Search

Natural disasters have a significant impact on urban areas, resulting in loss of lives and urban services. Using satellite and aerial imagery, the rapid and automatic assessment of at-risk located buildings from can improve the overall disaster management system of urban areas. To do this, the definition, and the implementation of models with strong generalization, is very important. Starting from these assumptions, the authors proposed a deep learning approach based on the U-Net model to map buildings that fall into mapped landslide risk areas. The U-Net model is trained and validated using the Dubai's Satellite Imagery Dataset. The transferability of the model results are tested in three different urban areas within Calabria Region, Southern Italy, using natural color orthoimages and multi-source GIS data. The results show that the proposed methodology can detect and predict buildings that fall into landslide risk zones, with an appreciable transferability capability. During the prevention phase of emergency planning, this tool can support decision-makers and planners with the rapid identification of buildings located within risk areas, and during the post event phase, by assessing urban system conditions after a hazard occurs. [ABSTRACT FROM AUTHOR]

Land-use changes generally are becoming through to urban classes from natural land cover classes. Remote sensing is a standard technology for such monitoring systems. On the other hand, automatic or semi-automatic applications are becoming broader and broader in most fields with development artificial intelligence over time. Building extraction from aerial photos and satellite imagery through deep learning is a new era for observing planned and unplanned urbanization, land-use changes. Besides traditional image-process methods such as supervised and unsupervised classification, deep learning presents a robust and needs less operator process. In this experiment, a commonly shared dataset is used and the sensors are QuickBird, Gaofen-2, WorldView2 with a resolution of 0.6, 0.8, 0.5 meters. Bands are Red, Green, Blue, and Near-Infrared. The dataset was split into train, test, validation, and test parts. Deep learning approaches were conducted to the dataset of different Deeplabv3+ CNN models based on Xception, Resnet-50, ResNet-18, MobileNetv2 networks. The optimized parameters were determined by selecting variations of the training options (different batch sizes, epoch numbers, backbone types, etc.). In the training phase, validation info as training and loss functions were considered. After the training process, the test phase was conducted, and evolution metrics were calculated as mean F1 score, precision, recall, IoU, and global accuracy. According to the results, the models based on ResNet-18 network were yielded better among others. Results were shown as tables and evaluated quantitatively also with time performances of the models. [ABSTRACT FROM AUTHOR]

Accurate building extraction from remotely sensed data is difficult to perform automatically because of the complex environments and the complex shapes, colours and textures of buildings. Supervised deep-learning-based methods offer a possible solution to solve this problem. However, these methods generally require many high-quality, manually labelled samples to obtain satisfactory test results, and their production is time and labour intensive. For multimodal data with sufficient information, extracting buildings accurately in as unsupervised a manner as possible. Combining remote sensing images and LiDAR point clouds for unsupervised building extraction is not a new idea, but existing methods often experience two problems: (1) the accuracy of vegetation detection is often not high, which leads to limited building extraction accuracy, and (2) they lack a proper mechanism to further refine the building masks. We propose two methods to address these problems, combining aerial images and aerial LiDAR point clouds. First, we improve two recently developed vegetation detection methods to generate accurate initial building masks. We then refine the building masks based on the image feature consistency constraint, which can replace inaccurate LiDAR-derived boundaries with accurate image-based boundaries, remove the remaining vegetation points and recover some missing building points. Our methods do not require manual parameter tuning or manual data labelling, but still exhibit a competitive performance compared to 29 methods: our methods exhibit accuracies higher than or comparable to 19 state-of-the-art methods (including 8 deep-learning-based methods and 11 unsupervised methods, and 9 of them combine remote sensing images and 3D data), and outperform the top 10 methods (4 of them combine remote sensing images and LiDAR data) evaluated using all three test areas of the Vaihingen dataset on the official website of the ISPRS Test Project on Urban Classification and 3D Building Reconstruction in average area quality. These comparative results verify that our unsupervised methods combining multisource data are very effective. [ABSTRACT FROM AUTHOR]

