Real Time Estimation of Heart Rate under Lighting of Smartphone Camera

Abstract

This paper presents an innovative approach for real-time heart rate estimation using a smartphone camera, addressing the challenges posed by fluctuating lighting conditions and motion artifacts. By merging sophisticated image processing techniques with machine learning algorithms, the system effectively extracts the fundamental photoplethysmogram (PPG) signal. PPG is a well-established, non- invasive optical method that assesses fluctuations in light absorption caused by variations in blood volume within tissues, with applications that extend beyond merely monitoring heart rate and oxygen saturation. The suggested approach enhances measurement precision and reliability by integrating robust signal processing methods with video frame analysis of the user\'s face, thereby ensuring consistent performance in everyday, uncontrolled settings. As PPG becomes increasingly significant in clinical and wearable health technologies, this research aids in broadening its applicability for mobile health monitoring solutions. Experimental validation demonstrates that the smartphone-based system achieves accuracy on par with traditional medical devices while providing improved portability, cost-effectiveness, and user-friendliness. The results underscore the potential of smartphone-integrated health monitoring systems as viable, scalable options for personal and remote healthcare management.

Introduction

Traditional heart rate monitoring relies on specialized tools like ECGs, but modern smartphones can now estimate heart rate using their cameras via photoplethysmography (PPG). This technique detects blood volume changes by analyzing light absorption fluctuations when a fingertip covers the camera lens, allowing real-time, non-invasive, and cost-effective heart rate tracking.

Despite its promise, smartphone-based heart rate monitoring faces challenges including variable lighting, motion artifacts, skin tone diversity, and battery constraints. Advances in signal processing, adaptive algorithms, and machine learning have improved accuracy, robustness, and efficiency. Studies show progress in handling motion artifacts, lighting changes, and optimizing algorithms for real-time use on mobile devices. Integration with telemedicine and fitness ecosystems further enhances its utility.

A proposed framework involves advanced signal processing combined with machine learning to reduce noise and motion artifacts, adaptive techniques to manage lighting, personalized calibration for skin tones, and strong privacy measures. Collaboration with smartphone manufacturers could improve hardware capabilities for more consistent measurements.

The system uses video frames capturing subtle skin color changes, focusing on the green channel for heart rate extraction. Preprocessing using deep learning models like ResNet enhances feature extraction and noise reduction, enabling accurate real-time heart rate estimation displayed instantly to users.

In sum, smartphone camera-based heart rate monitoring is evolving towards a reliable, accessible, and efficient health tool by addressing technical limitations, ensuring inclusivity, and protecting user privacy.

Conclusion

In conclusion, the real-time heart rate estimation via a smartphone camera is a promising and practical approach for personal health monitoring. Although there are still areas for improvement, the fact that one can monitor his or her heart rate non-invasively and continuously through a smartphone offers a significant advantage to users and healthcare professionals. The advancements of smartphone technology, signal processing techniques, and machine learning will propel this approach to revolutionize tracking and management of cardiovascular health in bettering overall well-being and timely medical intervention.

References

[1] Romano C, Schena E, Formica D, Massaroni C. Comparison between chest-worn accelerometer and gyroscope performance for heart rate and respiratory rate monitoring. Biosensors. (2022) 12:834. 10.3390/bios12100834 [DOI] [PMC free article] [PubMed] [Google Scholar] [2] Elgendi M, Wu W, Guan C, Menon C. Revolutionizing smartphone gyrocardiography for heart rate monitoring: overcoming clinical validation hurdles. Front Cardiovasc Med. (2023) 10:1–6. 10.3389/fcvm.2023.1237043 [DOI] [PMC free article] [PubMed] [Google Scholar] [3] Khatokar JA, Vinay N, Bale AS, Nayana M, Harini R, Reddy VS. et al. A study on improved methods in Micro- electromechanical systems technology. Mater Today Proc. (2021) 43:3784–90. 10.1016/j.matpr.2020.10.993 [DOI] [Google Scholar [4] Hansen, Patrik; Marianela García Lozano; Farzad Kamrani; and Joel Brynielsson. “Real-Time Estimation of Heart Rate in Situations Characterized by Dynamic Illumination using Remote Photoplethysmography.” Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, Canada, June 18–22 2023,pp. 6094–6103. DOI: 10.1109/CVPRW59228.2023.00649 — freely available via IEEE/CVF Open Acces [5] Gupta, Kapil, RuchikaSinhal, and Sagarkumar S. Badhiye. \"Remote photoplethysmography?based human vital sign prediction using cyclical algorithm.\" Journal of Biophotonics 17, no. 1 (2024): e202300286. [6] Krishnamoorthy, Anusha, G. MuralidharBairy, NandishSiddeshappa, Hilda Mayrose, NiranjanaSampathila, and KrishnarajChadaga. \"Channel intensity and edge-based estimation of heart rate via smartphone recordings.\" Computers 12, no. 2 (2023): 43. [7] Straczkiewicz, M., James, P., and Onnela, J. (2021). A systematic review of smartphone-based human activity recognition methods for health research. npj Digital Medcine 4, article number : 148. [8] Sarvat, Maham, SuhaibMasroor, Zain Anwar Ali, Sobia Shabbir, and Bilal Ahmad. \"Heart rate monitoring in COVID-19 patients: methods, performance, and evaluation. A review.\" International Journal of Biomedical Engineering and Technology 44, no. 2 (2024): 153-176. [9] Furniturewala, Mahera, Arjun Sivaraman, Anmol Anand, TarunKannuchamy, and R. Sasikala. \"Measurement of Body Vitals using Photoplethysmography (PPG) and Smartphone Sensors.\" In 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE), pp. 1-8. IEEE, 2024.

Copyright

Copyright © 2025 Mrs. Subhashree D C, Dr. Girish Kumar D, Mrs. Sharvani V, Miss. M M Harshitha, Mr. Sai Prakash Gubbala. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.