A Motion and Illumination Resistant Non-Contact Method Using Undercomplete Independent Component Analysis and Levenberg-Marquardt Algorithm

Abstract

Heart Rate (HR) estimation is of utmost importance due to its applicability in diverse fields. Conventional methods for HR estimation require skin contact and are not suitable in certain scenarios such as sensitive skin or prolonged unobtrusive HR monitoring. Therefore remote photoplethysmography (rPPG) methods have become an active area of research. These methods utilize the facial videos acquired using a camera followed by extracting the Blood Volume Pulse (BVP) signal for heart rate calculation. The existing rPPG methods either utilized a single color channel or weighted color differences, which has certain limitations dealing with motion and illumination artifacts. This study considered BVP extraction as an undercomplete problem and proposed a method resistant to motion and illumination variation artifacts. This method is based on an undercomplete independent component analysis, aiming to estimate the unmixing matrix using a non-linear Cumulative Density Function (CDF) that has been optimized using the customized Levenberg-Marquardt algorithm. Therefore, the method is named U-LMA. The proposed method was tested under three scenarios: constrained, motion, and illumination variations scenarios. High Pearson correlation coefficient values and smaller lower-upper statistical limits of Bland-Altman plots justified the outstanding performance of the proposed U-LMA. Furthermore, its comparative analysis with the state-of-theart methods demonstrated its efficacy and reliability, which was proven by the lowest error and highest correlation values (0.01 significance level). Additionally, higher accuracy satisfying the clinically accepted error differences also justified its clinical relevance.

Intelligent Remote Photoplethysmography-Based Methods for Heart Rate Estimation from Face Videos: A Survey

“…Later, the authors of [84] came up with a meta-learning approach (Meta-rPPG) that focuses on using a synthetic gradient generator, and it requires several transductive inference steps and achieves a greater accuracy than the state-of-the-art methods. A metaphysical model that works well with supervised and unsupervised models was proposed in [85] and evaluated on two different datasets. However, the performance degraded when the subject was darker.…”

“…Even if it outperformed the results of the state-ofthe-art signal processing methods, it still needs manual feature extraction. The main challenges still need to be mitigated are the following: An end-to-end model proposed in [85] using undercomplete independent component analysis U-LMA was tested under three scenarios to estimate the nonlinear cumulative density function (CDF). Another skin segmentation method was introduced in [86] to process low-resolution inputs, make use of depth-wise convolutional layers, and localize skin pixels.…”

“…They claimed that the red and blue color components are the ones most affected by video compression due to the low bit rate. The authors of [85] developed a STVEN autoencoder to convert video from one bit rate to another. They performed an image enhancement procedure to overcome the compression effects.…”