Natural disasters have a significant impact on urban areas, resulting in loss of lives and urban services. Using satellite and aerial imagery, the rapid and automatic assessment of at-risk located buildings from can improve the overall disaster management system of urban areas. To do this, the definition, and the implementation of models with strong generalization, is very important. Starting from these assumptions, the authors proposed a deep learning approach based on the U-Net model to map buildings that fall into mapped landslide risk areas. The U-Net model is trained and validated using the Dubai’s Satellite Imagery Dataset. The transferability of the model results are tested in three different urban areas within Calabria Region, Southern Italy, using natural color orthoimages and multi-source GIS data. The results show that the proposed methodology can detect and predict buildings that fall into landslide risk zones, with an appreciable transferability capability. During the prevention phase of emergency planning, this tool can support decision-makers and planners with the rapid identification of buildings located within risk areas, and during the post event phase, by assessing urban system conditions after a hazard occurs.

Accurate building extraction from remotely sensed data is difficult to perform automatically because of the complex environments and the complex shapes, colours and textures of buildings. Supervised deep-learning-based methods offer a possible solution to solve this problem. However, these methods generally require many high-quality, manually labelled samples to obtain satisfactory test results, and their production is time and labour intensive. For multimodal data with sufficient information, extracting buildings accurately in as unsupervised a manner as possible. Combining remote sensing images and LiDAR point clouds for unsupervised building extraction is not a new idea, but existing methods often experience two problems: (1) the accuracy of vegetation detection is often not high, which leads to limited building extraction accuracy, and (2) they lack a proper mechanism to further refine the building masks. We propose two methods to address these problems, combining aerial images and aerial LiDAR point clouds. First, we improve two recently developed vegetation detection methods to generate accurate initial building masks. We then refine the building masks based on the image feature consistency constraint, which can replace inaccurate LiDAR-derived boundaries with accurate image-based boundaries, remove the remaining vegetation points and recover some missing building points. Our methods do not require manual parameter tuning or manual data labelling, but still exhibit a competitive performance compared to 29 methods: our methods exhibit accuracies higher than or comparable to 19 state-of-the-art methods (including 8 deep-learning-based methods and 11 unsupervised methods, and 9 of them combine remote sensing images and 3D data), and outperform the top 10 methods (4 of them combine remote sensing images and LiDAR data) evaluated using all three test areas of the Vaihingen dataset on the official website of the ISPRS Test Project on Urban Classification and 3D Building Reconstruction in average area quality. These comparative results verify that our unsupervised methods combining multisource data are very effective.

Detecting and localizing buildings is of primary importance in urban planning tasks. Automating the building extraction process, however, has become attractive given the dominance of Convolutional Neural Networks (CNNs) in image classification tasks. In this work, we explore the effectiveness of the CNN-based architecture U-Net and its variations, namely, the Residual U-Net, the Attention U-Net, and the Attention Residual U-Net, in automatic building extraction. We showcase their robustness in feature extraction and information processing using exclusively RGB images, as they are a low-cost alternative to multi-spectral and LiDAR ones, selected from the SpaceNet 1 dataset. The experimental results show that U-Net achieves a 91.9% accuracy, whereas introducing residual blocks, attention gates, or a combination of both improves the accuracy of the vanilla U-Net to 93.6%, 94.0%, and 93.7%, respectively. Finally, the comparison between U-Net architectures and typical deep learning approaches from the literature highlights their increased performance in accurate building localization around corners and edges.

A novel adaptive morphological attribute profile under object boundary constraint (AMAP–OBC) method is proposed in this study for automatic building extraction from high-resolution remote sensing (HRRS) images. By investigating the associated attributes in morphological attribute profiles (MAPs), the proposed method establishes corresponding relationships between AMAP–OBC and building characteristics in HRRS images. In the preprocessing step, the candidate object set is extracted by a group of rules for screening of non-building objects. Second, based on the proposed adaptive scale parameter extraction and object boundary constraint strategies, AMAP–OBC is conducted to obtain the initial building set. Finally, a further identification strategy with adaptive threshold combination is proposed to obtain the final building extraction results. Through experiments of multiple groups of HRRS images from different sensors, the proposed method shows outstanding performance in terms of automatic building extraction from diverse geographic objects in urban scenes.

