Go to CVPR 2025 Workshop DemoDiv homepageSkinMap: A Novel Weighted Full-Body Skin Segmentation for Robust Remote Photoplethysmography
Keywords: Remote Photoplethysmography, Skin Segmentation, Diversity, Heart Rate Monitoring, rPPG Dataset
TL;DR: This paper presents a novel skin segmentation method and a new dataset to enhance rPPG signal extraction, focusing on accuracy and inclusivity across diverse skin tones, lighting, and real-world conditions.
Abstract: Remote photoplethysmography (rPPG) is an innovative method for monitoring heart rate and vital signs by recording a person with a simple camera, as long as any part of their skin is visible. This low-cost, contactless approach helps in remote patient monitoring, emotion analysis, smart vehicle utilization, and more. Over the years, various techniques have been proposed to improve the accuracy of this technology, especially given its sensitivity to lighting and movement. In the unsupervised pipeline, it is needed first to select skin regions from the video to extract the rPPG signal from the skin color change. We introduce a novel skin segmentation technique that is robust for real-world scenarios and prioritizes skin regions to enhance the quality of the extracted signal. It can detect areas of skin all over the body, making it more resistant to movement, while removing areas such as the mouth, eyes, and hair that may cause interference. Our model is evaluated on two public datasets, and we also present a new dataset called SYNC-rPPG to better represent real-world conditions. The results indicate that our model demonstrates a prior ability to capture heartbeats in challenging conditions, such as talking and head rotation, and maintain the mean absolute error (MAE) between predicted and actual heart rates, while other region of interest (ROI) selection methods fail to do so. In addition, it delivers comparable results in static scenarios and demonstrates high accuracy in detecting a diverse range of skin tones, making it a promising technique for real-world applications.
Submission Number: 18
Loading