Abstract: What is disclosed is a system and method for processing a video to extract a periodic signal which was captured by the video imaging device. One embodiment involves the following. First, a video of a subject in a scene is received. The video is acquired by a video imaging device. There is an underlying motion signal in the scene corresponding to cardiac or respiratory function. A time-series signal is generated for each pixel or for each group of pixels in a temporal direction across a plurality of image frames. Time-series signals of interest are selected. The selected time-series signals of interest are then processed to obtain a periodic signal corresponding to cardiac or respiratory function. The present method has a low computational complexity, is robust in the presence of noise, and finds its uses in applications requiring real-time motion quantification of a signal in a video.

Abstract: What is disclosed is a system and method for processing a video to extract a periodic signal which was captured by the video imaging device. One embodiment involves the following. First, a video of a subject in a scene is received. The video is acquired by a video imaging device. There is an underlying motion signal in the scene corresponding to cardiac or respiratory function. A time-series signal is generated for each pixel or for each group of pixels in a temporal direction across a plurality of image frames. Time-series signals of interest are selected. The selected time-series signals of interest are then processed to obtain a periodic signal corresponding to cardiac or respiratory function. The present method has a low computational complexity, is robust in the presence of noise, and finds its uses in applications requiring real-time motion quantification of a signal in a video.

Abstract: What is disclosed is a system and method for determining a respiration rate from a video of a subject breathing. One embodiment of the present method involves the following. A video is received of a subject breathing which comprises a first portion of N image frames, and a second portion of M image frames, N+M=T and N?10 seconds of video. For each image frame of the first portion, flow vectors Ft are determined for each (x,y) pixel location. A correlated flow field V is then calculated for the first portion of video. For each image frame of the second portion, flow vectors Ft(x,y) are determined for each (x,y) pixel location and a projection of Ft along V is calculated to obtain a velocity of thoracoabdominal motion in the direction of V. The velocity is integrated to obtain an integrated signal. Respiration rate is determined from the integrated signal.

Abstract: What is disclosed is a system and method for determining a respiration rate from a video of a subject breathing. One embodiment of the present method involves the following. A video is received of a subject breathing which comprises a first portion of N image frames, and a second portion of M image frames, N+M=T and N?10 seconds of video. For each image frame of the first portion, flow vectors Ft are determined for each (x,y) pixel location. A correlated flow field V is then calculated for the first portion of video. For each image frame of the second portion, flow vectors Ft(x,y) are determined for each (x,y) pixel location and a projection of Ft along V is calculated to obtain a velocity of thoracoabdominal motion in the direction of V. The velocity is integrated to obtain an integrated signal. Respiration rate is determined from the integrated signal.

Abstract: What is disclosed is a system and method for determining when a subject is speaking from a respiratory signal obtained from a video of that subject. A video of a subject is received and a respiratory signal is extracted from a time-series signal is obtained from processing pixels in image frames of the video. The respiratory signal comprises an inspiratory signal and an expiratory signal. Cycle-level feature are extracted from the respiratory signal and used to identify expiratory signals during which speech is likely to have occurred. The identified expiratory signal are divided into time intervals. Frame-level features are determined for each time interval and an amount of distortion in the expiratory signal for this time interval is quantified. The amount of distortion is compared to a threshold. In response to the comparison, a determination is made that speech occurred during this interval. The process repeats for all time intervals.