Assessment of ROI Selection for Facial Video-Based rPPG

Abstract

In general, facial image-based remote photoplethysmography (rPPG) methods use color-based and patch-based region-of-interest (ROI) selection methods to estimate the blood volume pulse (BVP) and beats per minute (BPM). Anatomically, the thickness of the skin is not uniform in all areas of the face, so the same diffuse reflection information cannot be obtained in each area. In recent years, various studies have presented experimental results for their ROIs but did not provide a valid rationale for the proposed regions. In this paper, to see the effect of skin thickness on the accuracy of the rPPG algorithm, we conducted an experiment on 39 anatomically divided facial regions. Experiments were performed with seven algorithms (CHROM, GREEN, ICA, PBV, POS, SSR, and LGI) using the UBFC-rPPG and LGI-PPGI datasets considering 29 selected regions and two adjusted regions out of 39 anatomically classified regions. We proposed a BVP similarity evaluation metric to find a region with high accuracy. We conducted additional experiments on the TOP-5 regions and BOT-5 regions and presented the validity of the proposed ROIs. The TOP-5 regions showed relatively high accuracy compared to the previous algorithm’s ROI, suggesting that the anatomical characteristics of the ROI should be considered when developing a facial image-based rPPG algorithm.

Effectiveness of Remote PPG Construction Methods: A Preliminary Analysis

“…In this study, we evaluated some of the most frequently used ROIs for rPPG in the current literature: the right cheek, left cheek, and forehead [ 12 , 13 ]. Moreover, two independent ROI assessments from Sungjun et al [ 14 ] and Dae-Yeol et al [ 7 ] determined that the forehead and cheeks are the most promising ROIs for rPPG.…”

“…This can be of limited help in determining whether the rPPG signal is of high quality because it only assesses the signal indirectly. The metrics most often used to compare the ground truth PPG with the estimated rPPG are the MAE or r of all sample points [ 7 ]. Furthermore, the PPG signal is occasionally evaluated with the rPPG signal via a frequency analysis or using the signal-to-noise ratio (SNR) [ 8 ].…”

Blood Pressure Measurement: From Cuff-Based to Contactless Monitoring

“…A suitable optimized algorithm should be found to transfer rPPG to PPG, because most of the features used for model establishment originate from PPG and are selected based on the physiological motivation. The authors of [ 237 , 238 , 239 ] noted that to extract stronger rPPG signals from the pixels of videos, the areas near the cheeks and forehead should be chosen. After the normalization of the pixel values, one of the useful denoising techniques is to extract all the frequency bands (including all their corresponding harmonic frequencies) related to the human body, as these can be relied upon to locate vital signs.…”

A Non-contact Heart Rate Measurement Approach Based on Modified EEMD Algorithm with Updated White-noise Iterating

“…Selecting appropriate ROI can effectively enhance the ruggedness of heart rate detection by IPPG [19][20]. The ROI ought to be capillary-rich, for instance, the frontal region of the face, the cheeks on the left and right, the lips and the chin, etc.…”