A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automated building extraction using satellite remote sensing imagery
Abstract Automatic extraction of buildings from remote sensing images plays a critical role in urban planning and digital city construction applications. In real-world applications, however, real scenes can be highly complex (e.g., various building structures and shapes, presence of obstacles, and low contrast between buildings and surrounding regions), making automatic building extraction extremely challenging. To conquer this challenge, we propose a novel method called Deep Automatic Building Extraction Network (DABE-Net). It adopts squeeze-and-excitation (SE) operations and the residual recurrent convolutional neural network (RRCNN) to construct building-blocks. Furthermore, an attention mechanism is introduced into the network to improve segmentation accuracy. Specifically, to handle small buildings, we highlight small buildings and develop a multi-scale segmentation loss function. The theoretical analysis and experimental results show that the proposed method is effective in building extraction and outperforms several peer methods on the dataset of Mapping challenge competition.
Highlighs Satellite remote sensing imagery is used to Automated building extraction. A novel deep model is developed for automatic building extraction from remote sensing images. Results demonstrate that precision, recall rate and F1-score are highly improved. The proposed method can be applied to in urban planning and digital city construction applications.
Automated building extraction using satellite remote sensing imagery
Abstract Automatic extraction of buildings from remote sensing images plays a critical role in urban planning and digital city construction applications. In real-world applications, however, real scenes can be highly complex (e.g., various building structures and shapes, presence of obstacles, and low contrast between buildings and surrounding regions), making automatic building extraction extremely challenging. To conquer this challenge, we propose a novel method called Deep Automatic Building Extraction Network (DABE-Net). It adopts squeeze-and-excitation (SE) operations and the residual recurrent convolutional neural network (RRCNN) to construct building-blocks. Furthermore, an attention mechanism is introduced into the network to improve segmentation accuracy. Specifically, to handle small buildings, we highlight small buildings and develop a multi-scale segmentation loss function. The theoretical analysis and experimental results show that the proposed method is effective in building extraction and outperforms several peer methods on the dataset of Mapping challenge competition.
Highlighs Satellite remote sensing imagery is used to Automated building extraction. A novel deep model is developed for automatic building extraction from remote sensing images. Results demonstrate that precision, recall rate and F1-score are highly improved. The proposed method can be applied to in urban planning and digital city construction applications.
Automated building extraction using satellite remote sensing imagery
Hu, Qintao (author) / Zhen, Liangli (author) / Mao, Yao (author) / Zhou, Xi (author) / Zhou, Guozhong (author)
2020-09-29
Article (Journal)
Electronic Resource
English
Automated Building Damage Assessment Using Remote-Sensing Imagery
| British Library Conference Proceedings | 2007
Remote sensing of vegetation water content from equivalent water thickness using satellite imagery
| Online Contents | 2008
Hash-Based Deep Learning Approach for Remote Sensing Satellite Imagery Detection
| DOAJ | 2022
Dam reservoir extraction from remote sensing imagery using tailored metric learning strategies
| ArXiv | 2022