EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimized Reinforcement Learning-Driven Model for Remote Sensing Change Detection

Yan Zhao, Zhiyun Xiao, Tengfei Bao iD, Yulong Zhou iD

Journal of Imaging · 19.03.2026 · 12 (3) · 139

DOI: 10.3390/jimaging12030139 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 19.03.2026. Verfasst von Yan Zhao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electric Power, Inner Mongolia University of Technology, Hohhot 010080, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science and Technology Revitalization Project of Inner Mongolia, the Natural Science Foundation of Inner Mongolia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, deep learning has driven remarkable progress in remote sensing change detection (CD); however, practical deployment is still hindered by two limitations. First, CD results are easily degraded by imaging-induced uncertainties—mixed pixels and blurred boundaries, radiometric inconsistencies (e.g., shadows and seasonal illumination changes), and slight residual misregistration—leading to pseudo-changes and fragmented boundaries. Second, prevailing methods follow a static one-pass inference paradigm and lack an explicit feedback mechanism for adaptive error correction, which weakens generalization in complex or unseen scenes. To address these issues, we propose a feedback-driven CD framework that integrates a dual-branch U-Net with deep reinforcement learning (RL) for pixel-level probabilistic iterative refinement of an initial change probability map. The backbone produces a preliminary posterior estimate of change likelihood from multi-scale bi-temporal features, while a PPO-based RL agent formulates refinement as a Markov decision process. The agent leverages a state representation that fuses multi-scale features, prediction confidence/uncertainty, and spatial consistency cues (e.g., neighborhood coherence and edge responses) to apply multi-step corrective actions. From an imaging and interpretation perspective, the RL module can be viewed as a learnable, self-adaptive imaging optimization mechanism: for high-risk regions affected by blurred boundaries, radiometric inconsistencies, and local misalignment, the agent performs feedback-driven multi-step corrections to improve boundary fidelity and spatial coherence while suppressing pseudo-changes caused by shadows and illumination variations. Experiments on four datasets (CDD, SYSU-CD, PVCD, and BRIGHT) verify consistent improvements. Using SiamU-Net as an example, the proposed RL refinement increases mIoU by 3.07, 2.54, 6.13, and 3.1 points on CDD, SYSU-CD, PVCD, and BRIGHT, respectively, with similarly consistent gains observed when the same RL module is integrated into other representative CD backbones.

Schlagwörter

Stichwörter der Autor:innen

U-NetUAV datasetadaptive segmentationdeep learningreinforcement learningremote sensing change detection

Autor:innen und Institutionen

  • School of Electric Power, Inner Mongolia University of Technology, Hohhot 010080, China.
  • Intelligent Energy Technology and Equipment Engineering Research Center of Colleges and Universities of Inner Mongolia Autonomous Region, Inner Mongolia University of Technology, Hohhot 010080, China.
  • Inner Mongolia Key Laboratory of Electrical and Mechanical Control, Inner Mongolia University of Technology, Hohhot 010080, China.
  • School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.

ORCID-Profile: Tengfei Bao, Yulong Zhou

Förderung

  • the Science and Technology Revitalization Project of Inner Mongolia
  • the Natural Science Foundation of Inner Mongolia

Zitieren

APA

Zhao, Y., Xiao, Z., Bao, T., & Zhou, Y. (2026). Optimized Reinforcement Learning-Driven Model for Remote Sensing Change Detection. Journal of Imaging, 12(3), 139. https://doi.org/10.3390/jimaging12030139

Vancouver

Zhao Y, Xiao Z, Bao T, Zhou Y. Optimized Reinforcement Learning-Driven Model for Remote Sensing Change Detection. Journal of Imaging. 2026;12(3):139. doi:10.3390/jimaging12030139

BibTeX
@article{Zhao2026,
  author = {Zhao, Yan and Xiao, Zhiyun and Bao, Tengfei and Zhou, Yulong},
  title = {Optimized Reinforcement Learning-Driven Model for Remote Sensing Change Detection},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {3},
  pages = {139},
  doi = {10.3390/jimaging12030139}
}
Kostenlos starten →