scholarly journals Use of Digital Surface Model Constructed from Digital Aerial Images to Detect Collapsed Buildings during Earthquake

2011 ◽  
Vol 14 ◽  
pp. 552-558 ◽  
Author(s):  
Yoshihisa Maruyama ◽  
Akira Tashiro ◽  
Fumio Yamazaki
Keyword(s):  
Aerial Images ◽  
Surface Model ◽  
Digital Surface Model ◽  
Collapsed Buildings

DETECTION OF COLLAPSED BUILDINGS DUE TO EARTHQUAKES USING A DIGITAL SURFACE MODEL CONSTRUCTED FROM AERIAL IMAGES

2014 ◽  
Vol 08 (01) ◽  
pp. 1450003 ◽  
Author(s):  
YOSHIHISA MARUYAMA ◽  
AKIRA TASHIRO ◽  
FUMIO YAMAZAKI
Keyword(s):  
Aerial Images ◽  
Surface Model ◽  
Digital Surface Model ◽  
Severe Damage ◽  
Aerial Photogrammetry ◽  
Surface Models ◽  
Event Models ◽  
Collapsed Buildings

The buildings that collapsed during the 2007 Niigata Chuetsu-oki earthquake are detected based on aerial photogrammetry using digital aerial images. The digital surface models (DSMs) in the area where severe damage to buildings was observed after the earthquake are constructed using digital aerial camera images. Pre- and post-event aerial images are employed to obtain the DSMs in this study. The differences in building heights between the pre- and post-event models are considered to detect collapsed buildings and the accuracy of the method is discussed in this paper. The results indicate that the collapsed buildings can be detected and undamaged buildings can also be correctly recognized by the proposed method.

scholarly journals BUILDING OUTLINE EXTRACTION FROM AERIAL IMAGERY AND DIGITAL SURFACE MODEL WITH A FRAME FIELD LEARNING FRAMEWORK

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 487-493
Author(s):  
X. Sun ◽  
W. Zhao ◽  
R. V. Maretto ◽  
C. Persello
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
Aerial Images ◽  
Surface Model ◽  
Digital Surface Model ◽  
Frame Field ◽  
Learning Framework ◽  
Elevation Data ◽  
3D Information ◽  
Direction Information

Abstract. Deep learning-based semantic segmentation models for building delineation face the challenge of producing precise and regular building outlines. Recently, a building delineation method based on frame field learning was proposed by Girard et al. (2020) to extract regular building footprints as vector polygons directly from aerial RGB images. A fully convolution network (FCN) is trained to learn simultaneously the building mask, contours, and frame field followed by a polygonization method. With the direction information of the building contours stored in the frame field, the polygonization algorithm produces regular outlines accurately detecting edges and corners. This paper investigated the contribution of elevation data from the normalized digital surface model (nDSM) to extract accurate and regular building polygons. The 3D information provided by the nDSM overcomes the aerial images’ limitations and contributes to distinguishing the buildings from the background more accurately. Experiments conducted in Enschede, the Netherlands, demonstrate that the nDSM improves building outlines’ accuracy, resulting in better-aligned building polygons and prevents false positives. The investigated deep learning approach (fusing RGB + nDSM) results in a mean intersection over union (IOU) of 0.70 in the urban area. The baseline method (using RGB only) results in an IOU of 0.58 in the same area. A qualitative analysis of the results shows that the investigated model predicts more precise and regular polygons for large and complex structures.

scholarly journals Updating Geospatial Data by Creating a High Resolution Digital Surface Model

2018 ◽  
Vol 8 (2) ◽  
pp. 51-58 ◽  
Author(s):  
Iuliana Adriana Cuibac Picu
Keyword(s):  
Laser Scanning ◽  
Smart Cities ◽  
Geographic Information ◽  
Geospatial Data ◽  
Aerial Images ◽  
Aerial Photographs ◽  
Planning System ◽  
Surface Model ◽  
Digital Surface Model ◽  
Digital Terrain

