EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Features Split and Aggregation Network for Camouflaged Object Detection

Zejin Zhang, Tao Wang iD, Jian Wang, Yao Sun

Journal of Imaging · 18.01.2024 · 10 (1) · 24

DOI: 10.3390/jimaging10010024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 18.01.2024. Verfasst von Zejin Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou 310018, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Higher standards have been proposed for detection systems since camouflaged objects are not distinct enough, making it possible to ignore the difference between their background and foreground. In this paper, we present a new framework for Camouflaged Object Detection (COD) named FSANet, which consists mainly of three operations: spatial detail mining (SDM), cross-scale feature combination (CFC), and hierarchical feature aggregation decoder (HFAD). The framework simulates the three-stage detection process of the human visual mechanism when observing a camouflaged scene. Specifically, we have extracted five feature layers using the backbone and divided them into two parts with the second layer as the boundary. The SDM module simulates the human cursory inspection of the camouflaged objects to gather spatial details (such as edge, texture, etc.) and fuses the features to create a cursory impression. The CFC module is used to observe high-level features from various viewing angles and extracts the same features by thoroughly filtering features of various levels. We also design side-join multiplication in the CFC module to avoid detail distortion and use feature element-wise multiplication to filter out noise. Finally, we construct an HFAD module to deeply mine effective features from these two stages, direct the fusion of low-level features using high-level semantic knowledge, and improve the camouflage map using hierarchical cascade technology. Compared to the nineteen deep-learning-based methods in terms of seven widely used metrics, our proposed framework has clear advantages on four public COD datasets, demonstrating the effectiveness and superiority of our model.

Schlagwörter

Stichwörter der Autor:innen

bio-inspired networkcamouflaged object detectioncontext-aware featuresmulti-scale features

Autor:innen und Institutionen

  • HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou 310018, China.
  • School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China.

ORCID-Profile: Tao Wang

Zitieren

APA

Zhang, Z., Wang, T., Wang, J., & Sun, Y. (2024). Features Split and Aggregation Network for Camouflaged Object Detection. Journal of Imaging, 10(1), 24. https://doi.org/10.3390/jimaging10010024

Vancouver

Zhang Z, Wang T, Wang J, Sun Y. Features Split and Aggregation Network for Camouflaged Object Detection. Journal of Imaging. 2024;10(1):24. doi:10.3390/jimaging10010024

BibTeX
@article{Zhang2024,
  author = {Zhang, Zejin and Wang, Tao and Wang, Jian and Sun, Yao},
  title = {Features Split and Aggregation Network for Camouflaged Object Detection},
  journal = {Journal of Imaging},
  year = {2024},
  volume = {10},
  number = {1},
  pages = {24},
  doi = {10.3390/jimaging10010024}
}
Kostenlos starten →