EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient UAV High-Resolution Image Stitching via Dense Deep Kernelized Feature

Jianglei Zhou iD, Zhaoyu Wei, Yisen Zhong iD, Xianqiang He

Sensors · 28.02.2026 · 26 (5) · 1540

DOI: 10.3390/s26051540 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.02.2026. Verfasst von Jianglei Zhou und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unmanned aerial vehicle (UAV) image stitching aims to generate panoramic remote sensing images beyond the field of view of a single camera. However, there are still significant challenges in constructing panoramic images of a target area quickly and accurately, especially in terms of computationally intensive feature matching extraction and feature alignment accuracy, which are particularly sensitive to high-resolution and low-texture scenes. To address this problem, this study proposes an efficient image stitching method that incorporates dense depth kernelized feature extraction and geometric constraint optimization. The learning-based kernelized feature matching framework is adopted to achieve subpixel-level dense matching, which effectively overcomes the time-consuming and sparse matching deficiencies of traditional manual features (e.g., SIFT) in high-resolution images. Second, a two-layer geometrically constrained mismatching filtering strategy is designed, which significantly improves the alignment accuracy in low-texture and large-parallax scenarios. Finally, panoramic stitching is achieved through a hybrid strategy consisting of a single-responsive transform and max-intensity pixel blending strategy to realize panoramic stitching. Experimental results obtained on multiple datasets show that the proposed method achieves similar visual quality metrics (PSNR, SSIM, and LPIPS) while reducing the stitching time to just 17.5% of that of the baseline method. This makes it a practical solution for efficiently stitching large UAV images.

Schlagwörter

Stichwörter der Autor:innen

dense deep featureefficient stitchinghigh-resolution imagehomographyunmanned aerial vehicle (UAV)

Autor:innen und Institutionen

  • School of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, China.
  • State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China.

ORCID-Profile: Jianglei Zhou, Yisen Zhong

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhou, J., Wei, Z., Zhong, Y., & He, X. (2026). Efficient UAV High-Resolution Image Stitching via Dense Deep Kernelized Feature. Sensors, 26(5), 1540. https://doi.org/10.3390/s26051540

Vancouver

Zhou J, Wei Z, Zhong Y, He X. Efficient UAV High-Resolution Image Stitching via Dense Deep Kernelized Feature. Sensors. 2026;26(5):1540. doi:10.3390/s26051540

BibTeX
@article{Zhou2026,
  author = {Zhou, Jianglei and Wei, Zhaoyu and Zhong, Yisen and He, Xianqiang},
  title = {Efficient UAV High-Resolution Image Stitching via Dense Deep Kernelized Feature},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {5},
  pages = {1540},
  doi = {10.3390/s26051540}
}
Kostenlos starten →