A Conditionally Parameterized Feature Fusion U-Net for Building Change Detection

Yao Gu, Chao Ren (), Qinyi Chen, Haoming Bai, Zhenzhong Huang and Lei Zou
Additional contact information
Yao Gu: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China
Chao Ren: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China
Qinyi Chen: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China
Haoming Bai: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China
Zhenzhong Huang: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China
Lei Zou: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China

Sustainability, 2024, vol. 16, issue 21, 1-20

Abstract: The semantic richness of remote sensing images often presents challenges in building detection, such as edge blurring, loss of detail, and low resolution. To address these issues and improve boundary precision, this paper proposes CCCUnet, a hybrid architecture developed for enhanced building extraction. CCCUnet integrates CondConv, Coord Attention, and a CGAFusion module to overcome the limitations of traditional U-Net-based methods. Additionally, the NLLLoss function is utilized in classification tasks to optimize model parameters during training. CondConv replaces standard convolution operations in the U-Net encoder, boosting model capacity and performance in building change detection while ensuring efficient inference. Coord Attention enhances the detection of complex contours in small buildings by utilizing its attention mechanism. Furthermore, the CGAFusion module combines channel and spatial attention in the skip connection structure, capturing both spatial and channel-wise correlations. Experimental results demonstrate that CCCUnet achieves high accuracy in building change detection, with improved edge refinement and the better detection of small building contours. Thus, CCCUnet serves as a valuable tool for precise building extraction from remote sensing images, with broad applications in urban planning, land use, and disaster monitoring.

Keywords: building change detection; small buildings; attention mechanism; feature fusion (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/16/21/9232/pdf (application/pdf)
https://www.mdpi.com/2071-1050/16/21/9232/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:16:y:2024:i:21:p:9232-:d:1505676

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().