Multispectral Object Detection Based on Multilevel Feature Fusion and Dual Feature Modulation
Electronics · 21.01.2024 · 13 (2) · 443
DOI: 10.3390/electronics13020443 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 21.01.2024. Verfasst von Jin Sun und 4 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Research Project of Colleges and Universities of Jiangsu Province, Changzhou Applied Basic Research Project (Medium subsidy).
Abstract (Originalsprache)
Multispectral object detection is a crucial technology in remote sensing image processing, particularly in low-light environments. Most current methods extract features at a single scale, resulting in the fusion of invalid features and the failure to detect small objects. To address these issues, we propose a multispectral object detection network based on multilevel feature fusion and dual feature modulation (GMD-YOLO). Firstly, a novel dual-channel CSPDarknet53 network is used to extract deep features from visible-infrared images. This network incorporates a Ghost module, which generates additional feature maps through a series of linear operations, achieving a balance between accuracy and speed. Secondly, the multilevel feature fusion (MLF) module is designed to utilize cross-modal information through the construction of hierarchical residual connections. This approach strengthens the complementarity between different modalities, allowing the network to improve multiscale representation capabilities at a more refined granularity level. Finally, a dual feature modulation (DFM) decoupling head is introduced to enhance small object detection. This decoupled head effectively meets the distinct requirements of classification and localization tasks. GMD-YOLO is validated on three public visible-infrared datasets: DroneVehicle, KAIST, and LLVIP. DroneVehicle and LLVIP achieved mAP@0.5 of 78.0% and 98.0%, outperforming baseline methods by 3.6% and 4.4%, respectively. KAIST exhibited an MR of 7.73% with an FPS of 61.7. Experimental results demonstrated that our method surpasses existing advanced methods and exhibits strong robustness.
Förderung
- National Natural Science Foundation of China
- Natural Science Research Project of Colleges and Universities of Jiangsu Province
- Changzhou Applied Basic Research Project (Medium subsidy)
Zitieren
APA
Sun, J., Yin, M., Wang, Z., Xie, T., & Bei, S. (2024). Multispectral Object Detection Based on Multilevel Feature Fusion and Dual Feature Modulation. Electronics, 13(2), 443. https://doi.org/10.3390/electronics13020443
Vancouver
Sun J, Yin M, Wang Z, Xie T, Bei S. Multispectral Object Detection Based on Multilevel Feature Fusion and Dual Feature Modulation. Electronics. 2024;13(2):443. doi:10.3390/electronics13020443
BibTeX
@article{Sun2024,
author = {Sun, Jin and Yin, Mingfeng and Wang, Zhiwei and Xie, Tao and Bei, Shaoyi},
title = {Multispectral Object Detection Based on Multilevel Feature Fusion and Dual Feature Modulation},
journal = {Electronics},
year = {2024},
volume = {13},
number = {2},
pages = {443},
doi = {10.3390/electronics13020443}
}
EUVIMED