Regular and non-invasive evaluations of cardiovascular function are important in cardiovascular catastrophe surveillance and chronic disease treatment therapies. Resting heart rate, one of the simplest cardiovascular parameters, has been identified as an independent risk factor (comparable with smoking, dyslipidemia or hypertension) for cardiovascular diseases. Standard gold techniques for heart rate measurement, such as the electrocardiogram (ECG), currently require patients to use adhesive gel patches or chest straps that can cause skin irritation and discomfort. Commercial pulse oximetry sensors that stick to fingertips or earlobes are also inconvenient for patients and the spring clips can cause pain if carried for a long period of time. The ability to monitor a patient's physiological signals through a remote, non-contact environment is a tempting prospect that would improve the delivery of primary care. For example, the idea of performing physiological measurements on the face was postulated by Pavlidis and his associates and later demonstrated through the analysis of thermal facial videos.
Although non-contact methods may not be able to provide details about cardiac electrical conduction ECG provides, these methods may now allow long-term follow-up of other physiological signals such as heart rate or respiratory rate through the continuous acquisition of a Discreet and comfortable way. Beyond that, such technology would also minimize the amount of wiring and disorder associated with neonatal ICU monitoring, long-term monitoring of epilepsy, monitoring of the patient with burns or trauma, sleep studies and other cases Where a continuous measure of heart rate is important. The use of photoplethysmography (PPG), an inexpensive and non-invasive means of detecting cardiovascular pulse waveform (also called blood volume pulse) has been recently investigated through variations in transmitted or reflected light, for non-contact physiological measurements . This electro-optic technique can provide valuable information about the cardiovascular system such as heart rate, arterial oxygen saturation, blood pressure, cardiac output and autonomic function.
Typically, PPG has always been implemented using dedicated light sources (eg, red and / or infrared wavelengths), but recent work has shown that pulse measurements can be acquired using digital video cameras with normal ambient light as a source of lighting. However, all these previous efforts lacked rigorous physiological and mathematical models capable of computation; They were based on manual segmentation and heuristic interpretation of raw images with minimal validation of performance characteristics. In addition, it is known that PPG is sensitive to motion-induced signal corruption and overcoming movement artifacts presents one of the most difficult problems. In most cases, noise falls within the same frequency band as the physiological signal of interest, thus rendering linear filtering ineffective at fixed cut-off frequencies. In order to develop a clinically useful technology, there is a need for ancillary functionality, such as reduction of motion artifacts through efficient and robust image analysis.