以玉树地震为例,提取城区的建筑物震害信息,实验证明该方法能够大幅提高建筑物震害评估精度。     

基于遥感影像不透水层估算的震后城区损坏面积评估

地震灾害评估对于抗震救灾具有重要的现实意义,传统的灾害评估方法大多基于震后实地的统计数据进行,在数据获取的现势性和灾害评估效率方面存在问题,针对这一不足,结合遥感数据的特点,提出了一种基于遥感不透水层估算的地震灾后城区损坏面积评估方法。该方法首先对地震前后玉树地区的两幅中分辨率遥感影像进行预处理,然后基于V-I-S模型,利用线性光谱混合分析方法,分别对地震前后震区遥感影像进行端元提取,获得不透水层的丰度图,最后通过计算地震前后不透水层像元个数,进行地震灾后城区损坏面积的评估。通过精度分析可以看出:该方法可以快速及时地获〖JP3〗取城市区域建筑物、公路等重要地物的宏观损坏面积情况,为灾后重建和震后决策提供了一定的依据。     

Detection of collapsed buildings caused by the 1999 Izmit,Turkey earthquake through digital analysis of post-event aerial photographs

In this study, the post-earthquake aerial photographs were digitally processed and analysed to detect collapsed buildings caused by the Izmit, Turkey earthquake of 17 August 1999. The selected area of study encloses part of the city of Golcuk, which is one of the urban areas most strongly hit by the earthquake. The analysis relies on the idea that if a building is collapsed, then it will not have corresponding shadows. The boundaries of the buildings were available and stored in a Geographical Information System (GIS) as vector polygons. The vector building polygons were used to match the shadow casting edges of the buildings with their corresponding shadows and to perform analyses in a building-specific manner. The shadow edges of the buildings were detected through a Prewitt edge detection algorithm. For each building, the agreement was then measured between the shadow producing edges of the building polygons and the thresholded edge image based on the percentage of shadow edge pixels. If the computed percentage value was below a preset threshold then the building being assessed was declared as collapsed. Of the 80 collapsed buildings, 74 were detected correctly, providing 92.50% producer's accuracy. The overall accuracy was computed as 96.15%. The results show that the detection of the collapsed buildings through digital analysis of post-earthquake aerial photographs based on shadow information is quite encouraging. It is also demonstrated that determining the optimum threshold value for separating the collapsed from uncollapsed buildings is important.     

面向对象的损毁建筑物提取

地震灾害已经成为一种频发的自然灾害之一,在震后的灾害评估中,建筑物的倒塌情况是很重要的一项指标。本文用GeoEye影像提取海地地震中的损毁建筑物。由于海地地震时发生倒塌的房子大多处于比较老旧的地区,房屋比较密集,而且房顶结构也比较复杂,我们采取了一种基于规则集的方法通过分类将倒塌建筑物逐步与其他各种地物区分开来。即在影像多尺度分割的基础上,结合纹理特征及几何特征,通过规则集的方法构成分类树提取损毁房屋。另外在进行植被剔除时本文根据影像的特点提出了一种新的植被指数geo-NDVI,最后根据目视解译的结果对分类的结果进行了对比。     

Structural damage detection using bi-temporal optical satellite images

Multi-temporal satellite imagery is now available at sub-metre accuracy and has been found to be very useful for performing rapid damage assessment on human settlement areas affected by large-scale disasters. In this article, a method of formulating structural damage detection measures based on pre- and post-disaster satellite images is proposed. To validate the proposed damage measures, building-based structural damage assessment is conducted. First, their effectiveness in representing multilevel structural damage is demonstrated using synthetic patterns of building damage. Second, the damage classification accuracy is evaluated by means of a pattern classification approach applied to a pair of bi-temporal satellite images, wherein earthquake damage to hundreds of buildings is assessed. The article concludes that the proposed damage detection measures, which are conceptually simple and computationally efficient, outperform traditional measures, such as linear correlation coefficients.     

