EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-Supervised Image Stitching from Unstructured Camera Arrays

Erman Nghonda Tchinda iD, Maximillian Kealoha Panoff iD, Danielle Tchuinkou Kwadjo iD, Christophe Bobda iD

Sensors · 28.11.2023 · 23 (23) · 9481

DOI: 10.3390/s23239481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.11.2023. Verfasst von Erman Nghonda Tchinda und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, The Herbert Wertheim College of Engineering, University of Florida, Gainesville, FL 32611-6200, US…. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, University Of Florida via Dr. Christophe Bobda.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image stitching involves combining multiple images of the same scene captured from different viewpoints into a single image with an expanded field of view. While this technique has various applications in computer vision, traditional methods rely on the successive stitching of image pairs taken from multiple cameras. While this approach is effective for organized camera arrays, it can pose challenges for unstructured ones, especially when handling scene overlaps. This paper presents a deep learning-based approach for stitching images from large unstructured camera sets covering complex scenes. Our method processes images concurrently by using the SandFall algorithm to transform data from multiple cameras into a reduced fixed array, thereby minimizing data loss. A customized convolutional neural network then processes these data to produce the final image. By stitching images simultaneously, our method avoids the potential cascading errors seen in sequential pairwise stitching while offering improved time efficiency. In addition, we detail an unsupervised training method for the network utilizing metrics from Generative Adversarial Networks supplemented with supervised learning. Our testing revealed that the proposed approach operates in roughly ∼1/7th the time of many traditional methods on both CPU and GPU platforms, achieving results consistent with established methods.

Schlagwörter

Stichwörter der Autor:innen

image blendingimage stitchingscene representationself-supervised learningunstructured camera arrays

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, The Herbert Wertheim College of Engineering, University of Florida, Gainesville, FL 32611-6200, USA.

ORCID-Profile: Erman Nghonda Tchinda, Maximillian Kealoha Panoff, Danielle Tchuinkou Kwadjo, Christophe Bobda

Förderung

  • National Science Foundation
  • University Of Florida via Dr. Christophe Bobda

Zitieren

APA

Nghonda Tchinda, E., Panoff, M. K., Tchuinkou Kwadjo, D., & Bobda, C. (2023). Semi-Supervised Image Stitching from Unstructured Camera Arrays. Sensors, 23(23), 9481. https://doi.org/10.3390/s23239481

Vancouver

Nghonda Tchinda E, Panoff MK, Tchuinkou Kwadjo D, Bobda C. Semi-Supervised Image Stitching from Unstructured Camera Arrays. Sensors. 2023;23(23):9481. doi:10.3390/s23239481

BibTeX
@article{NghondaTchinda2023,
  author = {Nghonda Tchinda, Erman and Panoff, Maximillian Kealoha and Tchuinkou Kwadjo, Danielle and Bobda, Christophe},
  title = {Semi-Supervised Image Stitching from Unstructured Camera Arrays},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {23},
  pages = {9481},
  doi = {10.3390/s23239481}
}
Kostenlos starten →