Nowadays, advanced real-time visualization for location-based applications, such as vehicle navigation or mobile phone navigation, requires large scale 3D reconstruction of street scenes. This paper presents methods for generating photorealistic 3D city models from raw mobile laser scanning data, which only contain georeferenced XYZ coordinates of points, to enable the use of photorealistic models in a mobile phone for personal navigation. The main focus is on the automated processing algorithms for noise point filtering, ground and building point classification, detection of planar surfaces, and on the key points (e.g., corners) of building derivation. The test site is located in the Tapiola area, Espoo, Finland. It is an area of commercial buildings, including shopping centers, banks, government agencies, bookstores, and high-rise residential buildings, with the tallest building being 45 m in height. Buildings were extracted by comparing the overlaps of X and Y coordinates of the point clouds between the cutoff-boxes at different and transforming the top-view of the point clouds of each overlap into a binary image and applying standard image processing technology to remove the non-building points, and finally transforming this image back into point clouds. The purpose for using points from cutoff-boxes instead of all points for building detection is to reduce the influence of tree points close to the building facades on building extraction. This method can also be extended to transform point clouds in different views into binary images for various other object extractions. In order to ensure the building geometry completeness, manual check and correction are needed after the key points of building derivation by automated algorithms. As our goal is to obtain photorealistic 3D models for walk-through views, terrestrial images were captured and used for texturing building facades. Currently, fully automatic generation of high quality 3D models is still challenging due to occlusions in both the laser and image data and due to significant illumination changes between the images. Especially when the scene contains both trees and vehicles, fully automated methods cannot achieve satisfactory visual appearance. In our approach, we employed the existing software for texture preparation and mapping.

Vzdrževanje podatkov v topografskih bazah je ena od pomembnejših nalog organizacij, ki te podatkovne baze vodijo. Eden od pomembnih podatkovnih slojev v topografskih bazah so podatki o stavbah. V člankusta opisani metoda za samodejen zajem stavb iz digitalnega modela površja in multispektralnega ortofota ter uporaba rezultatov zajema za samodejno iskanje sprememb v topografskih bazah, v katerih se vodijo podatki o stavbah. Začetno masko stavb smo izdelali iz normaliziranega digitalnega modela površja (nDMP). Vegetacijo smo iz maske stavb izločili z modificiranim vegetacijskim indeksom, izračunanim iz infrardečega ortofota ob upoštevanju indeksa senc in teksture nDMP. Na končni maski smo stavbe vektorizirali z uporabo transformacije Radon. Rezultate samodejnega zajema stavb smo primerjali s katastrom stavb in dejanskim stanjem na terenu. Ssamodejnim postopkom smo našli 94,4 % vseh stavb na območju in ocenili, da je opisana metoda primerna za zajem podatkov o stavbah za topografske baze v merilih 1 : 10 000 in manj. Rezultat samodejnegaiskanja sprememb (popolnost 93,5 % in pravilnost 78,4 %) kaže, da je opisana metoda primerna za iskanje sprememb med podatki o stavbah : The update of topographic databases is an important task for organizations that maintain them. Building data are one of the important data types in topographic databases. The article describes a method for automatic building extraction from digital surfacemodel and multispectral orthophoto and the use of extraction results for the building change detection in the topographic database. The initial building mask was created from the normalized digital surface model (nDSM).Vegetation was eliminated from the building mask using a modified vegetation index calculated from the infrared orthophoto and also considering the shadow index and the nDMP texture. The finalbuilding mask was vectorised using Radon transform. The results of the automatic building extraction were compared to the building cadastre and the actual situation on the ground. The automatic methoddetected 94.4% of all buildings in the area. We concluded that the described method is appropriate for capturing of the building data for the topographic database in scales 1 : 10 000 and smaller. Automatic change detection results (completeness 93.5% and correctness 78.4%) indicate that the described method is appropriate for building change detection.