视角和光照显著变化时的变化检测方法研究

探讨使用计算机视觉的最新方法来解决基于两幅高空间分辨率光学遥感图像的城市变化检测问题. 基本原理是通过提取聚类出现的变化直线段群来提取城市变化, 重点研究了拍摄视角和光照条件显著变化时的几个主要问题. 提出了一种基于多种类型图像特征的匹配方法来提取无变化建筑的顶部区域, 结合几何约束引入了变化盲区的概念以处理高层建筑在不同视角和光照下的图像不同现象. 使用真实遥感图像进行实验, 在视角和光照显著变化时仍可取得满意的变化检测结果.     

Integration of super-pixel segmentation and deep-learning methods for evaluating earthquake-damaged buildings using single-phase remote sensing imagery

ABSTRACT

Rapid identification of post-earthquake collapsed buildings can be used to conduct immediate damage assessments (scope and extent), which could potentially be conducive to the formulation of emergency response strategies. Up to the present, the assessments of earthquake damage are mainly achieved through artificial field investigations, which are time-consuming and cannot meet the urgent requirements of quick-response emergency relief allocation. In this research study, an intelligent assessment method based on deep-learning, super-pixel segmentation, and mathematical morphology was proposed to evaluate the damage degrees of earthquake-damaged buildings. This method firstly utilized the Deeplab v2 neural network to obtain the initial damaged building areas. Then, the simple linear iterative cluster (SLIC) method was employed to segment the test images so as to accurately extract the area boundaries of the earthquake-damaged buildings. Next, the images subdivided by SLIC can be merged according to the initial damaged building areas identified by Deeplab v2 neural network. Finally, a mathematical morphological method was introduced to eliminate the background noise. Experimental results demonstrated that the proposed algorithm was superior to others in both convergent speed and accuracy. Besides, its parameter selection was flexible and easily realized which was of great significance to earthquake damage assessments and provided valuable guidance for the formulation of future emergency response plans after earthquake events.     

Post‐earthquake building collapse: a comparison of government statistics and estimates derived from SPOT HRVIR data

On 17 August 1999 at 3:02 a.m. local time the Izmit earthquake occurred on the North Anatolian Fault Zone (NAFZ) in north‐west Turkey. This earthquake caused considerable damage in the urban areas of Izmit, Adapazari (Sakarya), Golcuk and Yalova. This study used three different data sources to estimate the proportion of Adapazari that contained collapsed buildings: (i) government statistics on the number of collapsed buildings; (ii) the difference between pre‐ and post‐earthquake land cover estimated from classified SPOT HRVIR XI images; and (iii) land cover estimated from density‐sliced SPOT HRVIR Panchromatic image recorded after the earthquake. The results were similar at 16%, 16.1% and 15.5%, respectively. These were all slight overestimates; however, the remotely sensed estimates provided the spatial context of building collapse and in doing so highlighted areas of previously uncontrolled building.     

Building extraction from very high-resolution synthetic aperture radar images based on statistical and structural information fusion

To investigate the limits of building detection from very high-resolution (VHR) synthetic aperture radar (SAR) images, a new method, based on statistical and structural information fusion, is proposed in this paper. The proposed method contains two stages: First, using order statistics constant false alarm rate (OS-CFAR) and power ratio (PR) detectors, a set of detections are made. These detections have different statistical properties, compared to the other objects, and these properties are selected for discriminating buildings from clutters. Second, the morphological analysis is used for increasing the precision of the detection. In this stage, segments, which have the most similarities to buildings in terms of shape and size, are extracted via various structural elements (SEs). The final result is obtained by fusing the two sets of detections. The experimental results on the four real VHR SAR images show that the proposed method has a high detection rate (DR) and low false alarm rate (FAR).     

