Non-contact human respiratory rate measurement under dark environments by low-light video enhancement

A non-contact human respiratory rate measurement algorithm under dark environments is proposed in this study. The algorithm takes the low-light video as input, which includes four steps: time-domain preprocessing, space-domain preprocessing, image enhancement, and respiratory rate measurement. Firstly, the time-domain preprocessing and space-domain preprocessing run in turn to filter out the image noise and environment interference. Then, a Retinex-based image enhancement algorithm works for image enhancement. The human respiratory rate is measured at last. Experiments on a self-made dataset show that an average increase of 2.3 % in accuracy can be obtained by the proposed method. Specifically, high-precision measurement results can be achieved when the light intensity is not less than 200 lux and the detection distance is not far from 1.5 m.