The heart rate is typically defined as the number of times the heart beats per minute,and it is a key factor in measuring an individual’s health level.Currently,there are many types of technologies used to detect heart rate,which can be classified as contact and non-contact depending on whether they are in contact with the human body.Contact heart rate detection obtains information by installing sensors,electrodes,and other equipment,but this detection method is constrained by the environment,equipment,and operator,and is therefore great ly limited.In contrast,non-contact technology does not require contact with the human body,does not cause discomfort to the body,and can perform heart rate detection more safely and quickly,thereby better meeting the needs of medical and health care.Since the outbreak of the COVID-19 pandemic,the non-contact heart rate detection method based on remote optical volume pulse techniques has been widely recognized in academic and industrial circles and has achieved significant development.However,this technology is easily affected by factors such as lighting changes,facial movements,and the selection of the region of interest,and its detection accuracy is still insufficient,and its reliability is also not ideal.This article conducts in-depth research on motion interference and insufficient lighting.Based on the research on traditional RGB color space heart rate detection,it analyzes and compares the detection performance of other color spaces under motion state,selects a suitable color spac e to suppress the influence of motion interference,and analyzes and verifies the strong correlation and consistency between the experimental group and the control group.To address the impact of insufficient lighting,a method of using low-light image enhancement is proposed to improve the visible light details of the image,and heart rate signals are obtained in weak light videos,achieving detection in low-light environments.Finally,combined with the actual requirements,this paper designed and implemented a non-contact real-time heart rate detection application based on Flask framework.The test results show that the relative error is less than 6.7%,which can help users more conveniently monitor their own heart rate and change trend. |