Detection of building damage caused by Van Earthquake using image and Digital Surface Model (DSM) difference

An earthquake occurred at Van City on 23 October 2011 at 13:41 local time with the local magnitude (ML) 6.7 and moment magnitude (Mw) 7.0. Approximately seventeen thousand buildings collapsed or were damaged, and 644 people died because of the main earthquake and its aftershocks. One hundred and fifty-two aerial images of the earthquake area covering 1,296 km² were taken with an UltraCam X large format digital aerial camera with 30 cm ground sample distance (GSD) just one day after the earthquake on 24 October 2011. This study attempted to detect damaged buildings automatically with the help of pre and post-earthquake aerial images. With the image and digital surface model (DSM), different methods are used for damage detection, but it was seen that these methods are not satisfactory. So, a novel approach that uses the geometric characteristics of buildings, i.e. area and area to perimeter ratios, was introduced to improve the results. The results show that ‘Area/Perimeter’ approach improves the damage detection accuracy considerably.     

Building detection in an urban area using lidar data and QuickBird imagery

This article presents a hierarchical approach to detect buildings in an urban area through the combined usage of lidar data and QuickBird imagery. A normalized digital surface model (nDSM) was first generated on the basis of the difference between a digital surface model and the corresponding digital terrain model. Then, ground objects were removed according to a height threshold. In consideration of the relief displacement effect in very high resolution remote-sensing imagery, we segmented the nDSM by the region-growing method and used the overlap ratio to avoid over-removing building objects. Finally, the region size and spatial relation of trees and buildings were used to filter out trees occluded by buildings based on an object-based classification. Compared with previous methods directly using the normalized difference vegetation index (NDVI), our method improved the completeness from 85.94% to 90.20%. The overall accuracy of the buildings detected using the proposed method can be up to 94.31%, indicating the practical applicability of the method.     

Use of lidar-derived NDTI and intensity for rule-based object-oriented extraction of building footprints

Buildings play an essential role in urban intra-construction, planning, and climate. The precise knowledge of building footprints not only serves as a primary source for interpreting complex urban characteristics, but also provides regional planners with more realistic and multidimensional scenarios for urban management. The recently developed airborne light detection and ranging (lidar) technology provides a very promising alternative for building-footprint measurement. In this study, lidar intensity data, a normalized digital surface model (nDSM) of the first and last returns, and the normalized difference tree index (NDTI) derived from the two returns are used to extract building footprints using rule-based object-oriented classification. The study area is chosen in London, Ontario, based on the various types of buildings surrounded by trees. An integrated segmentation approach and a hierarchical rule-based classification strategy are proposed during the process. The results indicate that the proposed object-based classification is a very effective semi-automatic method for building-footprint extraction, with buildings and trees successfully separated. An overall accuracy of 94.0% and a commission error of 6.3% with a kappa value of 0.84 are achieved. Lidar-derived NDTI and intensity data are of great importance in object-based building extraction, and the kappa value of the proposed method is double that of the object-based method without NDTI or intensity.     

基于多纹理特征融合的震后SAR图像倒塌建筑物信息提取

合成孔径雷达（SAR）凭借其全天候观测能力以及SAR图像中丰富的纹理信息,在震后建筑物倒塌评估中发挥了重要作用。针对SAR图像中倒塌建筑物纹理特征多样但利用率较低,且特征信息冗余的问题,提出一种基于主成分分析的SAR图像多纹理特征分类方法。该方法基于灰度直方图、灰度共生矩阵、局部二值模式、Gabor滤波器提取了26种纹理特征信息,构建主成分变量进行多维特征优选与降维融合,通过随机森林分类算法提取建筑物的倒塌信息。以2016年日本熊本地震为例验证了该方法的有效性,结果显示其提取精度高达79.85%,倒塌建筑物的识别效率有所提高,分类结果优于单种纹理特征提取方法及多种纹理特征组合提取法,可用于震后建筑物震害信息的快速提取。     

Detection of collapsed buildings with the aerial images captured from UAV基于低空无人机航拍图像的坍塌建筑物自动探测方法

