EUVIMEDEUVIMED entdecken
Crossref

DSCNet: lightweight and efficient self-supervised network via depthwise separable cross convolution blocks for speckle image matching

Lin Li, Peng Wang, Lingrui Wang, Changku Sun, Luhua Fu

Optics Express · 11.03.2024 · 32 (6) · 10715

DOI: 10.1364/oe.519957 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 08.03.2024. Verfasst von Lin Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 36 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speckle structured light has become a research hotspot due to its ability to acquire target three-dimensional information with single image projection in recent years. To address the challenges of a low number of extracted speckle feature points, high mismatch rate and poor real-time performance in traditional algorithms, as well as the obstacle of requiring expensive annotation data in deep learning-based methods, a lightweight and efficient self-supervised convolutional neural network (CNN) is proposed to achieve high-precision and rapid matching of speckle images. First, to efficiently utilize the speckle projection information, a feature extraction backbone based on the depthwise separable cross convolution blocks is proposed. Second, in the feature detection module, a softargmax detection head is designed to refine the coordinates of speckle feature points to sub-pixel accuracy. In the feature description module, a coarse-to-fine module is presented to further refine matching accuracy. Third, we adopt strategies of transfer learning and self-supervised learning to improve the generalization and feature representation capabilities of the model. Data augmentation and real-time training techniques are used to improve the robustness of the model. The experimental results show that the proposed method achieves a mean matching accuracy of 91.62% for speckle feature points on the pilot’s helmet, with mere 0.95% mismatch rate. The full model runs at 42ms for a speckle image pair on an RTX 3060.

Zitieren

APA

Li, L., Wang, P., Wang, L., Sun, C., & Fu, L. (2024). DSCNet: lightweight and efficient self-supervised network via depthwise separable cross convolution blocks for speckle image matching. Optics Express, 32(6), 10715. https://doi.org/10.1364/oe.519957

Vancouver

Li L, Wang P, Wang L, Sun C, Fu L. DSCNet: lightweight and efficient self-supervised network via depthwise separable cross convolution blocks for speckle image matching. Optics Express. 2024;32(6):10715. doi:10.1364/oe.519957

BibTeX
@article{Li2024,
  author = {Li, Lin and Wang, Peng and Wang, Lingrui and Sun, Changku and Fu, Luhua},
  title = {DSCNet: lightweight and efficient self-supervised network via depthwise separable cross convolution blocks for speckle image matching},
  journal = {Optics Express},
  year = {2024},
  volume = {32},
  number = {6},
  pages = {10715},
  doi = {10.1364/oe.519957}
}
Kostenlos starten →