Smart City Gnosys
Smart city article details
| Title | Building Type Classification Using Cnn-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images |
|---|---|
| ID_Doc | 13116 |
| Authors | Zhang S.; Li M.; Zhao W.; Wang X.; Wu Q. |
| Year | 2025 |
| Published | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18 |
| DOI | http://dx.doi.org/10.1109/JSTARS.2024.3501678 |
| Abstract | Building type information indicates the functional properties of buildings and plays a crucial role in smart city development and urban socioeconomic activities. Existing methods for classifying building types often face challenges in accurately distinguishing buildings between types while maintaining well-delineated boundaries, especially in complex urban environments. This study introduces a novel framework, i.e., CNN-Transformer cross-attention feature fusion network (CTCFNet), for building type classification from very high resolution remote sensing images. CTCFNet integrates convolutional neural networks (CNNs) and Transformers using an interactive cross-encoder fusion module that enhances semantic feature learning and improves classification accuracy in complex scenarios. We develop an adaptive collaboration optimization module that applies human visual attention mechanisms to enhance the feature representation of building types and boundaries simultaneously. To address the scarcity of datasets in building type classification, we create two new datasets, i.e., the urban building type (UBT) dataset and the town building type (TBT) dataset, for model evaluation. Extensive experiments on these datasets demonstrate that CTCFNet outperforms popular CNNs, Transformers, and dual-encoder methods in identifying building types across various regions, achieving the highest mean intersection over union of 78.20% and 77.11%, F1 scores of 86.83% and 88.22%, and overall accuracy of 95.07% and 95.73% on the UBT and TBT datasets, respectively. We conclude that CTCFNet effectively addresses the challenges of high interclass similarity and intraclass inconsistency in complex scenes, yielding results with well-delineated building boundaries and accurate building types. © 2008-2012 IEEE. |
| Author Keywords | Building type classification; CNN-transformer networks; cross-encoder; feature interaction; very high resolution remote sensing |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
4137  | 0.888 | Yang 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) |
| 47466 | 0.867 | Pan X.; Xu K.; Yang S.; Liu Y.; Zhang R.; He P. | Sda-Net: A Spatially Optimized Dual-Stream Network With Adaptive Global Attention For Building Extraction In Multi-Modal Remote Sensing Images | Sensors, 25, 7 (2025) |
| 21839 | 0.866 | Holail 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 Imagery | ISPRS Journal of Photogrammetry and Remote Sensing, 227 (2025) |
| 13125 | 0.866 | Yuan Q.; Wang N. | Buildings Change Detection Using High-Resolution Remote Sensing Images With Self-Attention Knowledge Distillation And Multiscale Change-Aware Module | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 46, M-2-2022 (2022) |
| 38966 | 0.863 | Zhou Y.; Jiang W.; Wang B. | Nesf-Net: Building Roof And Facade Segmentation Based On Neighborhood Relationship Awareness And Scale-Frequency Modulation Network For High-Resolution Remote Sensing Images | ISPRS Journal of Photogrammetry and Remote Sensing, 226 (2025) |
| 55087 | 0.861 | Sun H.; Xu H.; Wei Q. | The Classification Method Of Urban Architectural Styles Based On Deep Learning And Street View Imagery | Advances in Transdisciplinary Engineering, 31 (2022) |
| 13075 | 0.86 | Han Z.; Li X.; Wang X.; Wu Z.; Liu J. | Building Segmentation In Urban And Rural Areas With Mfa-Net: A Multidimensional Feature Adjustment Approach | Sensors, 25, 8 (2025) |
| 5676 | 0.858 | Chatterjee S.; Saha S.; Mahapatra P.R.S. | A Two-Stage Cnn Based Satellite Image Analysis Framework For Estimating Building-Count In Residential Built-Up Area | Lecture Notes in Networks and Systems, 998 LNNS (2024) |
| 2916 | 0.853 | Yin J.; Wu F.; Qiu Y.; Li A.; Liu C.; Gong X. | A Multiscale And Multitask Deep Learning Framework For Automatic Building Extraction | Remote Sensing, 14, 19 (2022) |
| 305 | 0.85 | Lu Z.; Xu T.; Liu K.; Liu Z.; Zhou F.; Liu Q. | 5M-Building: A Large-Scale High-Resolution Building Dataset With Cnn Based Detection Analysis | Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, 2019-November (2019) |