In this article, we innovatively use Pearson correlation coefficient, etc. to analyze the components of the snowy image (the
snow-free image and the mask image), and then create an effective and accurate snow-free model using the relationship
between the components of the snowy image. For the snow-free model, we innovatively consider the similarity in the
generation of the snow-free image and the mask image; we also consider this relationship in our neural network framework.
We set the generator model in the generative adversarial network as the pseudo-siamese network with the same structure
but the different parameters. Each branch of the pseudo-siamese network adopts the autoencoder and the multi-scale
perception structure. The former can guarantee the acquisition of high-resolution images, and the latter can perceive context
information at different scales. We restore the mask image first and then restore the snow-free image because the mask
image has a simpler background than the snow-free image and the mask image is easier to recover than the snow-free
image. The results show that our (PS-GAN) pseudo-siamese generative adversarial network not only has better
performance on the data set, but also has good results in the real world which greatly improves the effect of using the
yolov5 to detect.
Significance: The measurement of human vital signs based on photoplethysmography imaging (PPGI) can be severely affected by the interference of various factors in the measurement process; therefore, a lot of complex signal processing techniques are used to remove the influence of the interference.
Aim: We comprehensively analyze several methods for color channel combination in the color spaces currently used in PPGI and determine the combination method that can improve the quality of the pulse signal, which results in a modified plane-orthogonal-to-skin based method (POS).
Approach: Based on the analysis of the previous studies, 13 methods for color channel combination in the different color spaces, which can be seen as having potential abilities in measuring vital signs, were compared by employing the average value of signal-to-noise ratio (SNR) and the box-plot in the public databases UBFC-RPPG and PURE. In addition, the pulse signal was extracted through the dual-color space transformation (sRGB → intensity normalized RGB → YCbCr) and fine-tuning on the CbCr plane.
Results: Among the 13 methods for color channel combination, the signal extracted by the Cb+Cr combination in the YCbCr color space includes the most pulse information. Furthermore, the average SNR of the modified POS for all the used databases is improved by 69.3% compared to POS.
Conclusions: The methods using prior knowledge are not only simple to calculate but can significantly increase the SNR, which will provide a great help in the practical use of vital sign measurements based on PPGI.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.