Semi-Supervised Building Detection from High-Resolution Remote Sensing Imagery

Daoyuan Zheng, Jia-Ning Kang, Kaishun Wu, Yuting Feng, Han Guo (), Xiaoyun Zheng, Shengwen Li and Fang Fang
Additional contact information
Daoyuan Zheng: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Kaishun Wu: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Yuting Feng: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Han Guo: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Xiaoyun Zheng: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Shengwen Li: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Fang Fang: Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China

Sustainability, 2023, vol. 15, issue 15, 1-22

Abstract: Urban building information reflects the status and trends of a region’s development and is essential for urban sustainability. Detection of buildings from high-resolution (HR) remote sensing images (RSIs) provides a practical approach for quickly acquiring building information. Mainstream building detection methods are based on fully supervised deep learning networks, which require a large number of labeled RSIs. In practice, manually labeling building instances in RSIs is labor-intensive and time-consuming. This study introduces semi-supervised deep learning techniques for building detection and proposes a semi-supervised building detection framework to alleviate this problem. Specifically, the framework is based on teacher–student mutual learning and consists of two key modules: the color and Gaussian augmentation (CGA) module and the consistency learning (CL) module. The CGA module is designed to enrich the diversity of building features and the quantity of labeled images for better training of an object detector. The CL module derives a novel consistency loss by imposing consistency of predictions from augmented unlabeled images to enhance the detection ability on the unlabeled RSIs. The experimental results on three challenging datasets show that the proposed framework outperforms state-of-the-art building detection methods and semi-supervised object detection methods. This study develops a new approach for optimizing the building detection task and a methodological reference for the various object detection tasks on RSIs.

Keywords: building detection; high-resolution remote sensing imagery; semi-supervised deep learning; object detection; consistency learning (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/15/11789/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/15/11789/ (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:15:y:2023:i:15:p:11789-:d:1207877

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 ().