Automatic Building Detection Research Articles

Automatic Detection of War-Destroyed Buildings from High-Resolution Remote Sensing Images

Modern high-intensity armed conflicts often lead to extensive damage to urban infrastructure. The use of high-resolution remote sensing images can clearly detect damage to individual buildings which is of great significance for monitoring war crimes and damage assessments that destroy civilian infrastructure indiscriminately. In this paper, we propose SOCA-YOLO (Sampling Optimization and Coordinate Attention–YOLO), an automatic detection method for destroyed buildings in high-resolution remote sensing images based on deep learning techniques. First, based on YOLOv8, Haar wavelet transform and convolutional blocks are used to downsample shallow feature maps to make full use of spatial details in high-resolution remote sensing images. Second, the coordinate attention mechanism is integrated with C2f so that the network can use the spatial information to enhance the feature representation earlier. Finally, in the feature fusion stage, a lightweight dynamic upsampling strategy is used to improve the difference in the spatial boundaries of feature maps. In addition, this paper obtained high-resolution remote sensing images of urban battlefields through Google Earth, constructed a dataset for the detection of objects on buildings, and conducted training and verification. The experimental results show that the proposed method can effectively improve the detection accuracy of destroyed buildings, and the method is used to map destroyed buildings in cities such as Mariupol and Volnovaja where violent armed conflicts have occurred. The results show that deep learning-based object detection technology has the advantage of fast and accurate detection of destroyed buildings caused by armed conflict, which can provide preliminary reference information for monitoring war crimes and assessing war losses.

Automatic Detection and 3D Reconstruction of Buildings from Historical Maps

ABSTRACT This paper presents an automatic 3D building reconstruction methodology for historical urban maps. It uses facade and openings detection on the maps, followed by rectification, regularization, and 3D model generation techniques. Evaluation metrics confirm the effectiveness of the approach, with high accuracy in detecting facades and their openings while maintaining geometric integrity. The flexibility and interoperability of the chosen 3D building representation method allow for adjustments in dimensions without compromising layout, making it suitable for completing the urban environments where facades may not be directly visible. This methodology represents a significant step toward automating the reconstruction of 3D historical urban landscapes, contributing to heritage preservation and architectural understanding.

Automatic crack detection and structural inspection of cultural heritage buildings using UAV photogrammetry and digital twin technology

Current methods for rapidly inspecting structures are difficult to document and subjective. Automating the process with innovative technologies is necessary to overcome these limitations. Precisely monitoring cracking in cultural heritage buildings is vital as they pose a significant risk to their integrity. Recent advancements in artificial intelligence, including imaging equipment and computer vision, offer significant advantages for automating the detection of structural cracks. This study conducted tests to investigate utilizing unmanned aerial vehicle photogrammetry, a modern surveying method, for monitoring such inspections. Initially, a level of detail 3 digital model of the structure was generated. Finally, the metric accuracy of the detected cracks was analyzed. The cracks measured by the traditional method were considered as reference data and compared with the automatically detected cracks. As a result, 83 % of the cracks were detected by the modern techniques and the RMSE value was 0.802 cm because of the metric comparison.

Automated, quick, and precise building extraction from aerial images using ll-unet model

