EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Iterative Mamba Diffusion Change-Detection Model for Remote Sensing

Feixiang Liu, Yihan Wen, Jiayi Sun, Peipei Zhu, Liang Mao, Guanchong Niu, Jie Li

Remote Sensing · 30.09.2024 · 16 (19) · 3651

DOI: 10.3390/rs16193651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 30.09.2024. Verfasst von Feixiang Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Foundation of Shenzhen Polytechnic University, Guangdong Basic and Applied Basic Research Foundation, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the field of remote sensing (RS), change detection (CD) methods are critical for analyzing the quality of images shot over various geographical areas, particularly for high-resolution images. However, there are some shortcomings of the widely used Convolutional Neural Networks (CNNs) and Transformers-based CD methods. The former is limited by its insufficient long-range modeling capabilities, while the latter is hampered by its computational complexity. Additionally, the commonly used information-fusion methods for pre- and post-change images often lead to information loss or redundancy, resulting in inaccurate edge detection. To address these issues, we propose an Iterative Mamba Diffusion Change Detection (IMDCD) approach to iteratively integrate various pieces of information and efficiently produce fine-grained CD maps. Specifically, the Swin-Mamba-Encoder (SME) within Mamba-CD (MCD) is employed as a semantic feature extractor, capable of modeling long-range relationships with linear computability. Moreover, we introduce the Variable State Space CD (VSS-CD) module, which extracts abundant CD features by training the matrix parameters within the designed State Space Change Detection (SS-CD). The computed high-dimensional CD feature is integrated into the noise predictor using a novel Global Hybrid Attention Transformer (GHAT) while low-dimensional CD features are utilized to calibrate prior CD results at each iterative step, progressively refining the generated outcomes. IMDCD exhibits a high performance across multiple datasets such as the CDD, WHU, LEVIR, and OSCD, marking a significant advancement in the methodologies within the CD field of RS. The code for this work is available on GitHub.

Förderung

  • Research Foundation of Shenzhen Polytechnic University
  • Guangdong Basic and Applied Basic Research Foundation
  • Shenzhen Science and Technology Program
  • Fundamental Research Funds for the Central Universities of China
  • Guangdong Province Rural Science and Technology Commissioner project, zen tea reliable traceability and intelligent planting key technology research and develo…
  • Special project of Guangdong Provincial Education Department, research on abnormal behavior recognition technology of pregnant sows based on graph convolution
  • Guangdong Province Rural Science and Technology Commissioner project, cloud platform based agricultural products e-commerce platform construction and promotion…
  • Shenzhen Polytechnic University Smart Agriculture Innovation Application R&D center

Zitieren

APA

Liu, F., Wen, Y., Sun, J., Zhu, P., Mao, L., Niu, G., & Li, J. (2024). Iterative Mamba Diffusion Change-Detection Model for Remote Sensing. Remote Sensing, 16(19), 3651. https://doi.org/10.3390/rs16193651

Vancouver

Liu F, Wen Y, Sun J, Zhu P, Mao L, Niu G, et al. Iterative Mamba Diffusion Change-Detection Model for Remote Sensing. Remote Sensing. 2024;16(19):3651. doi:10.3390/rs16193651

BibTeX
@article{Liu2024,
  author = {Liu, Feixiang and Wen, Yihan and Sun, Jiayi and Zhu, Peipei and Mao, Liang and Niu, Guanchong and Li, Jie},
  title = {Iterative Mamba Diffusion Change-Detection Model for Remote Sensing},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {19},
  pages = {3651},
  doi = {10.3390/rs16193651}
}
Kostenlos starten →