Non-Contect Heart Rate Signal Detection Based On Video

In recent years,with the improvement of living standard,people pay more attention to health.The development of technology has also made the rapid development of medical detection.Heart rate detection has become a research hotspot.The traditional heart rate detection methods need to contact with skin directly.Long time testing make people feel uncomfortable.With the deepening of research and the improvement of social needs,the methods of video-based contactless heart rate signal detection have became the focus of current researches.The difficulty of video-based heart rate signal detection is susceptible to noises.Traditional video-based heart rate signal detection need purer environmental requirements.According to the constituent of noises,an algorithm for of video-based contactless heart rate signal detection method is proposed to removal motion artifacts and ambient light interference.In this paper,the heart rate signal is extracted from the videos containing frontal faces by using photoplethysmography(PPG).Motion artifact and physiological motion noise are preliminarily removed by separating face and background area from a video containing a frontal face.Select the part of the face region in the video frames as the region of interest(ROI)to further remove motion artifacts.Extract raw signals from ROI area and background area respectively and combine with Normalized Least Mean Square(NLMS)adaptive filter algorithm to remove ambient light.Noises elimination of heart rate signal is further done through time domain filtering.Noise elimination of heart rate signal is further done through time domain filtering.Extract heart rate by using cycle analysis.Through experiment,the method proposed in this paper can reflect the trend of heart rate before and after exercise.Under the conditions of environmental light change,the effectiveness of the measurement is 96%.This indicates that the method proposed in this paper has good stability under the condition of changing the ambient light.