EUVIMEDEUVIMED entdecken
Crossref

Co-Enhancement of Multi-Modality Image Fusion and Object Detection via Feature Adaptation

Aimei Dong, Long Wang, Jian Liu, Jingyuan Xu, Guixin Zhao, Yi Zhai, Guohua Lv, Jinyong Cheng

IEEE Transactions on Circuits and Systems for Video Technology · 2024-12 · 34 (12) · 12624-12637

DOI: 10.1109/tcsvt.2024.3433555 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-12. Verfasst von Aimei Dong und 7 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Shandong Provincial Natural Science Foundation, Talent Research Projects of Qilu University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of multi-modality images significantly enhances the clarity of critical details for object detection. Valuable semantic data from object detection enriches the fusion process of these images. However, the potential reciprocal relationship that could enhance their mutual performance remains largely unexplored and underutilized, despite some semantic-driven fusion methodologies catering to specific application needs. To address these limitations, this study proposes a mutually reinforcing, dual-task-driven fusion architecture. Specifically, our design integrates a feature-adaptive interlinking module into both image fusion and object detection components, effectively managing the inherent feature discrepancies. The core idea is to channel distinct features from both tasks into a unified feature space after feature transformation. We then design a feature-adaptive selection module to generate features rich in target semantic information and compatible with the fusion network. Finally, effective combination and mutual enhancement of the two tasks are achieved through an alternating training process. A diverse range of swift evaluations is performed across various datasets to corroborate the potential efficiency of our framework, actualizing visible advancements in both fusion effectiveness and detection accuracy.

Förderung

  • Shandong Provincial Natural Science Foundation
  • Talent Research Projects of Qilu University of Technology

Zitieren

APA

Dong, A., Wang, L., Liu, J., Xu, J., Zhao, G., Zhai, Y., Lv, G., & Cheng, J. (2024). Co-Enhancement of Multi-Modality Image Fusion and Object Detection via Feature Adaptation. IEEE Transactions on Circuits and Systems for Video Technology, 34(12), 12624-12637. https://doi.org/10.1109/tcsvt.2024.3433555

Vancouver

Dong A, Wang L, Liu J, Xu J, Zhao G, Zhai Y, et al. Co-Enhancement of Multi-Modality Image Fusion and Object Detection via Feature Adaptation. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(12):12624-12637. doi:10.1109/tcsvt.2024.3433555

BibTeX
@article{Dong2024,
  author = {Dong, Aimei and Wang, Long and Liu, Jian and Xu, Jingyuan and Zhao, Guixin and Zhai, Yi and Lv, Guohua and Cheng, Jinyong},
  title = {Co-Enhancement of Multi-Modality Image Fusion and Object Detection via Feature Adaptation},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {12},
  pages = {12624--12637},
  doi = {10.1109/tcsvt.2024.3433555}
}
Kostenlos starten →