Abstract Smart Cities are no longer just an aspiration, they are a necessity. For a city to be smart, accurate data collection or improvement the existing ones is needed, also an infrastructure that allows the integration of heterogeneous geographic information and sensor networks at a common technological point. Over the past two decades, laser scanning technology, also known as LiDAR (Light Detection and Ranging), has become a very important measurement method, providing high accuracy data and information on land topography, vegetation, buildings, and so on. Proving to be a great way to create Digital Terrain Models. The digital terrain model is a statistical representation of the terrain surface, including in its dataset the elements on its surface, such as construction or vegetation. The data use in the following article is from the LAKI II project “Services for producing a digital model of land by aerial scanning, aerial photographs and production of new maps and orthophotomaps for approximately 50 000 sqKm in 6 counties: Bihor, Arad, Hunedoara, Alba, Mures, Harghita including the High Risk Flood Zone (the border area with the Republic of Hungary in Arad and Bihor)”, which are obtained through LiDAR technology with a point density of 8 points per square meter. The purpose of this article is to update geospatial data with a higher resolution digital surface model and to demonstrate the differences between a digital surface models obtain by aerial images and one obtain by LiDAR technology. The digital surface model will be included in the existing geographic information system of the city Marghita in Bihor County, and it will be used to help develop studies on land use, transport planning system and geological applications. It could also be used to detect changes over time to archaeological sites, to create countur lines maps, flight simulation programs, or other viewing and modelling applications.

scholarly journals Using Total Probability in Image Template Matching

2019 ◽  
Vol 17 (3) ◽  
pp. 347-357
Author(s):  
Haval Sadeq
Keyword(s):  
Computer Vision ◽  
Template Matching ◽  
Cross Correlation ◽  
Threshold Value ◽  
Aerial Images ◽  
Geometric Distortion ◽  
Surface Model ◽  
Total Probability ◽  
Main Task ◽  
Digital Surface Model

Image template matching is a main task in photogrammetry and computer vision. The matching can be used to automatically determine the 3D coordinates of a point. A firstborn image matching method in fields of photogrammetry and computer vision is area-based matching, which is based on correlation measuring that uses normalised cross-correlation. However, this method fails at a discontinuous edge and at the area of low illumination or at geometric distortion because of changes in imaging location. Thus, these points are considered outliers. The proposed method measures correlations, which is based on normalised cross-correlation, at each point by using various sizes of window and then considering the probability of correlations for each window. Thereafter, the determined probability values are integrated. On the basis of a specific threshold value, the point of maximum total probability correlation is recognised as a corresponding point. The algorithm is applied to aerial images for Digital Surface Model (DSM) generation. Results show that the corresponding points are identified successfully at different locations, especially at a discontinuous point, and that a Digital Surface Model of high resolution is generated.

scholarly journals Generation of 2D Land Cover Maps for Urban Areas Using Decision Tree Classification

2014 ◽  
Vol II-7 ◽  
pp. 15-21 ◽  
Author(s):  
J. Höhle
Keyword(s):  
Land Cover ◽  
Decision Tree ◽  
Urban Areas ◽  
Aerial Images ◽  
Surface Model ◽  
Digital Surface Model ◽  
Decision Tree Classification ◽  
Map Generation ◽  
Land Cover Map ◽  
False Colour

A 2D land cover map can automatically and efficiently be generated from high-resolution multispectral aerial images. First, a digital surface model is produced and each cell of the elevation model is then supplemented with attributes. A decision tree classification is applied to extract map objects like buildings, roads, grassland, trees, hedges, and walls from such an "intelligent" point cloud. The decision tree is derived from training areas which borders are digitized on top of a false-colour orthoimage. The produced 2D land cover map with six classes is then subsequently refined by using image analysis techniques. The proposed methodology is described step by step. The classification, assessment, and refinement is carried out by the open source software "R"; the generation of the dense and accurate digital surface model by the "Match-T DSM" program of the Trimble Company. A practical example of a 2D land cover map generation is carried out. Images of a multispectral medium-format aerial camera covering an urban area in Switzerland are used. The assessment of the produced land cover map is based on class-wise stratified sampling where reference values of samples are determined by means of stereo-observations of false-colour stereopairs. The stratified statistical assessment of the produced land cover map with six classes and based on 91 points per class reveals a high thematic accuracy for classes "building" (99 %, 95 % CI: 95 %-100 %) and "road and parking lot" (90 %, 95 % CI: 83 %-95 %). Some other accuracy measures (overall accuracy, kappa value) and their 95 % confidence intervals are derived as well. The proposed methodology has a high potential for automation and fast processing and may be applied to other scenes and sensors.

Sign in / Sign up

Export Citation Format

Share Document