Smart City Gnosys

Smart city article details

Title Buildings Change Detection Using High-Resolution Remote Sensing Images With Self-Attention Knowledge Distillation And Multiscale Change-Aware Module
ID_Doc 13125
Authors Yuan Q.; Wang N.
Year 2022
Published International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 46, M-2-2022
DOI http://dx.doi.org/10.5194/isprs-Archives-XLVI-M-2-2022-225-2022
Abstract Building change detection from remote sensing images is vital for many applications such as urban planning and dynamic monitoring, smart city construction, and geographical information census. In recent years, with the improvement of artificial intelligence and computer vision techniques, deep learning algorithms, especially convolutional neural networks (CNN), provide automatic detection and extraction methods. Unlike traditional approaches relying on shallow manual features, CNN can generate the deep semantic features by fusing spatial and spectral information, which is conducive to identifying building change regions. However, most deep CNN models directly fuse different level features and recover spatial details, which probably introduce redundant background information and noise from shallow layers. Considering the building's multiscale, convolution operation with fixed receptive fields cannot obtain a strong global feature response to changed regions. To address the above problems, we develop a CNN framework for automatic building region change detection using dual-Temporal high-resolution remote sensing images. To refine the shallow features, self-Attention knowledge distillation strategies are introduced to FCN. Furthermore, we propose the multiscale feature change-Aware module to integrate the globally changed information in different decoders. Finally, the model aggregates the multi-scale regional change information and outputs the prediction map. The results of comparative visual analysis and quantitative evaluation in two public datasets demonstrate that the proposed network model can improve the accuracy and efficiency of the automatic building change detection (85.69 IoU, 97.56 OA on the WHU dataset, and 83.72 IoU, 97.64 OA on the LEVIR-CD dataset). © 2022 Q. Yuan.
Author Keywords Building change detection; Convolutional neural network; Deep learning; Knowledge distillation; Self-Attention


Similar Articles

Id Similarity Authors Title Published
21845 View0.902Yang M.; Zhou Y.; Feng Y.; Huo S.Edge-Guided Hierarchical Network For Building Change Detection In Remote Sensing ImagesApplied Sciences (Switzerland), 14, 13 (2024)
21839 View0.898Holail S.; Saleh T.; Xiao X.; Zahran M.; Xia G.-S.; Li D.Edge-Cvt: Edge-Informed Cnn And Vision Transformer For Building Change Detection In Satellite ImageryISPRS Journal of Photogrammetry and Remote Sensing, 227 (2025)
48330 View0.889Sun C.; Chen H.; Du C.; Jing N.Semibuildingchange: A Semi-Supervised High-Resolution Remote Sensing Image Building Change Detection Method With A Pseudo Bitemporal Data GeneratorIEEE Transactions on Geoscience and Remote Sensing, 61 (2023)
4137 View0.887Yang M.; Zhao L.; Ye L.; Jiang H.; Yang Z.A Review Of Convolutional Neural Networks Related Methods For Building Extraction From Remote Sensing Images; [基于卷积神经网络的遥感影像建筑物提取方法综述]Journal of Geo-Information Science, 26, 6 (2024)
305 View0.875Lu Z.; Xu T.; Liu K.; Liu Z.; Zhou F.; Liu Q.5M-Building: A Large-Scale High-Resolution Building Dataset With Cnn Based Detection AnalysisProceedings - International Conference on Tools with Artificial Intelligence, ICTAI, 2019-November (2019)
18080 View0.868Bao H.; Zerres V.H.D.; Lehnert L.W.Deep Siamese Network For Annual Change Detection In Beijing Using Landsat Satellite DataInternational Journal of Applied Earth Observation and Geoinformation, 130 (2024)
13116 View0.866Zhang S.; Li M.; Zhao W.; Wang X.; Wu Q.Building Type Classification Using Cnn-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18 (2025)
2916 View0.862Yin J.; Wu F.; Qiu Y.; Li A.; Liu C.; Gong X.A Multiscale And Multitask Deep Learning Framework For Automatic Building ExtractionRemote Sensing, 14, 19 (2022)
26526 View0.858Wang Z.; Zhou Y.; Wang F.; Wang S.; Qin G.; Zou W.; Wang Z.; Liu S.; Zhu J.Fine-Grained Building Extraction With Multispectral Remote Sensing Imagery Using The Deep ModelIEEE Transactions on Geoscience and Remote Sensing, 61 (2023)
8040 View0.858Gonthina N.; Narasimha Prasad L.V.An Enhanced Convolutional Neural Network Architecture For Semantic Segmentation In High-Resolution Remote Sensing ImagesDiscover Computing, 28, 1 (2025)