The subject matter of this article is the detection and semantic segmentation of buildings from high-resolution aerial images. It extracts building images from similar characteristics of roads and soil objects. It is used for various applications such as urban planning, infrastructure development, and disaster management. The goal of this study is to develop a fast, accurate, and automatic building detection model based on the semantic segmentation LL-UNET architecture that is optimized and tuned with proper hyper parameter settings. The tasks to be solved are as follows: collect remote sensing building dataset that is divided into three parts of training, validation, and testing; apply data augmentation on the training dataset by vertical flip, horizontal flip, and rotation methods; further pass into the bilateral filter to remove noises from the images; optimize LL-UNET model by various optimizer methods and tuned hyper parameter by proper selection value, the method is compared by the performance metrics recall, precision, and accuracy. The following results were obtained: the model is evaluated under the training loss curve and accuracy curve of different optimizers SGD, ASGD, ADAM, ADAMW, and RMSProp; it measures the training time, mean accuracy, and mean IOU parameters during the training phase; the testing phase is evaluated by precision and recall; the method is compared by visualizing the result of LL-UNET + different optimizers; and the proposed method is compared with the existing method by common evolution parameters metric. Conclusions. The scientific novelty of the results obtained is as follows: 1) the LL-UNET effectively segmented the building remotely sensed images in the limited number of training samples available; 2) the loss function of the model observed under hyper parameter selection of the optimizer, learning rate, batch size, and epochs; which makes an optimal model to extract the building in an accurate and fast manner from the complex background; 3) the proposed model results compared with a well-known model of the building extraction under the common evaluation metrics of F1 score.

Cross-level and multiscale CNN-Transformer network for automatic building extraction from remote sensing imagery

ABSTRACT Automatic building detection from remote sensing images holds significant applications in various domains, including cartography, land-use change detection, urban planning, and 3D intelligent city construction. Driven by the innovation of deep learning technology, convolutional neural networks (CNNs) have emerged as a powerful framework for automatic interpretation, exhibiting hierarchical feature generation and robust representation for building extraction. However, the inherent computational limitations of convolutional operators hinder the acquisition of an effective global receptive field. Recent advancements in deep learning have witnessed the adoption of the multi-head self-attention (MHSA) mechanism by Transformer, presenting the superiority of global context construction. Nonetheless, this network structure encounters difficulties in effectively modelling two-dimensional spatial structure features with scale variation in semantic segmentation and often has huge parameters with high algorithm complexity. To address the above problems, this paper proposed a hybrid deep neural network synergistically harnessing the superiority of CNN and Transformer to extract buildings from remote sensing images. Meanwhile, an improved MHSA mechanism is developed to facilitate the construction of multiscale global representations, concurrently reducing computational complexity. Furthermore, the cross-level MHSA modules the semantic correlation between the deep and shallow-level features to refine spatial fine-grained information. The proposed method was comprehensively evaluated on two building datasets via quantitative analysis and visualization. The experimental results confirmed that the developed network and modules outperform other state-of-the-art methods and can effectively improve the accuracy (93.4% F1-score on the WHU dataset, 89.38% F1-score on the CAMB dataset) with high efficiency for building extraction.

Building Footprint Extraction from LiDAR Data Using SVM Classification

Automatic detection of buildings from very high resolution (VHR) satellite images is a current research hotspot in remote sensing. In this work presents a novel approach to detect the buildings by atomization of the training area collecting stage for supervised classification. The classification method for the analysis of satellite image based on Normalized Difference Vegetation Index (NDVI). The method employs the multi-spectral remote sensing data technique to find spectral signature of different objects such as vegetation index, land cover classification, concrete structure, road structure, rural and urban areas, rocky areas and remaining areas presented in the image. In the experiments, the proposed SVM framework outperformed for the three (Linear SVM, Cubic SVM, Medium Gaussian SVM) methods tested. SVM is trained through supervised learning to classify each location in the image as “buildings” or “Non-buildings.” Finally, SVM algorithm to find the accuracy value, training time and receiver operating characteristic curves to evaluate detection performance, and compare the proposed algorithm with several existing methods.

