Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
RGB + NIR face-video fusion for driving. CSLM (cross-spectral linear modulation, implemented as FiLM-style gating in the repo) exchanges physiological-band info between streams; MS-Mamba models long-range temporal and cross-channel structure. Runs on RGB-only, NIR-only, or fused input (README).
- Authors
- Jiho Choi, Sang Jun Lee (Jeonbuk National University)
- Form factor
- camera_rppg
- Year
- 2026
ICRA 2026, pp. 10371–10378; DOI 10.1109/ICRA57385.2026.11695785; arXiv:2606.21115
- Code
https://github.com/ziiho08/MS-rPPG (stated in the paper; repo LICENSE is Responsible AI Source Code License v1.1)
- Datasets
MR-NIRP Car (paper: publicly available); MS-Drive (paper: collected from 50 participants while driving)
- Type
- Task model
- Modalities
- Not reported
- Form factor
- Camera rPPG
- Parameters
- Not reported
- Architecture
- Not reported
- Venue
- ICRA 2026
- Year
- 2026
- Weights
- Not reported
- Licence
- Responsible AI Source Code License v1.1 (licenses.ai) — use restrictions apply
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Not reported
- Updated
- Oct 26, 2026
Abstract
Remote photoplethysmography (rPPG) is a camera-based technique for measuring physiological signals, particularly cardiac activity. From the remotely measured signals, heart rate can be estimated, which is crucial for health monitoring. In this study, we investigate a driver health monitoring system based on remote heart rate estimation. However, driving environments represent uncontrolled settings where videos are subject to varying illumination conditions and frequent head movements. We introduce MS-rPPG, a multi-spectral framework that combines RGB with near-infrared (NIR) face video to alleviate rPPG estimation under challenging driving conditions. To combine the complementary features from two spectral videos, we propose a cross-spectral linear modulation (CSLM) strategy based on frequency-domain analysis. Moreover, we introduce MS-Mamba, a novel state space model designed to effectively model long-range temporal dependencies while jointly capturing cross-channel interactions between multi-spectral features. We collected a real-world dataset called MS-Drive, which was recorded from 50 participants while driving the vehicle. The proposed method was evaluated on the MR-NIRP Car dataset and MS-Drive datasets. The experimental results indicate that MS-rPPG shows better robustness and heart rate estimation accuracy than previous methods, highlighting its promise for driver health monitoring. The codes are available at github.com/ziiho08/MS-rPPG.
Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)
How it works
- Approach
- rppg · model · multi spectral · nir · mamba · state space
Datasets
Papers· 1
Cite
APA
Choi, J., & Lee, S. J. (2026). MS-rPPG: Multi-spectral State Space Model for Remote Photoplethysmography in Driver Monitoring Systems. ICRA 2026. https://doi.org/10.1109/ICRA57385.2026.11695785
BibTeX
@inproceedings{choi2026msrppg,
title = {{MS-rPPG: Multi-spectral State Space Model for Remote Photoplethysmography in Driver Monitoring Systems}},
author = {Choi, Jiho and Lee, Sang Jun},
year = {2026},
booktitle = {ICRA 2026},
doi = {10.1109/ICRA57385.2026.11695785},
eprint = {2606.21115},
archivePrefix = {arXiv}
}Built from the hub record. Check it against the publisher before submitting.
History
Record updated