Search

Automatic classification of buildings within port areas from synthetic aperture radar (SAR) images is crucial for effective port monitoring and planning. Yet, the unique challenges of SAR imaging, such as side-looking geometry, multi-bouncing scattering, and the compact arrangement of structures, often lead to incomplete building structures and blurred boundaries in classification results. To address these issues, this paper introduces SPformer, an efficient and lightweight pyramid transformer model tailored for semantic segmentation. The SPformer utilizes a pyramid transformer encoder with spatially separable self-attention (SSSA) to refine both local and global spatial information and to process multi-scale features, enhancing the accuracy of building structure delineation. It also integrates a lightweight all multi-layer perceptron (ALL-MLP) decoder to consolidate multi-scale information across various depths and attention scopes, refining detail processing. Experimental results on the Gaofen-3 (GF-3) 1 m port building classification dataset demonstrate the effectiveness of SPformer, achieving competitive performance compared to state-of-the-art models, with mean intersection over union (mIoU) and mean F1-score (mF1) reaching 77.14% and 87.04%, respectively, while maintaining a compact model size and lower computational requirements. Experiments conducted on the entire scene of SAR images covering port area also show the good capabilities of the proposed method. [ABSTRACT FROM AUTHOR]

Automatic classification of buildings within port areas from synthetic aperture radar (SAR) images is crucial for effective port monitoring and planning. Yet, the unique challenges of SAR imaging, such as side-looking geometry, multi-bouncing scattering, and the compact arrangement of structures, often lead to incomplete building structures and blurred boundaries in classification results. To address these issues, this paper introduces SPformer, an efficient and lightweight pyramid transformer model tailored for semantic segmentation. The SPformer utilizes a pyramid transformer encoder with spatially separable self-attention (SSSA) to refine both local and global spatial information and to process multi-scale features, enhancing the accuracy of building structure delineation. It also integrates a lightweight all multi-layer perceptron (ALL-MLP) decoder to consolidate multi-scale information across various depths and attention scopes, refining detail processing. Experimental results on the Gaofen-3 (GF-3) 1 m port building classification dataset demonstrate the effectiveness of SPformer, achieving competitive performance compared to state-of-the-art models, with mean intersection over union (mIoU) and mean F1-score (mF1) reaching 77.14% and 87.04%, respectively, while maintaining a compact model size and lower computational requirements. Experiments conducted on the entire scene of SAR images covering port area also show the good capabilities of the proposed method.

Building function labelling plays an important role in understanding human activities inside buildings. This study develops a method of function label classification using integrated features derived from remote sensing and crowdsensing data with an extreme gradient boosting tree (XGBoost). The classification framework is verified based on a dataset from Shenzhen, China. An extended label system for six building types (residential, commercial, office, industrial, public facilities, and others) was applied, and various social functions were considered. The overall classification accuracies were 88.15% (kappa index = 0.72) and 85.56% (kappa index = 0.69). The importance of features was evaluated using the occurrence frequency of features at decision nodes. In the six-category classification system, the basic building attributes (22.99%) and POIs (46.74%) contributed most to the classification process; moreover, the building footprint (7.40%) and distance to roads (11.76%) also made notable contributions. The result shows that it is feasible to extract building environments from POI labels and building footprint geometry with a dimensional reduction model using an autoencoder. Additionally, crowdsensing data (e.g., POI and distance to roads) will become increasingly important as classification tasks become more complicated and the importance of basic building attributes declines.

The detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detection was by using the imagery and it entailed human–computer interaction, which was a daunting proposition. To tackle this task, a novel network based on an end-to-end deep learning framework is proposed to detect and classify buildings features. The proposed CNN has three parallel stream channels: the first is the high-resolution aerial imagery, while the second stream is the digital surface model (DSM). The third was fixed on extracting deep features using the fusion of channel one and channel two, respectively. Furthermore, the channel has eight group convolution blocks of 2D convolution with three max-pooling layers. The proposed model’s efficiency and dependability were tested on three different categories of complex urban building structures in the study area. Then, morphological operations were applied to the extracted building footprints to increase the uniformity of the building boundaries and produce improved building perimeters. Thus, our approach bridges a significant gap in detecting building objects in diverse environments; the overall accuracy (OA) and kappa coefficient of the proposed method are greater than 80% and 0.605, respectively. The findings support the proposed framework and methodologies’ efficacy and effectiveness at extracting buildings from complex environments.