"Towards Real-time House Detection in Aerial Imagery Using Faster Region-based Convolutional Neural Network"

In the past few years, automatic building detection in aerial images has become an emerging field in computer vision. Detecting the specific types of houses will provide information in urbanization, change detection, and urban monitoring that play increasingly important roles in modern city planning and natural hazard preparedness. In this paper, we demonstrate the effectiveness of detecting various types of houses in aerial imagery using Faster Region-based Convolutional Neural Network (Faster-RCNN). After formulating the dataset and extracting bounding-box information, pre-trained ResNet50 is used to get the feature maps. The fully convolutional Region Proposal Network (RPN) first predicts the bounds and objectness score of objects (in this case house) from the feature maps. Then, the Region of Interest (RoI) pooling layer extracts interested regions to detect objects that are present in the images. To the best of our knowledge, this is the first attempt at detecting houses using Faster R-CNN that has achieved satisfactory results. This experiment opens a new path to conduct and extent the works not only for civil and environmental domain but also other applied science disciplines.

Flynet–Neural Network Model for Automatic Building Detection from Satellite Images

Flynet–Neural Network Model for Automatic Building Detection from Satellite Images

Frequency Spectrum Intensity Attention Network for Building Detection from High-Resolution Imagery

Computational intelligence techniques have been widely used for automatic building detection from high-resolution remote sensing imagery and especially the methods based on neural networks. However, existing methods do not pay attention to the value of high-frequency and low-frequency information in the frequency domain for feature extraction of buildings in remote sensing images. To overcome these limitations, this paper proposes a frequency spectrum intensity attention network (FSIANet) with an encoder–decoder structure for automatic building detection. The proposed FSIANet mainly involves two innovations. One, a novel and plug-and-play frequency spectrum intensity attention (FSIA) mechanism is devised to enhance feature representation by evaluating the informative abundance of the feature maps. The FSIA is deployed after each convolutional block in the proposed FSIANet. Two, an atrous frequency spectrum attention pyramid (AFSAP) is constructed by introducing FSIA in widely used atrous spatial pyramid pooling. The AFSAP is able to select the features with high response to building semantic features at each scale and weaken the features with low response, thus enhancing the feature representation of buildings. The proposed FSIANet is evaluated on two large public datasets (East Asia and Inria Aerial Image Dataset), which demonstrates that the proposed method can achieve the state-of-the-art performance in terms of F1-score and intersection-over-union.

Detecting Buildings and Nonbuildings from Satellite Images Using U-Net.

Automatic building detection from high-resolution satellite imaging images has many applications. Understanding socioeconomic development and keeping track of population migrations are essential for effective civic planning. These civil feature systems may also help update maps after natural disasters or in geographic regions undergoing dramatic population expansion. To accomplish the desired goal, a variety of image processing techniques were employed. They are often inaccurate or take a long time to process. Convolutional neural networks (CNNs) are being designed to extract buildings from satellite images, based on the U-Net, which was first developed to segment medical images. The minimal number of images from the open dataset, in RGB format with variable shapes, reveals one of the advantages of the U-Net; that is, it develops excellent accuracy from a limited amount of training material with minimal effort and training time. The encoder portion of U-Net was altered to test the feasibility of using a transfer learning facility. VGGNet and ResNet were both used for the same purpose. The findings of these models were also compared to our own bespoke U-Net, which was designed from the ground up. With an accuracy of 84.9%, the VGGNet backbone was shown to be the best feature extractor. Compared to the current best models for tackling a similar problem with a larger dataset, the present results are considered superior.

Automatic Building Detection for Multi-Aspect SAR Images Based on the Variation Features

Multi-aspect synthetic aperture radar (SAR) images contain more information available for automatic target recognition (ATR) than images from a single view. However, the sensitivity to aspect angles also makes it hard to extract and integrate information from multi-aspect images. In this paper, we propose a novel method based on the variations features to realize automatic building detection in the image level. First, to get a comprehensive description of target variation patterns, statistical characteristic variances are derived from three representative and complementary categories. Then, these obtained features are fused and put in the K-means classifier for prescreening, whose results are used as the training sets in supervised classification later to avoid manual labeling. Second, for more precise detection performance, finer features in vector forms are obtained by principal component analysis (PCA). The variation patterns of these feature vectors are explored in two different manners of correlation and fluctuation analyses and processed by separate support vector machines (SVMs) after fusion. Finally, the independent SVM detection results are fused according to a maximum probability rule. Experiments conducted on two different airborne data sets demonstrate the robustness and effectiveness of the proposed method, in spite of significant target signature variabilities and cluttered background.

