CPulse: Heart Rate Estimation From RGB Videos Under Realistic ConditionsThe challenges obscuring contactless heart rate (HR) measurement using an RGB camera to emerge as a reliable alternative to the existing contact-based methods are the reliability and inconsistencies of performance in natural conditions resulting from illumination variations, varying skin tone, and motion artifacts. To address these problems, this article proposes a robust end-to-end automated framework [called camera pulse (CPulse)] for HR measurement using facial RGB videos. Face being the region of interest (ROI) is split into a number of small sub-ROIs of uniform size and a pool of quality sub-ROIs is created to deal with spatial uneven illumination variation and motion artifacts. The color signals from each sub-ROI undergo homomorphic filtering to mitigate the effect of temporal illumination variation. Two distinct color channels, namely, green (G) and chrominance (A) from RGB and LAB color spaces, respectively, are selected and processed using the empirical wavelet transform (EWT) followed by principal component analysis (PCA) to obtain a pulsating signal describing the volumetric changes in the blood for HR computation. The experimental analysis is carried out over several recordings from three publicly available datasets (PURE, UBFC, and COHFACE) and our own ASIPL dataset. The framework achieved the mean absolute error (MAE) of 0.98, 1.06, 1.99, and 1.81 beats per minute (bpm) for PURE, UBFC, COHFACE, and ASIPL datasets, respectively, depicting the HR measurement accuracy well above the threshold of clinical acceptance and outperforming the state-of-the-art methods used for comparisons. Notably, the experimental analysis reveals substantial tolerance of the technique against varying skin tones, which is a critical performance influencing factor. The performance results advocate the suitability of the framework in practical situations.

Research Works / Publications and Articles

CPulse: Heart Rate Estimation from RGB Videos under Realistic Conditions

2023 IEEE Transactions on Instrumentation and Measurement ( Volume: 72)

2023 | Journal Article

OPOIRES: A robust non-contact respiratory rate extraction based on optimal points-of-interest selection from an RGB camera

2023 Biomedical Signal Processing and Control, Volume 86, Part B, September 2023, 105193

2023 | Journal Article

Heart Rate Estimation from RGB Facial Videos Using Robust Face Demarcation and VMD

2021 27th National Conference on Communication (NCC), held at IIT Kanpur and IIT Roorkee

2021 | conference-paper

Tracking Nostril Movement in Facial Video for Respiratory Rate Estimation

2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT) held at IIT Kharagpur

2020-07 | conference-paper

RFI Suppression Methods for UWB Radar using Data Processing

International Journal of Electrical, Electronics and Data Communication (IJEEDC)

2018-08-13 | journal-article

Stepped LFM Processing Methods for High Range Resolution Phased Array Radar

International Journal of Electrical, Electronics and Data Communication (IJEEDC)

2018-08-13 | journal-article

RFI Suppression Methods for UWB Radar using Data Processing

ARSSS INTERNATIONAL CONFERENCE

2018-04-15 | conference-paper

Stepped LFM Processing Methods for High Range Resolution Phased Array Radar

ARSSS INTERNATIONAL CONFERENCE

2018-04-15 | conference-paper

Google Sites

Report abuse