EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Radar–Camera Fusion Deep Learning Model for Human Activity Recognition

Minkyung Jeon, Sungmin Woo iD

Sensors · 2026

DOI: 10.3390/s26030894 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Minkyung Jeon und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Engineering, Korea University of Technology and Education (KOREATECH), Cheonan-si 31253, Republic of Kore…. Hauptthemen laut MEDLINE: Radar, Deep Learning, Human Activities. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Basic Science Institute, Korea Regional Innovation System & Education, Korea Regional Innovation System & Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition in privacy-sensitive indoor environments requires sensing modalities that remain robust under illumination variation and background clutter while preserving user anonymity. To this end, this study proposes a lightweight radar–camera fusion deep learning model that integrates motion signatures from FMCW radar with coarse spatial cues from ultra-low-resolution camera frames. The radar stream is processed as a Range–Doppler–Time cube, where each frame is flattened and sequentially encoded using a Transformer-based temporal model to capture fine-grained micro-Doppler patterns. The visual stream employs a privacy-preserving 4×5-pixel camera input, from which a temporal sequence of difference frames is extracted and modeled with a dedicated camera Transformer encoder. The two modality-specific feature vectors—each representing the temporal dynamics of motion—are concatenated and passed through a lightweight fully connected classifier to predict human activity categories. A multimodal dataset of synchronized radar cubes and ultra-low-resolution camera sequences across 15 activity classes was constructed for evaluation. Experimental results show that the proposed fusion model achieves 98.74% classification accuracy, significantly outperforming single-modality baselines (single-radar and single-camera). Despite its performance, the entire model requires only 11 million floating-point operations (11 MFLOPs), making it highly efficient for deployment on embedded or edge devices.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadarDeep LearningHuman ActivitiesHumansAlgorithmsImage Processing, Computer-AssistedPattern Recognition, Automated

Stichwörter der Autor:innen

FMCW radarhuman activity recognitionlightweight deep learning modelmultimodal sensor fusionprivacy-preserving

Autor:innen und Institutionen

  • Department of Information and Communication Engineering, Korea University of Technology and Education (KOREATECH), Cheonan-si 31253, Republic of Korea.

ORCID-Profile: Sungmin Woo

Förderung

  • Korea Basic Science Institute
  • Korea Regional Innovation System & Education
  • Korea Regional Innovation System & Education

Zitieren

APA

Jeon, M., & Woo, S. (2026). A Lightweight Radar–Camera Fusion Deep Learning Model for Human Activity Recognition. Sensors. https://doi.org/10.3390/s26030894

Vancouver

Jeon M, Woo S. A Lightweight Radar–Camera Fusion Deep Learning Model for Human Activity Recognition. Sensors. 2026. doi:10.3390/s26030894

BibTeX
@article{Jeon2026,
  author = {Jeon, Minkyung and Woo, Sungmin},
  title = {A Lightweight Radar–Camera Fusion Deep Learning Model for Human Activity Recognition},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26030894}
}
Kostenlos starten →