In recent years, the acquisition and processing techniques of high resolution Digital Surface Models (DSM) have been rapidly improved. Airborne LiDAR production as a well-known and high quality DSM is still unbeatable in elevation accuracy and highly produced dense point clouds. In this paper, the objective is to update an old but high quality DSM produced by LiDAR data using a DSM generated from high resolution stereo satellite images. A classification-base algorithm is proposed to extract building changes between DSMs in two epochs. For image classification procedure, the DSM and Worldview-2 orthorectified images have been used as input data for a fuzzy-based classification method. Then, extracted buildings are classified into unchanged, destroyed, new, and changed classes. In this study a dataset related to Munich city, has been utilized to test the experimental investigation. The implemented qualitative and quantitative assessments demonstrate high quality as well as high feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Building extraction from high resolution (HR) satellite imagery is one of the most significant issue for remote sensing community. Manual extraction process is onerous and time consuming that's why the improvement of the best automation is a crucial topic for the researchers. In this study, we aimed to expose the significant contribution of normalized digital surface model (nDSM) to the automatic building extraction from mono HR satellite imagery performing two-step application in an appropriate study area which includes various terrain formations. In first step, the buildings were manually and object-based automatically extracted from ortho-rectified pan-sharpened IKONOS and Quickbird HR imagery that have 1 m and 0.6 m ground sampling distances (GSD), respectively. Next, the nDSM was created using available aerial photos to represent the height of individual non-terrain objects and used as an additional channel for segmentation. All of the results were compared with the reference data, produced from aerial photos that have 5 cm GSD. With the contribution of nDSM, the number of extracted buildings was increased and more importantly, the number of falsely extracted buildings occurred by automatic extraction errors was sharply decreased, both are the main components of precision, completeness and overall quality. [ABSTRACT FROM AUTHOR]

Abstract: Satellite images are promising data sources for map generation and updating of available maps to support activities and missions of government agencies and consumers. Full exploitation of these data sources depends on automatic techniques for object extraction from satellite imageries. Buildings, as one of the important man-made objects are subjects of concern to be extracted automatically. In this paper, Mathematical Morphologic operator has been used to close and eliminate the unwanted objects over the building roofs. The proposed approach involves several advanced morphological operators among which an adaptive hit-or-miss transform with varying size and shape of structuring element is used to determine the optimal filtering parameters automatically. After morphological operations, based on the texture parameters of buildings which are able to differentiate buildings from nearby non-building regions, buildings are extracted. [Copyright &y& Elsevier]

Nowadays, advanced real-time visualization for location-based applications, such as vehicle navigation or mobile phone navigation, requires large scale 3D reconstruction of street scenes. This paper presents methods for generating photorealistic 3D city models from raw mobile laser scanning data, which only contain georeferenced XYZ coordinates of points, to enable the use of photorealistic models in a mobile phone for personal navigation. The main focus is on the automated processing algorithms for noise point filtering, ground and building point classification, detection of planar surfaces, and on the key points (e.g., corners) of building derivation. The test site is located in the Tapiola area, Espoo, Finland. It is an area of commercial buildings, including shopping centers, banks, government agencies, bookstores, and high-rise residential buildings, with the tallest building being 45 m in height. Buildings were extracted by comparing the overlaps of X and Y coordinates of the point clouds between the cutoff-boxes at different and transforming the top-view of the point clouds of each overlap into a binary image and applying standard image processing technology to remove the non-building points, and finally transforming this image back into point clouds. The purpose for using points from cutoff-boxes instead of all points for building detection is to reduce the influence of tree points close to the building facades on building extraction. This method can also be extended to transform point clouds in different views into binary images for various other object extractions. In order to ensure the building geometry completeness, manual check and correction are needed after the key points of building derivation by automated algorithms. As our goal is to obtain photorealistic 3D models for walk-through views, terrestrial images were captured and used for texturing building facades. Currently, fully automatic generation of high quality 3D models is still challenging due to occlusions in both the laser and image data and due to significant illumination changes between the images. Especially when the scene contains both trees and vehicles, fully automated methods cannot achieve satisfactory visual appearance. In our approach, we employed the existing software for texture preparation and mapping. [ABSTRACT FROM AUTHOR]

