Light-Aware Modality Balancing Network for Multimodal Pedestrian Detection
Mathematics · 06.05.2026 · 14 (9) · 1567
DOI: 10.3390/math14091567 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 06.05.2026. Verfasst von Yu Fu und 2 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Key Laboratory of Precision Manufacturing for Extreme Service Performance of Central South University.
Abstract (Originalsprache)
The visible light and infrared thermal multimodal images in autonomous driving provide a wealth of information for pedestrian detection, and its challenge lies in utilizing the complementary information across modalities to obtain an optimal joint representation. This study proposes a light-aware modality balancing network (LMB-Net) for pedestrian detection by fusing visible light and infrared thermal images. We designed an alignment complementary fusion module across modalities to exchange target information. Deformable convolutions are employed to automatically perform spatial deformation on features, thereby eliminating perception biases caused by misalignment. Furthermore, as the contribution of different modalities to pedestrian detection varies under different lighting conditions, we designed a light-aware module to utilize the distinct advantages of visible light and infrared thermal images. Extensive experiments on the KAIST and LLVIP datasets demonstrate that our method achieves the best detection performance compared to some other methods.
Förderung
- State Key Laboratory of Precision Manufacturing for Extreme Service Performance of Central South University
Zitieren
APA
Fu, Y., Zhang, F., & Li, Z. (2026). Light-Aware Modality Balancing Network for Multimodal Pedestrian Detection. Mathematics, 14(9), 1567. https://doi.org/10.3390/math14091567
Vancouver
Fu Y, Zhang F, Li Z. Light-Aware Modality Balancing Network for Multimodal Pedestrian Detection. Mathematics. 2026;14(9):1567. doi:10.3390/math14091567
BibTeX
@article{Fu2026,
author = {Fu, Yu and Zhang, Fan and Li, Zhou},
title = {Light-Aware Modality Balancing Network for Multimodal Pedestrian Detection},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {9},
pages = {1567},
doi = {10.3390/math14091567}
}
EUVIMED