Uncertainty, Edge, and Reverse-Attention Guided Generative Adversarial Network for Automatic Building Detection in Remotely Sensed Images

Despite recent advances in deep-learning-based semantic segmentation, automatic building detection from remotely sensed imagery is still a challenging problem owing to large variability in the appearance of buildings across the globe. The errors occur mostly around the boundaries of the building footprints, in shadow areas, and when detecting buildings whose exterior surfaces have reflectivity properties that are very similar to those of the surrounding regions. To overcome these problems, we propose a generative adversarial network-based segmentation framework with uncertainty attention unit and refinement module embedded in the generator. The refinement module, composed of edge and reverse-attention units, is designed to refine the predicted building map. The edge attention enhances the boundary features to estimate building boundaries with greater precision, and the reverse attention allows the network to explore the features missing in the previously estimated regions. The uncertainty attention unit assists the network in resolving uncertainties in classification. As a measure of the power of our approach, as of December 4, 2021, it ranks at the second place on DeepGlobe’s public leaderboard despite the fact that main focus of our approach—refinement of the building edges—does not align exactly with the metrics used for leaderboard rankings. Our overall <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$F$</tex-math></inline-formula> 1-score on DeepGlobe’s challenging dataset is 0.745. We also report improvements on the previous-best results for the challenging INRIA validation dataset for which our network achieves an overall IoU of 81.28% and an overall accuracy of 97.03%. Along the same lines, for the official INRIA test dataset, our network scores 77.86% and 96.41% in overall IoU and accuracy. We have also improved upon the previous best results on two other datasets: the WHU building dataset and the Massachusetts buildings dataset.

Automatic detection of unreinforced masonry buildings from street view images using deep learning-based image segmentation

Mitigation of seismic risk is a challenge for 70+ countries in the world. Screening the building stock for potential structural defects is one way to locate structures that are vulnerable to strong ground motion. Often in developing countries, masonry buildings are not reinforced or confined to withstand earthquake loads. It has been observed that such buildings cannot withstand the lateral loads imposed by an earthquake. An estimated 77 percent of the fatalities in the earthquakes during the last 100 years were caused mainly by the collapse of masonry buildings. Given the probability of severe damage or collapse in the event of an earthquake, identification and retrofit of such masonry buildings are critical. Screening of masonry buildings by conventional methods is usually a time-consuming and labor-intensive process. This research presents an automated workflow for segmenting the presence of such buildings through the use of street-view images. The method uses deep learning techniques. An inventory composed of a set of street view images was collected from the streets of Oaxaca State, Mexico using a 360° camera mounted on a car. These images were then annotated by trained engineers. Using the annotated dataset, an instance segmentation model was trained to detect and classify masonry buildings from the street view images. Using the model, we performed city scale detections of masonry buildings. We found the spatial distribution pattern of masonry buildings is correlated with the urbanization paths of the cities. The model could be used to produce large-scale automated detection of buildings at a fraction of the cost and in the fraction of the time of the alternatives. With affordable, accurate and massive screenings, governments can target these buildings for retrofit efforts and companies can assess the business opportunity of prevention (or “Building Better Before”).

Automatic Building Detection with Polygonizing and Attribute Extraction from High-Resolution Images

Buildings can be introduced as a fundamental element for forming a city. Therefore, up-to-date building maps have become vital for many applications, including urban mapping and urban expansion analysis. With the development of deep learning, segmenting building footprints from high-resolution remote sensing imagery has become a subject of intense study. Here, a modified version of the U-Net architecture with a combination of pre- and post-processing techniques was developed to extract building footprints from high-resolution aerial imagery and unmanned aerial vehicle (UAV) imagery. Data pre-processing with the logarithmic correction image enhancing algorithm showed the most significant improvement in the building detection accuracy for aerial images; meanwhile, the CLAHE algorithm improved the most concerning UAV images. This study developed a post-processing technique using polygonizing and polygon smoothing called the Douglas–Peucker algorithm, which made the building output directly ready to use for different applications. The attribute information, land use data, and population count data were applied using two open datasets. In addition, the building area and perimeter of each building were calculated as geometric attributes.

