EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSAFusion: A Lightweight Multispectral Pedestrian Detection Network with Multi-Scale and Adaptive Feature Fusion

Yang Song, Xin Zuo, Chenyu Qu, Qiang Qian iD, Dengbiao Jiang

Journal of Imaging · 30.05.2026 · 12 (6) · 246

DOI: 10.3390/jimaging12060246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 30.05.2026. Verfasst von Yang Song und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hangzhou Boomy Intelligent Technology Co., Ltd..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Robust multispectral pedestrian detection remains challenging in complex environments such as those with low illumination, strong thermal contrast, and background clutter. Although RGB–thermal fusion provides complementary cues, lightweight detectors often suffer from unstable feature representation across scales and insufficient control over modality-biased responses during fusion, which can degrade localization accuracy and weaken the detection of small or distant pedestrians. To address these issues, we develop a lightweight stage-wise RGB–thermal fusion pipeline that integrates pre-fusion feature refinement, cross-modal interaction, and post-fusion adaptive recalibration. Specifically, a Multi-scale Feature Refinement (MSFR) module is proposed at the mid-level to enhance modality-specific representations by jointly modeling local details and contextual information, thereby reducing scale-sensitive noise before interaction. An established Cross-Modality Fusion Transformer (CFT) is then adopted to promote semantic correspondence between RGB and thermal features. After interaction, an Adaptive Feature Recalibration (AFR) module is introduced to suppress background-dominated and modality-biased responses through lightweight channel-wise adjustment. Extensive experiments on three public RGB–thermal benchmarks, including the pedestrian-focused KAIST and LLVIP datasets together with the FLIR-aligned road-scene benchmark, demonstrate that the proposed method achieves a favorable accuracy–efficiency trade-off, delivering consistent improvements over the lightweight baseline while maintaining a compact architecture and real-time inference capability.

Schlagwörter

Stichwörter der Autor:innen

RGB–thermal pedestrian detectionadaptive feature recalibrationlightweight architecturemulti-scale feature refinementmultispectral pedestrian detectionsmall-object detection

Autor:innen und Institutionen

  • School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China.

ORCID-Profile: Qiang Qian

Förderung

  • Hangzhou Boomy Intelligent Technology Co., Ltd.

Zitieren

APA

Song, Y., Zuo, X., Qu, C., Qian, Q., & Jiang, D. (2026). MSAFusion: A Lightweight Multispectral Pedestrian Detection Network with Multi-Scale and Adaptive Feature Fusion. Journal of Imaging, 12(6), 246. https://doi.org/10.3390/jimaging12060246

Vancouver

Song Y, Zuo X, Qu C, Qian Q, Jiang D. MSAFusion: A Lightweight Multispectral Pedestrian Detection Network with Multi-Scale and Adaptive Feature Fusion. Journal of Imaging. 2026;12(6):246. doi:10.3390/jimaging12060246

BibTeX
@article{Song2026,
  author = {Song, Yang and Zuo, Xin and Qu, Chenyu and Qian, Qiang and Jiang, Dengbiao},
  title = {MSAFusion: A Lightweight Multispectral Pedestrian Detection Network with Multi-Scale and Adaptive Feature Fusion},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {6},
  pages = {246},
  doi = {10.3390/jimaging12060246}
}
Kostenlos starten →