人体皮肤彩色视频误差分析及一致性提高  

Error analysis and consistency improvement for human skin color videos

作　　者：闫勇刚[1,2] 邓小玲[1] 马祥[2] 欧阳健飞[2] 

机构地区：[1]河南理工大学机械与动力工程学院,河南焦作454003 [2]天津大学精密测试技术及仪器国家重点实验室,天津300072

出　　处：《红外与激光工程》2016年第B05期222-226,共5页Infrared and Laser Engineering

基　　金：国家自然科学基金(61178040);河南省高等学校重点科研项目(16A413006)

摘　　要：人体皮肤彩色视频测量是实现远程无创生理参数监测技术的基础和关键,而视频图像的一致性常常决定着生理参数的测量精度。从视频人体皮肤测量误差出发,提出了一种基于尺度不变特征变换和小波变换的视频稳定方法并应用此方法进行皮肤视频图像一致性研究。分析了影响视频一致性的误差因素,建立了视频图像误差数学模型。在此基础上,利用尺度不变特征变换算法提取皮肤视频图像的匹配特征点对;并采用仿射变换进行视频全局运动参数估计,完成了视频运动补偿。采用统计方法评估了视频稳定前后的一致性效果。结果表明,所提出的方法能有效地改进皮肤视频图像的稳定性和一致性,为进一步利用彩色视频准确提取人体生理参数以及研究穴位光学特性奠定基础。Skin color video measurements are very important in remote and non-invasive physiological monitoring, and its consistency always affects the measurement accuracy of physiological parameters like heart rate. An image-stabilization method was presented based on Scale Invariant Feature Transform（SIFT） and Wavelet Transform（WT）, and was applied to improve the consistency of skin videos image.The video image error was analyzed and an error mathematical model was built. Based on that, the matched pair-points of skin video images was extracted using SIFT algorithm, and on the global motion parameter estimation was carried for the skin videos image to achieve the motion compensation. Finally, a statistics computation was used to evaluate the consistency effects. The results show that the proposed method is valid and correct for improving the consistency of skin videos image, and it lays a foundation for further physiological parameters calculation and studying the optical characteristics of the acupoints.

关 键 词：皮肤彩色视频 非接触测量 一致性 尺度不变特征 误差分析 

分 类 号：TN391[电子电信—物理电子学]