DEEP LEARNING BASED ROOF TYPE CLASSIFICATION USING VERY HIGH RESOLUTION AERIAL IMAGERY

Abstract. Automatic detection, segmentation and reconstruction of buildings in urban areas from Earth Observation (EO) data are still challenging for many researchers. Roof is one of the most important element in a building model. The three-dimensional geographical information system (3D GIS) applications generally require the roof type and roof geometry for performing various analyses on the models, such as energy efficiency. The conventional segmentation and classification methods are often based on features like corners, edges and line segments. In parallel to the developments in computer hardware and artificial intelligence (AI) methods including deep learning (DL), image features can be extracted automatically. As a DL technique, convolutional neural networks (CNNs) can also be used for image classification tasks, but require large amount of high quality training data for obtaining accurate results. The main aim of this study was to generate a roof type dataset from very high-resolution (10 cm) orthophotos of Cesme, Turkey, and to classify the roof types using a shallow CNN architecture. The training dataset consists 10,000 roof images and their labels. Six roof type classes such as flat, hip, half-hip, gable, pyramid and complex roofs were used for the classification in the study area. The prediction performance of the shallow CNN model used here was compared with the results obtained from the fine-tuning of three well-known pre-trained networks, i.e. VGG-16, EfficientNetB4, ResNet-50. The results show that although our CNN has slightly lower performance expressed with the overall accuracy, it is still acceptable for many applications using sparse data.

Performance Evaluation Towards Automatic Building and Road Detection Technique for High-Resolution Remote Sensing Images

Building and road detection from the high-resolution remote sensing images has many applications in a wide range of areas including urban design, real-estate management, and disaster relief. Extracting buildings and roads from the remote sensing images have been performed by human experts manually, but it takes too much time and the cost of labor to build is also very high. So, an automated system that can emulate a human operator is desired. Our goal is to develop a system for automatically detecting buildings and roads directly from high-resolution satellite images. Therefore, we propose Internal Gray Variance (IGV) to detect the buildings and roads in the urban areas. First, the satellite images are enhanced by using morphological operators, which enhance the edges of the objects. Then multiseed-based clustering technique detects the building and road edges using the variance in the gray levels. To reduce the false alarm, tiny regions that are improbable to be buildings and roads are separated. Finally, by using the adaptive threshold-based segmentation technique, the buildings are segmented and the road network is extracted based on supervised directional homogeneity. Finally, we evaluate our system on a large-scale road and building detection data sets that are publicly available.

Automatic Building Detection from High-Resolution Remote Sensing Images Based on Joint Optimization and Decision Fusion of Morphological Attribute Profiles

High-resolution remote sensing (HRRS) images, when used for building detection, play a key role in urban planning and other fields. Compared with the deep learning methods, the method based on morphological attribute profiles (MAPs) exhibits good performance in the absence of massive annotated samples. MAPs have been proven to have a strong ability for extracting detailed characterizations of buildings with multiple attributes and scales. So far, a great deal of attention has been paid to this application. Nevertheless, the constraints of rational selection of attribute scales and evidence conflicts between attributes should be overcome, so as to establish reliable unsupervised detection models. To this end, this research proposes a joint optimization and fusion building detection method for MAPs. In the pre-processing step, the set of candidate building objects are extracted by image segmentation and a set of discriminant rules. Second, the differential profiles of MAPs are screened by using a genetic algorithm and a cross-probability adaptive selection strategy is proposed; on this basis, an unsupervised decision fusion framework is established by constructing a novel statistics-space building index (SSBI). Finally, the automated detection of buildings is realized. We show that the proposed method is significantly better than the state-of-the-art methods on HRRS images with different groups of different regions and different sensors, and overall accuracy (OA) of our proposed method is more than 91.9%.

