Processing a video for respiration rate estimation

摘要

What is disclosed is a system and method for estimating a respiration rate by analyzing distortions in reflections of structured illumination patterns captured in a video containing a view of a subject's thoracic region. In one embodiment, a video of a target region of a body of a subject of interest is received. Video image frames are processed to estimate 3D time-series data for the target region. As more fully disclosed herein, the subject's respiration rate is estimated from the 3D time-series data. Measurements can be acquired under a diverse set of lighting conditions. The teachings hereof provide a non-contact approach to patient respiratory function monitoring that is useful for intensive care units and for monitoring at homes, and which aid in the detection of sudden deterioration of physiological conditions due to changes in respiration rates. The teachings hereof provide an effective tool for non-contact respiratory function study and analysis.

主权项

1. A method for estimating respiration rate of a subject of interest being monitored for respiratory function in a non-contact, remote sensing environment, the method comprising:
receiving a video of a target region of a body of a subject of interest being monitored for respiratory function, wherein said video is captured using a video camera and an illuminator configured to project a pattern of structured illumination, said video camera being sensitive to electromagnetic radiation in a wavelength of said structured illumination, each image of said captured video comprising a sampling of radiation emitted by a reflection of said structured illumination off a surface of said target region, a spatial distortion being introduced by a reflection of said projected pattern off said surface; processing said video images to reconstruct 3D depth information of the scene and estimate 3D time-series data from said 3D depth information for said target region; and estimating said subject's respiration rate from said 3D time-series data comprising: for each image of said video:
comparing spatial attributes of said spatial distortion to known spatial attributes of undistorted projected patterns such that said distortion can be characterized in said image;calculating a depth map from said characterized distortion at different locations on said surface of said target region;estimating a 3D volume from said depth map; andconcatenating said resulting estimated 3D volumes to obtain said estimated 3D time-series data.