EUVIMEDEUVIMED entdecken
Crossref

Frequency Domain-Based Cross-Layer Feature Aggregation Network for Camouflaged Object Detection

Chunhong Ren, Anzhi Wang, Chengbang Yang, Jintao Wu, Minghui Wang

IEEE Signal Processing Letters · 2025 · 32 · 2005-2009

DOI: 10.1109/lsp.2025.3549010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Chunhong Ren und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Academic Xinmiao Project of Guizhou Normal University, Guizhou Province Department of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the progress of existing techniques in Camouflaged Object Detection, there are still problems such as multi-target omission, small-object misjudgment, and insufficient localization and segmentation accuracy. With the advantage of image frequency domain transformation, high-frequency features can capture detailed information such as edges and textures of the image, while low-frequency features depict the overall outline of the image, improving the accuracy of camouflage object detection. Therefore, this paper proposes a Frequency Domain-Based Cross-layer Feature Aggregation Network (FCFANet), aiming to improve the problems of multi-target omission, small target loss, object localization deviation, and insufficient segmentation accuracy in complex scenes. FCFANet mainly consists of an Intra- and Inter-layer Enhancement Module (IEM) and a Frequency-Spatial Interaction Fusion Module (FSIFM). IEM reduces noise and enhances the feature representation, while FSIFM extracts frequency information, and enhances feature discrimination by complementary fusion of spatial and frequency domains, thus realizing the precise positioning and high-precision segmentation of camouflaged objects. Compared with 16 state-of-the-art(SOTA) methods, experiments show that FCFANet outperforms other SOTA methods on four benchmark datasets.

Förderung

  • National Natural Science Foundation of China
  • Academic Xinmiao Project of Guizhou Normal University
  • Guizhou Province Department of Science and Technology

Zitieren

APA

Ren, C., Wang, A., Yang, C., Wu, J., & Wang, M. (2025). Frequency Domain-Based Cross-Layer Feature Aggregation Network for Camouflaged Object Detection. IEEE Signal Processing Letters, 32, 2005-2009. https://doi.org/10.1109/lsp.2025.3549010

Vancouver

Ren C, Wang A, Yang C, Wu J, Wang M. Frequency Domain-Based Cross-Layer Feature Aggregation Network for Camouflaged Object Detection. IEEE Signal Processing Letters. 2025;32:2005-2009. doi:10.1109/lsp.2025.3549010

BibTeX
@article{Ren2025,
  author = {Ren, Chunhong and Wang, Anzhi and Yang, Chengbang and Wu, Jintao and Wang, Minghui},
  title = {Frequency Domain-Based Cross-Layer Feature Aggregation Network for Camouflaged Object Detection},
  journal = {IEEE Signal Processing Letters},
  year = {2025},
  volume = {32},
  pages = {2005--2009},
  doi = {10.1109/lsp.2025.3549010}
}
Kostenlos starten →