Improved U-Nets with inception blocks for building detection

With the rapid increase of the world’s population, urban growth management and monitoring have become an important component in environmental, social, and economic terms. In general, automatic detection of buildings in urban areas from high-resolution satellite imagery has become an important issue. In recent years, the U-Net architecture has become one of the most popular convolutional neural networks in terms of pixel-based image segmentation. A new deep learning architecture has been developed by combining inception blocks with the convolutional layers of the original U-Net architecture to achieve remarkably high performance in building detection. First, the width of the network is increased by adding parallel filters of different sizes to the convolutional layers in the original U-Net model, and Inception UNet architecture is developed. For the proposed architecture, parallel layers were used only in feature extraction stage to reduce the number of parameters and computation time due to a large network size. In this context, performance comparisons were made with two different datasets. The results show that a significant improvement in F1 and kappa scores compared to the original U-Net was achieved using the proposed architecture, and model size is dramatically reduced according to Inception UNet-v1.

Automatic Detection of Earthquake-Damaged Buildings by Integrating UAV Oblique Photography and Infrared Thermal Imaging

Extracting damage information of buildings after an earthquake is crucial for emergency rescue and loss assessment. Low-altitude remote sensing by unmanned aerial vehicles (UAVs) for emergency rescue has unique advantages. In this study, we establish a remote sensing information-extraction method that combines ultramicro oblique UAV and infrared thermal imaging technology to automatically detect the structural damage of buildings and cracks in external walls. The method consists of four parts: (1) 3D live-action modeling and building structure analysis based on ultramicro oblique images; (2) extraction of damage information of buildings; (3) detection of cracks in walls based on infrared thermal imaging; and (4) integration of detection systems for information of earthquake-damaged buildings. First, a 3D live-action building model is constructed. A multi-view structure image for segmentation can be obtained based on this method. Second, a method of extracting information on damage to building structures using a 3D live-action building model as the geographic reference is proposed. Damage information of the internal structure of the building can be obtained based on this method. Third, based on analyzing the temperature field distribution on the exterior walls of earthquake-damaged buildings, an automatic method of detecting cracks in the walls by using infrared thermal imaging is proposed. Finally, the damage information detection and assessment system is researched and developed, and the system is integrated. Taking earthquake search-and-rescue simulation as an example, the effectiveness of this method is verified. The damage distribution in the internal structure and external walls of buildings in this area is obtained with an accuracy of 78%.

Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE

Abstract. Fast and efficient detection and reconstruction of buildings have become essential in real-time applications such as navigation, 3D rendering, augmented reality, and 3D smart cities. In this study, a modern Deep Learning (DL)-based framework is proposed for automatic detection, localization, and height estimation of buildings, simultaneously, from a single aerial image. The proposed framework is based on a Y-shaped Convolutional Neural Network (Y-Net) which includes one encoder and two decoders. The input of the network is a single RGB image, while the outputs are predicted height information of buildings as well as the rooflines in three classes of eave, ridge, and hip lines. The extracted knowledge by the Y-Net (i.e. buildings’ heights and rooflines) is utilized for 3D reconstruction of buildings based on the third Level of Detail (LoD2). The main steps of the proposed approach are data preparation, CNNs training, and 3D reconstruction. For the experimental investigations airborne data from Potsdam are used, which were provided by ISPRS. For the predicted heights, the results show an average Root Mean Square Error (RMSE) and a Normalized Median Absolute Deviation (NMAD) of about 3.8 m and 1.3 m, respectively. Moreover, the overall accuracy of the extracted rooflines is about 86%.