Detecting and localizing buildings is of primary importance in urban planning tasks. Automating the building extraction process, however, has become attractive given the dominance of Convolutional Neural Networks (CNNs) in image classification tasks. In this work, we explore the effectiveness of the CNN-based architecture U-Net and its variations, namely, the Residual U-Net, the Attention U-Net, and the Attention Residual U-Net, in automatic building extraction. We showcase their robustness in feature extraction and information processing using exclusively RGB images, as they are a low-cost alternative to multi-spectral and LiDAR ones, selected from the SpaceNet 1 dataset. The experimental results show that U-Net achieves a 91.9 % accuracy, whereas introducing residual blocks, attention gates, or a combination of both improves the accuracy of the vanilla U-Net to 93.6 % , 94.0 % , and 93.7 % , respectively. Finally, the comparison between U-Net architectures and typical deep learning approaches from the literature highlights their increased performance in accurate building localization around corners and edges. [ABSTRACT FROM AUTHOR]

Vzdrževanje podatkov v topografskih bazah je ena od pomembnejših nalog organizacij, ki te podatkovne baze vodijo. Eden od pomembnih podatkovnih slojev v topografskih bazah so podatki o stavbah. V člankusta opisani metoda za samodejen zajem stavb iz digitalnega modela površja in multispektralnega ortofota ter uporaba rezultatov zajema za samodejno iskanje sprememb v topografskih bazah, v katerih se vodijo podatki o stavbah. Začetno masko stavb smo izdelali iz normaliziranega digitalnega modela površja (nDMP). Vegetacijo smo iz maske stavb izločili z modificiranim vegetacijskim indeksom, izračunanim iz infrardečega ortofota ob upoštevanju indeksa senc in teksture nDMP. Na končni maski smo stavbe vektorizirali z uporabo transformacije Radon. Rezultate samodejnega zajema stavb smo primerjali s katastrom stavb in dejanskim stanjem na terenu. Ssamodejnim postopkom smo našli 94,4 % vseh stavb na območju in ocenili, da je opisana metoda primerna za zajem podatkov o stavbah za topografske baze v merilih 1 : 10 000 in manj. Rezultat samodejnegaiskanja sprememb (popolnost 93,5 % in pravilnost 78,4 %) kaže, da je opisana metoda primerna za iskanje sprememb med podatki o stavbah ; The update of topographic databases is an important task for organizations that maintain them. Building data are one of the important data types in topographic databases. The article describes a method for automatic building extraction from digital surfacemodel and multispectral orthophoto and the use of extraction results for the building change detection in the topographic database. The initial building mask was created from the normalized digital surface model (nDSM).Vegetation was eliminated from the building mask using a modified vegetation index calculated from the infrared orthophoto and also considering the shadow index and the nDMP texture. The finalbuilding mask was vectorised using Radon transform. The results of the automatic building extraction were compared to the building cadastre and the actual situation on the ground. The automatic methoddetected 94.4% of all buildings in the area. We concluded that the described method is appropriate for capturing of the building data for the topographic database in scales 1 : 10 000 and smaller. Automatic change detection results (completeness 93.5% and correctness 78.4%) indicate that the described method is appropriate for building change detection.

A novel adaptive morphological attribute profile under object boundary constraint (AMAP–OBC) method is proposed in this study for automatic building extraction from high-resolution remote sensing (HRRS) images. By investigating the associated attributes in morphological attribute profiles (MAPs), the proposed method establishes corresponding relationships between AMAP–OBC and building characteristics in HRRS images. In the preprocessing step, the candidate object set is extracted by a group of rules for screening of non-building objects. Second, based on the proposed adaptive scale parameter extraction and object boundary constraint strategies, AMAP–OBC is conducted to obtain the initial building set. Finally, a further identification strategy with adaptive threshold combination is proposed to obtain the final building extraction results. Through experiments of multiple groups of HRRS images from different sensors, the proposed method shows outstanding performance in terms of automatic building extraction from diverse geographic objects in urban scenes. [ABSTRACT FROM AUTHOR]