A face video heart rate estimation method based on color space learning
A color space and color space transformation technology, applied in neural learning methods, pulse rate/heart rate measurement, calculation, etc., to reduce errors, improve prediction accuracy, and improve accuracy.
Active Publication Date: 2021-11-19
ZHEJIANG LAB
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The purpose of the present invention is to address the deficiencies in the prior art, and propose a method for estimating the heart rate of human face video based on color space learning. This method adds a learnable color space transformation layer to the neural network, and can obtain a more suitable heart rate estimation method through training. The color space of , which solves the problem of color space selection in the heart rate estimation problem
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0028] The specific embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.
[0029] Such as figure 1 and figure 2 As shown, a kind of face video heart rate estimation method based on color space learning provided by the present invention, concrete steps are as follows:
[0030] (1) Shoot the face video through the camera, and cut the video to a fixed length to obtain the face video clip:
[0031] (2) Construct a neural network for face video heart rate estimation; the neural network includes a feature extraction module, a color space transformation layer and a heart rate estimation module; the feature extraction module uses a multi-layer skin area selection method to extract the human face video Feature map, the color space conversion layer is obtained by learning, and the extracted feature map is mapped to a suitable color space, and the heart rate estimation module is a deep neural network for estimati...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for estimating the heart rate of human face video based on color space learning. First, the human face video is obtained, and then a neural network for estimating the heart rate of the human face video is constructed; the neural network includes a feature extraction module and a color space transformation layer. And heart rate estimation module; The feature extraction module adopts the multi-layer skin area selection method to extract the feature map of the face video, and the color space conversion layer is obtained by learning, and the extracted feature map is mapped to a suitable color space, the described The heart rate estimation module is a deep neural network for estimating heart rate; finally, the acquired face video is input into the constructed and trained neural network for face video heart rate estimation to obtain an estimated heart rate. For the first time, the present invention uses the method of color space transformation to estimate the heart rate of human face video, which reduces the error and improves the prediction accuracy compared with the traditional color space.
Description
technical field [0001] The invention relates to the field of heart rate estimation, in particular to a method for estimating the heart rate of human face video based on color space learning. Background technique [0002] Heart rate estimation using face videos is an important application of non-contact photoplethysmography (rPPG) technology. It estimates the blood pulse signal of the face by modeling and analyzing the subtle changes in the face color in the video, thereby predicting the heart rate information of the subject. [0003] The traditional rPPG method uses mathematical modeling regression to establish a mapping relationship between face video and heart rate. The CHROM method uses a color processing method based on chroma to extract the pulse signal, and obtains higher accuracy than the method based on the RGB color space. The POS method uses the Plane-Orthogonal-to-Skin method to project the facial video frame and extract the pulse signal. The 2SR method uses th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08A61B5/024
CPCG06N3/08A61B5/02416G06V40/168G06V40/172G06V10/44G06N3/045G06F18/241
Inventor 邱兆林林兰芬陈延伟童若锋李劲松
Owner ZHEJIANG LAB