EUVIMEDEUVIMED entdecken
Crossref

HUNTNet: Homomorphic Unified Nexus Topology for Camouflaged Object Detection

Haolin Ji, Fengying Xie, Linpeng Pan, Yushan Zheng, Zhenwei Shi

IEEE Transactions on Image Processing · 2025 · 34 · 6068-6082

DOI: 10.1109/tip.2025.3607635 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Haolin Ji und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Camouflaged object detection (COD) is challenging for both human and computer vision, as targets often blend into the background by sharing similar color, texture, or shape. While many feature enhancement techniques exist, single-view methods tend to overemphasize certain Recognizing that camouflaged objects exhibit different concealment strategies under varying observational perspectives, we propose HUNTNet, a network that establishes a dynamic detection mechanism to decouple target features from RGB images and perform topological decamouflage across multiple homomorphic feature spaces through a unified feature focusing architecture. We adopt PVTv2 as the backbone to extract multi-perspective spatial features. Detail representation is enhanced via a feature module that integrates Dual-Channel Recursive (DCR), Wavelet-Gabor Transform (WGT), and Anisotropic Gradient Responding (AGR), which together improve boundary discrimination and edge contour detection. To further boost performance, the Simplicial Feature Integration (SFI) module recursively fuses multi-layer features, enabling high-resolution focus on target regions. Experiments show that HUNTNet surpasses state-of-the-art methods in both accuracy and generalization, offering a robust solution for COD and improving segmentation in complex scenes. Our code is available at https://github.com/HaolinJi817/HUNTNet.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Ji, H., Xie, F., Pan, L., Zheng, Y., & Shi, Z. (2025). HUNTNet: Homomorphic Unified Nexus Topology for Camouflaged Object Detection. IEEE Transactions on Image Processing, 34, 6068-6082. https://doi.org/10.1109/tip.2025.3607635

Vancouver

Ji H, Xie F, Pan L, Zheng Y, Shi Z. HUNTNet: Homomorphic Unified Nexus Topology for Camouflaged Object Detection. IEEE Transactions on Image Processing. 2025;34:6068-6082. doi:10.1109/tip.2025.3607635

BibTeX
@article{Ji2025,
  author = {Ji, Haolin and Xie, Fengying and Pan, Linpeng and Zheng, Yushan and Shi, Zhenwei},
  title = {HUNTNet: Homomorphic Unified Nexus Topology for Camouflaged Object Detection},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {6068--6082},
  doi = {10.1109/tip.2025.3607635}
}
Kostenlos starten →