In this paper, we present a method of detecting the collapsed buildings with the aerial images which are captured by an unmanned aerial vehicle (UAV) for the postseismic evaluation. Different from the conventional methods that apply the satellite images or the high-altitude UAV for the coarse disaster evaluation over large area, the purpose of this work is to achieve the accurate detection of collapsed buildings in small area from low altitude. By combining the motion and appearance features of collapsed buildings extracted from successive aerial images, each pixel in the input image will be measured by a statistical method where the background pixels will be penalized and the ones of collapsed buildings will be assigned with high value. The candidates of collapsed buildings will be established by integrating the extracted feature points into local groups with the online clustering algorithm. To reduce the false alarm caused by the complex background noise, each predicted candidate will be further verified by the temporal tracking framework where both the trajectory and the appearance of a candidate will be measured. The candidate of collapsed buildings that can survive through long time will be considered as true positive, otherwise rejected as a false alarm. Through extensive experiments, the efficiency and the effectiveness of proposed algorithm have been proved.     

Detecting damaged building parts in earthquake-damaged areas using differential seeded region growing

Acquiring information about earthquake-damaged buildings is essential for effective rescue and restoration operations. Building damage must be assessed to provide detailed information regarding the location and proportion of damage to individual buildings. Automatic processing of damage assessment is also critical in hastening relief efforts. Therefore, we propose a new method for automatically extracting damaged building parts and quantitatively assessing the damage to individual buildings caused by earthquakes. The proposed method consists of four parts: generating differential information, differential seeded region growing (DSRG), rule-based earthquake damage analysis, and accuracy assessment. First, differential information is automatically derived to extract the damage candidates. The damage candidates are then used as seed points for the region growing process to extract damaged building parts without requiring intervention by a human analyst. Then, designed automated extraction rules based on the condition of the collapsed or crushed buildings are used on the DSRG results. We applied the proposed method to both a residential area and a business area in Port-au-Prince, Haiti, and evaluated its accuracy using a visual comparison, a location-based assessment, and a proportion-based assessment. The results of the visual comparison were similar to the reference data, exhibiting location accuracies of 86% and 89% for the chosen residential and business areas, respectively. An assessment of the damage proportion to individual buildings was performed, which showed that the proposed method achieved accuracies of 81% and 84% for the residential and business areas, respectively, and was highly correlated with the reference data. The proposed method can accurately estimate damaged building parts, which can accelerate rapid relief actions in earthquake-damaged areas. In addition, the proposed method promotes cost-effective relief actions because it filters out many intact buildings without omitting damaged buildings.     

A hypergraph-based context-sensitive representation technique for VHR remote-sensing image change detection

This article presents a novel semi-supervised change detection approach for very-high-resolution (VHR) remote-sensing images. The proposed approach aims at extracting the change information by making full use of the context-sensitive relationships among pixels in the images. This is accomplished via a context-sensitive image representation technique based on hypergraph model. First, each temporal image is modelled as a hypergraph that utilizes a set of hyperedges to capture the context-sensitive properties of pixels in the image. Second, the difference in the bi-temporal images is measured by both the similarity and the consistency between the two hypergraphs. Finally, the changes are separated from the unchanged ones by a hypergraph-based semi-supervised classifier on the difference image. Experimental results obtained on different VHR remote-sensing data sets demonstrate the effectiveness of the proposed approach.     

