Automatic building extraction in dense urban areas through GeoEye multispectral imagery

Ghanea, Mohsen; Moallem, Payman; Momeni, Mehdi

doi:10.1080/01431161.2014.933278

Cited by 25 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of FAR increased from 0.87 in 1997 to 1.58 in 2011 with an average annual growth of 0.05. AV also increased from 10,695.81 m in 1997 to 17,557.92 m in 2011, increasing by an average of 490.15 m 3 per year. These changes indicate that average building height and volume increased, meaning that Tiexi District increased its urban capacity as a result of renewal.…”

Section: Analyzing Indicesmentioning

confidence: 92%

“…Rapid, highly accurate and automatic extraction of urban space 3D information has always been the focus of research on photogrammetry, remote sensing and computer vision [14]. Methods for automatic extraction of 3D information regarding buildings [15,16] from integration of multispectral/hyper spectral images [17,18], LiDAR [19] or SAR [20][21][22] became an emerging research focus. This 3D information have been effectively applied to analyzing 3D urban space [23].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Three-Dimensional Space Expansion Characteristics in Old Industrial Area Renewal Using GIS and Barista: A Case Study of Tiexi District, Shenyang, China

Liu

et al. 2019

Sustainability

View full text Add to dashboard Cite

With rapid urban development in China in the last two decades, 3D characteristics have been the main feature of urban morphology. Nevertheless, the vast majority of urban growth research has only focused on area expansion horizontally, with few studies conducted in a 3D perspective. In this paper, the characteristics of 3D expansion that occurred in Tiexi from 1997 to 2011 were evaluated based on geographic information system (GIS) tools, remote-sensing images, and Barista software. Landscape index, the spatiotemporal distribution of changes in buildings’ renewal modes and variations in city skylines as well as the relationship between number and size of high-rise buildings are the specific phenomena and data utilized to quantify the 3D urban expansion. The results showed that the average height of Tiexi increased by 0.69 m annually, the average urban capacity increased by 490.15 m3 annually, and space congestion degree increased by 0.11% annually. The average annual increase of the building evenness index was 36.43. The renewal area occupied up to 75.38% of the total area. The change of the skyline was more consistent with the east–west direction. The change in the south direction was significant, while in the north direction it was relatively slow. The overall shape of the city was that of a weak pyramid, with the angle of the top of the pyramid gradually becoming larger. The methods proposed in this paper laid a foundation for a wide range of study of 3D urban morphology changes.

show abstract

Section: Analyzing Indicesmentioning

confidence: 92%

mentioning

confidence: 99%

Analysis of Three-Dimensional Space Expansion Characteristics in Old Industrial Area Renewal Using GIS and Barista: A Case Study of Tiexi District, Shenyang, China

Liu

et al. 2019

Sustainability

View full text Add to dashboard Cite

show abstract

“…Building extraction is important for updating geographic information and urban construction using remote sensing technology. Building information has been used in a wide range of domains such as urban management and expansion, intelligent city construction, 3D semantic modeling, autonomous driving, and traffic navigation [1][2][3][4][5][6]. Accurate building spatial information can provide vital decisions and analyses for urbanization, especially land use and cover.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Semantic Feature Optimization and Fusion Network for Building Extraction Using High-Resolution Aerial Images and LiDAR Data

et al. 2021

View full text Add to dashboard Cite

Automatic building extraction has been applied in many domains. It is also a challenging problem because of the complex scenes and multiscale. Deep learning algorithms, especially fully convolutional neural networks (FCNs), have shown robust feature extraction ability than traditional remote sensing data processing methods. However, hierarchical features from encoders with a fixed receptive field perform weak ability to obtain global semantic information. Local features in multiscale subregions cannot construct contextual interdependence and correlation, especially for large-scale building areas, which probably causes fragmentary extraction results due to intra-class feature variability. In addition, low-level features have accurate and fine-grained spatial information for tiny building structures but lack refinement and selection, and the semantic gap of across-level features is not conducive to feature fusion. To address the above problems, this paper proposes an FCN framework based on the residual network and provides the training pattern for multi-modal data combining the advantage of high-resolution aerial images and LiDAR data for building extraction. Two novel modules have been proposed for the optimization and integration of multiscale and across-level features. In particular, a multiscale context optimization module is designed to adaptively generate the feature representations for different subregions and effectively aggregate global context. A semantic guided spatial attention mechanism is introduced to refine shallow features and alleviate the semantic gap. Finally, hierarchical features are fused via the feature pyramid network. Compared with other state-of-the-art methods, experimental results demonstrate superior performance with 93.19 IoU, 97.56 OA on WHU datasets and 94.72 IoU, 97.84 OA on the Boston dataset, which shows that the proposed network can improve accuracy and achieve better performance for building extraction.

show abstract

“…Over the past decade, some methods have tried to extract buildings through VHR imagery, which applied different strategies such as new frameworks [3], new parameters [4], new indices [5], other related information [6], and some hybrid algorithms [7]. Based on the used data, building extraction methods can generally be divided into three categories: 2D (two-dimensional) information based, fused 2D-3D information based and 3D information based [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Building Extraction in Very High Resolution Imagery by Dense-Attention Networks

et al. 2018

View full text Add to dashboard Cite

Building extraction from very high resolution (VHR) imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Compared with the traditional building extraction approaches, deep learning networks have recently shown outstanding performance in this task by using both high-level and low-level feature maps. However, it is difficult to utilize different level features rationally with the present deep learning networks. To tackle this problem, a novel network based on DenseNets and the attention mechanism was proposed, called the dense-attention network (DAN). The DAN contains an encoder part and a decoder part which are separately composed of lightweight DenseNets and a spatial attention fusion module. The proposed encoder–decoder architecture can strengthen feature propagation and effectively bring higher-level feature information to suppress the low-level feature and noises. Experimental results based on public international society for photogrammetry and remote sensing (ISPRS) datasets with only red–green–blue (RGB) images demonstrated that the proposed DAN achieved a higher score (96.16% overall accuracy (OA), 92.56% F1 score, 90.56% mean intersection over union (MIOU), less training and response time and higher-quality value) when compared with other deep learning methods.

show abstract

Automatic building extraction in dense urban areas through GeoEye multispectral imagery

Cited by 25 publications

References 25 publications

Analysis of Three-Dimensional Space Expansion Characteristics in Old Industrial Area Renewal Using GIS and Barista: A Case Study of Tiexi District, Shenyang, China

Analysis of Three-Dimensional Space Expansion Characteristics in Old Industrial Area Renewal Using GIS and Barista: A Case Study of Tiexi District, Shenyang, China

Multiscale Semantic Feature Optimization and Fusion Network for Building Extraction Using High-Resolution Aerial Images and LiDAR Data

Building Extraction in Very High Resolution Imagery by Dense-Attention Networks

Contact Info

Product

Resources

About