EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-Supervised Deep Image Stitching for Moving Elongated Objects

Xiao Lai, Ziqi Xie iD, Xianhui Liu iD

Sensors · 11.08.2026 · 26 (16) · 5092

DOI: 10.3390/s26165092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.08.2026. Verfasst von Xiao Lai und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai 2025 Key Technology R&D Program New Generation Information Technology Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image-stitching methods for moving elongated objects require high stitching quality, efficient inference, and robustness to interference from regions outside the target object. Existing methods still have difficulty satisfying these requirements simultaneously. This paper proposes a semi-supervised deep image-stitching method for moving elongated objects. The proposed framework consists of two stages: semi-supervised registration and unsupervised reconstruction. In the semi-supervised registration stage, a semi-supervised optical-flow estimation network is used to predict the bidirectional optical flow between the input images. An object-centric spatial transformation module is then introduced to remove regions outside the moving object and warp the inputs onto a unified plane. In the unsupervised reconstruction stage, a multi-scale fusion model is used to improve the quality of the reconstructed stitched image. Correspondingly, we design a reconstruction objective function based on multi-scale feature representations. To address the lack of available datasets for this task, we construct two datasets: MEOIS-D, a synthetic dataset for generalized evaluation, and Container-D, a real-world scene-specific dataset. Extensive comparative experiments and ablation studies demonstrate the effectiveness of the proposed method.

Schlagwörter

Stichwörter der Autor:innen

deep image stitchingimage reconstructionimage registrationsemi-supervised learning

Autor:innen und Institutionen

  • School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.
  • College of Electronics and Information Engineering, Tongji University, Shanghai 200070, China.

ORCID-Profile: Ziqi Xie, Xianhui Liu

Förderung

  • Shanghai 2025 Key Technology R&D Program New Generation Information Technology Project

Zitieren

APA

Lai, X., Xie, Z., & Liu, X. (2026). Semi-Supervised Deep Image Stitching for Moving Elongated Objects. Sensors, 26(16), 5092. https://doi.org/10.3390/s26165092

Vancouver

Lai X, Xie Z, Liu X. Semi-Supervised Deep Image Stitching for Moving Elongated Objects. Sensors. 2026;26(16):5092. doi:10.3390/s26165092

BibTeX
@article{Lai2026,
  author = {Lai, Xiao and Xie, Ziqi and Liu, Xianhui},
  title = {Semi-Supervised Deep Image Stitching for Moving Elongated Objects},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5092},
  doi = {10.3390/s26165092}
}
Kostenlos starten →