A Coarse-to-Fine Contour Optimization Network for Extracting Building Instances from High-Resolution Remote Sensing Imagery

Fang, Fang; Wu, Kaishun; Liu, Yuanyuan; Li, Shengwen; Wan, Bo; Chen, Yanling; Zheng, Daoyuan

doi:10.3390/rs13193814

Cited by 12 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fang et al . 19 constructed a Chinese building instance segmentation dataset (CBISD) from Google Earth images. CBISD comprises 7,260 pairs of 500 × 500 images, covering an area of 124.32 km 2 , and containing 63,886 buildings in four Chinese cities (i.e., Beijing, Shanghai, Shenzhen, and Wuhan).…”

Section: Background and Summarymentioning

confidence: 99%

See 1 more Smart Citation

A benchmark GaoFen-7 dataset for building extraction from satellite images

Chen,

Huang,

et al. 2024

Sci Data

View full text Add to dashboard Cite

Accurate building extraction is crucial for urban understanding, but it often requires a substantial number of building samples. While some building datasets are available for model training, there remains a lack of high-quality building datasets covering urban and rural areas in China. To fill this gap, this study creates a high-resolution GaoFen-7 (GF-7) Building dataset utilizing the Chinese GF-7 imagery from six Chinese cities. The dataset comprises 5,175 pairs of 512 × 512 image tiles, covering 573.17 km2. It contains 170,015 buildings, with 84.8% of the buildings in urban areas and 15.2% in rural areas. The usability of the GF-7 Building dataset has been proved with seven convolutional neural networks, all achieving an overall accuracy (OA) exceeding 93%. Experiments have shown that the GF-7 building dataset can be used for building extraction in urban and rural scenarios. The proposed dataset boasts high quality and high diversity. It supplements existing building datasets and will contribute to promoting new algorithms for building extraction, as well as facilitating intelligent building interpretation in China.

show abstract

Section: Background and Summarymentioning

confidence: 99%

“…We evaluated both the total number of annotations and the coverage area of our dataset as well as the CBISD 19 and SpaceNet 2 dataset 16 . These datasets all cover localized areas of China to some extent.…”

Section: Data Recordsmentioning

confidence: 99%

A benchmark GaoFen-7 dataset for building extraction from satellite images

Chen,

Huang,

et al. 2024

Sci Data

View full text Add to dashboard Cite

show abstract

“…While these feature maps contain richer semantic information, they also lose fine-grained information including building boundaries, small buildings and texture information [8,9]. Although the fine-grained information is reconstructed during the decoding process, by integrating feature maps from the encoding stage, it also introduces noise information, leading to poor building extraction especially for boundary and small objects identification [5,[10][11][12][13][14]. Therefore, it is essential to efficiently enhance semantic features in the encoding stage and recover fine-grained semantic information in the decoding stage to improve the building extraction performance.…”

Section: Introductionmentioning

confidence: 99%

SAU-Net: A Novel Network for Building Extraction From High-Resolution Remote Sensing Images by Reconstructing Fine-Grained Semantic Features

Chen,

Mao,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The extraction of buildings from High-resolution Remote Sensing Imagery (HRSI) is crucial across various applications and stands as a pivotal task in the field of remote sensing. While recent methods based on convolutional neural networks exhibit superior performance in building extraction from HRSI, there are still challenges such as incomplete and missing extractions of buildings especially the building boundaries and the small buildings. To address these issues, we propose a Supervised Attention U-Net (SAU-Net), which combines a well-designed encoder and decoder. In the encoder, we incorporate a novel Residual Channel Attention Block (RCAB) and a Densely Connected Multidilated Convolutional Block (DMCB) to enhance semantic features in the channel and spatial dimensions, respectively. Additionally, in the decoder, we design a Supervised Attention Block (SAB) which reconstructs fine-grained semantic features by systematically refining features in a supervised way and efficiently integrating feature maps from both the encoding and decoding stages. The efficacy of SAU-Net is evaluated using four HRSI datasets encompassing varying scenarios. The experimental results highlight that SAU-Net exhibits superior performance in building extraction, particularly excelling in the extraction of building boundaries and small buildings.

show abstract

“…Although the current instance segmentation method has achieved excellent performance, it is rarely used in remote sensing images. Fang et al designed an attention module and a boundary optimization module to improve the detection performance of small target buildings [ 27 ]. Li et al used the Mask-RCNN framework to identify new and old buildings in rural areas [ 28 ].…”

Section: Introductionmentioning

confidence: 99%

A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images

Wei

Fan

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

It is very significant for rural planning to accurately count the number and area of rural homesteads by means of automation. The development of deep learning makes it possible to achieve this goal. At present, many effective works have been conducted to extract building objects from VHR images using semantic segmentation technology, but they do not extract instance objects and do not work for densely distributed and overlapping rural homesteads. Most of the existing mainstream instance segmentation frameworks are based on the top-down structure. The model is complex and requires a large number of manually set thresholds. In order to solve the above difficult problems, we designed a simple query-based instance segmentation framework, QueryFormer, which includes an encoder and a decoder. A multi-scale deformable attention mechanism is incorporated into the encoder, resulting in significant computational savings, while also achieving effective results. In the decoder, we designed multiple groups, and used a Many-to-One label assignment method to make the image feature region be queried faster. Experiments show that our method achieves better performance (52.8AP) than the other most advanced models (+0.8AP) in the task of extracting rural homesteads in dense regions. This study shows that query-based instance segmentation framework has strong application potential in remote sensing images.

show abstract

A Coarse-to-Fine Contour Optimization Network for Extracting Building Instances from High-Resolution Remote Sensing Imagery

Cited by 12 publications

References 44 publications

A benchmark GaoFen-7 dataset for building extraction from satellite images

A benchmark GaoFen-7 dataset for building extraction from satellite images

SAU-Net: A Novel Network for Building Extraction From High-Resolution Remote Sensing Images by Reconstructing Fine-Grained Semantic Features

A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images

Contact Info

Product

Resources

About