The invention discloses a construction method for a short-time remote photoplethysmography
signal detection model. The method comprises the following steps: acquiring a face
video image sequence, and preprocessing the face
video image sequence as an initial
data set;
processing the collected photoplethysmography signals to serve as a target set; and training a short-time remote photoplethysmography
signal detection model. An
encoder, a decoder, a
branch loss module and a residual constant block in
feature extraction constructed based on a 3D space-time
convolution filter and a
deconvolution filter, and a significant
feature extraction module based on a CBAM attention mechanism are designed. The design of the
encoder and the decoder is used for carrying out
scale transformation under time-space domain features and
time domain features, it is guaranteed that effective features highly related to short-time remote photoplethysmography
signal time sequence information are reserved in the
feature extraction process, and the performance of the model is improved. On the basis of a CBAM attention mechanism-based significant feature extraction module, the perceptual feature extraction capability is improved, and the problem of low robustness in the prior art is solved.