Utilising satellite images for planning and development is becoming a common practice as computational power and machine learning capabilities expand. In this paper, we explore the use of satellite image derived building footprint data to classify the residential status of urban buildings in low and middle income countries. A recently developed ensemble machine learning building classification model is applied for the first time to the Democratic Republic of the Congo, and to Nigeria. The model is informed by building footprint and label data of greater completeness and attribute consistency than have previously been available for these countries. A GIS workflow is described that semiautomates the preparation of data for input to the model. The workflow is designed to be particularly useful to those who apply the model to additional countries and use input data from diverse sources. Results show that the ensemble model correctly classifies between 85% and 93% of structures as residential and nonresidential across both countries. The classification outputs are likely to be valuable in the modelling of human population distributions, as well as in a range of related applications such as urban planning, resource allocation, and service delivery.

The detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detection was by using the imagery and it entailed human–computer interaction, which was a daunting proposition. To tackle this task, a novel network based on an end-to-end deep learning framework is proposed to detect and classify buildings features. The proposed CNN has three parallel stream channels: the first is the high-resolution aerial imagery, while the second stream is the digital surface model (DSM). The third was fixed on extracting deep features using the fusion of channel one and channel two, respectively. Furthermore, the channel has eight group convolution blocks of 2D convolution with three max-pooling layers. The proposed model's efficiency and dependability were tested on three different categories of complex urban building structures in the study area. Then, morphological operations were applied to the extracted building footprints to increase the uniformity of the building boundaries and produce improved building perimeters. Thus, our approach bridges a significant gap in detecting building objects in diverse environments; the overall accuracy (OA) and kappa coefficient of the proposed method are greater than 80% and 0.605, respectively. The findings support the proposed framework and methodologies' efficacy and effectiveness at extracting buildings from complex environments. [ABSTRACT FROM AUTHOR]

Building function labelling plays an important role in understanding human activities inside buildings. This study develops a method of function label classification using integrated features derived from remote sensing and crowdsensing data with an extreme gradient boosting tree (XGBoost). The classification framework is verified based on a dataset from Shenzhen, China. An extended label system for six building types (residential, commercial, office, industrial, public facilities, and others) was applied, and various social functions were considered. The overall classification accuracies were 88.15% (kappa index = 0.72) and 85.56% (kappa index = 0.69). The importance of features was evaluated using the occurrence frequency of features at decision nodes. In the six-category classification system, the basic building attributes (22.99%) and POIs (46.74%) contributed most to the classification process; moreover, the building footprint (7.40%) and distance to roads (11.76%) also made notable contributions. The result shows that it is feasible to extract building environments from POI labels and building footprint geometry with a dimensional reduction model using an autoencoder. Additionally, crowdsensing data (e.g., POI and distance to roads) will become increasingly important as classification tasks become more complicated and the importance of basic building attributes declines. [ABSTRACT FROM AUTHOR]

Utilising satellite images for planning and development is becoming a common practice as computational power and machine learning capabilities expand. In this paper, we explore the use of satellite image derived building footprint data to classify the residential status of urban buildings in low and middle income countries. A recently developed ensemble machine learning building classification model is applied for the first time to the Democratic Republic of the Congo, and to Nigeria. The model is informed by building footprint and label data of greater completeness and attribute consistency than have previously been available for these countries. A GIS workflow is described that semiautomates the preparation of data for input to the model. The workflow is designed to be particularly useful to those who apply the model to additional countries and use input data from diverse sources. Results show that the ensemble model correctly classifies between 85% and 93% of structures as residential and nonresidential across both countries. The classification outputs are likely to be valuable in the modelling of human population distributions, as well as in a range of related applications such as urban planning, resource allocation, and service delivery. [ABSTRACT FROM AUTHOR]