Damage assessment in urban areas using post-earthquake airborne PolSAR imagery

Synthetic aperture radar (SAR) has often been used in earthquake damage assessment due to its extreme versatility and almost all-weather, day-and-night capability. In this article, we demonstrate the potential to use only post-event, high-resolution airborne polarimetric SAR (PolSAR) imagery to estimate the damage level at the block scale. Intact buildings with large orientation angles have a similar scattering mechanism to collapsed buildings; they are all volume-scattering dominant and reflection asymmetric, which seriously hampers the process of damage assessment. In this article, we propose a new damage assessment method combining polarimetric and spatial texture information to eliminate this deficiency. In the proposed method, the normalized circular-pol correlation coefficient is used first to identify intact buildings aligned parallel with the flight direction of the radar. The ‘homogeneity’ feature of the grey-level co-occurrence matrix (GLCM) is then introduced to distinguish building patches with large orientation angles from the severely damaged class. Furthermore, a new damage assessment index is also introduced to handle the assessment at the level of the block scale. To demonstrate the effectiveness of the proposed approach, the high-resolution airborne PolSAR imagery acquired after the earthquake that hit Yushu County, Qinghai Province of China, is investigated. By comparison with the damage validation map, the results confirm the validity of the proposed method and the advantage of further improving the assessment accuracy without external ancillary optical or SAR data.     

A graph-based approach for the co-registration refinement of very-high-resolution imagery and digital line graphic data

Co-registration refinement of very-high-resolution (VHR) imagery and digital-line-graphic (DLG) data is an important procedure before data fusion and analysis. However, existing approaches either make little consideration of topological relations between features or have to extract complete objects, which is very challenging. In this study, to overcome the drawbacks mentioned above, a graph-based approach is presented for the co-registering of VHR imagery and DLG data. Our proposed method uses a graph to represent the topological relations between buildings in both data sources, which helps match buildings in the two data sources and compute the affine transformation parameters. The proposed method is validated on three diverse VHR images, and two objective evaluation metrics (correctness and quality rate) are computed to evaluate its performance. It is shown that correctness and quality rate are averagely improved by 37.3% and 46.7%, respectively, after co-registration. These results indicate that our proposed method is effective in the co-registration of VHR imagery and DLG data.     

An enhanced 3D model and generative adversarial network for automated generation of horizontal building mask images and cloudless aerial photographs

Information extracted from aerial photographs is widely used in the fields of urban planning and design. An effective method for detecting buildings in aerial photographs is to use deep learning to understand the current state of a target region. However, the building mask images used to train the deep learning model must be manually generated in many cases. To overcome this challenge, a method has been proposed for automatically generating mask images by using textured three-dimensional (3D) virtual models with aerial photographs. Some aerial photographs include clouds, which degrade image quality. These clouds can be removed by using a generative adversarial network (GAN), which leads to improvements in training quality. Therefore, the objective of this research was to propose a method for automatically generating building mask images by using 3D virtual models with textured aerial photographs. In this study, using GAN to remove clouds in aerial photographs improved training quality. A model trained on datasets generated by the proposed method was able to detect buildings in aerial photographs with IoU = 0.651.     

True orthoimage generation in urban areas with very tall buildings

The orthoimage usually serves as a valuable base layer in GIS. With an increasing demand in many urban GIS applications, orthoimages in urban areas are required to represent spatial objects in their true positions. However, the traditional methods for orthoimage generation did not consider features (e.g. occlusion, shadow, etc.) of spatial objects (e.g. bridges and buildings), resulting in that spatial objects in the created orthoimages cannot be located in their true positions. This paper presents our research and experimental results of true orthoimage generation in extremely tall urban areas using lidar and multi-view large-scale aerial images. Lidar data are used for the extraction of an urban digital surface model (DSM), further for the extraction of a digital building model (DBM) and a digital terrain model (DTM). Data structure and a data model for managing urban spatial objects, such as buildings and bridges, are developed. The photogrammetric geometry is used for the detection of occluded and shadowed areas in true orthoimage generation. For the occluded and shadowed areas, lost information is compensated from a conjugate area in adjacent images, for which a new mosaicking method, which automatically chooses the 'best' imagery and automatically optimizes the seam line, has been developed. Experimental results from central Denver, Colorado and Lower Manhattan, New York City demonstrated that the proposed true orthoimage generation scheme in this paper is capable of truly orthorectifying the relief displacement in aerial images and significantly reducing occlusion and shadow defects.