Visual Heart Rate Estimation from Facial Video Based on CNN

Due to the advantages of non-contact and low-cost, visual heart rate (HR) estimation is attracting more and more scholars to research. Recently, Some studies have shown that deep learning method could be developed for visual HR estimation. In this paper, we proposed an End-to-end deep neural network method for this task. The network is consisted of 2D convolutional (Conv2D) and LSTM (long short-term memory) operations. The Conv2D operation extract spatial feature and LSTM capture temporal information. The input of our model is facial ROI video and output is the predict HR. Experiment demonstrate that the proposed method could estimate HR value precisely.