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: A video is received of a region of a subject where a signal corresponding to respiratory function can be registered by a video device. Pixels in the region in each of the image frames are processed to identify a respiratory pattern with peak/valley pairs. A peak/valley pair of interest is selected. An array of optical flow vectors is determined between a window of groups of pixel locations in a reference image frame corresponding to a peak of the pair/valley pair and a window in each of a number of image frames corresponding to the respiratory signal between the peak and ending at a valley point. Optical flow vectors have a direction and a magnitude. A ratio is determined between upwardly pointing optical flow vectors and downwardly pointing optical flow vectors. Based on the ratio, a determination is made whether the respiration phase for that peak/valley pair is inspiration or expiration.

Abstract: What is disclosed is a system and method for determining a subject's respiratory pattern from a video of that subject. One embodiment involves receiving a video comprising N?2 time-sequential image frames of a region of interest (ROI) of a subject where a signal corresponding to the subject's respiratory function can be registered by at least one imaging channel of a video imaging device. The ROI comprises P pixels. Time-series signals of duration N are generated from pixels isolated in the ROI. Features are extracted from the time-series signals and formed into P-number of M-dimensional vectors. The feature vectors are clustered into K clusters. The time-series signals corresponding to pixels represented by the feature vectors in each cluster are averaged along a temporal direction to obtain a representative signal for each cluster. One of the clusters is selected. A respiratory pattern is determined for the subject based on the representative signal.

Abstract: A video is received of a region of a subject where a signal corresponding to respiratory function can be registered by a video device. Pixels in the region in each of the image frames are processed to identify a respiratory pattern with peak/valley pairs. A peak/valley pair of interest is selected. An array of optical flow vectors is determined between a window of groups of pixel locations in a reference image frame corresponding to a peak of the pair/valley pair and a window in each of a number of image frames corresponding to the respiratory signal between the peak and ending at a valley point. Optical flow vectors have a direction and a magnitude. A ratio is determined between upwardly pointing optical flow vectors and downwardly pointing optical flow vectors. Based on the ratio, a determination is made whether the respiration phase for that peak/valley pair is inspiration or expiration.

Abstract: What is disclosed is a system and method for generating a respiration gating signal from a video of a subject for gating diagnostic imaging and therapeutic delivery applications which require respiration phase and/or respiration amplitude gating. One embodiment involves receiving a video of a subject and generating a plurality of time-series signals from the video image frames. A set of features are extracted from the time-series signals and multi-dimensional feature vectors are formed. The feature vectors are clustered. Time-series signals corresponding in each of the clusters are averaged in a temporal direction to obtain a representative signal for each cluster. One cluster is selected and a respiration gating signal is generated from that cluster's representative signal. Thereafter, the respiration gating signal is used to gate diagnostic imaging and therapeutic delivery applications which requires gating based on a threshold set with respect to either respiration phase or respiration amplitude.

Abstract: What is disclosed is a system and method for determining a subject's respiratory pattern from a video of that subject. One embodiment involves receiving a video comprising N?2 time-sequential image frames of a region of interest (ROI) of a subject where a signal corresponding to the subject's respiratory function can be registered by at least one imaging channel of a video imaging device. The ROI comprises P pixels. Time-series signals of duration N are generated from pixels isolated in the ROI. Features are extracted from the time-series signals and formed into P-number of M-dimensional vectors. The feature vectors are clustered into K clusters. The time-series signals corresponding to pixels represented by the feature vectors in each cluster are averaged along a temporal direction to obtain a representative signal for each cluster. One of the clusters is selected. A respiratory pattern is determined for the subject based on the representative signal.