SYSTEM AND METHOD FOR HOME HEALTH CARE MONITORING
3 Assignments
0 Petitions
Accused Products
Abstract
A monitoring method and system are disclosed. In one embodiment, a method includes monitoring the health of a person in a home. The method includes capturing a video sequence from a first camera disposed within the home, including capturing two-dimensional image data for the video sequence; receiving depth data corresponding to the two-dimensional data, and associating the depth data with the video sequence as metadata; setting a plurality of events to monitor associated with the person, the events defined to include actions captured from the first camera, at least a first event including the person'"'"'s body being in a particular bodily position and performing video content analysis on the video sequence to determine whether the events have occurred. The video content analysis includes automatically detecting a potential human object from the video sequence based on the two-dimensional image data; using the depth data to determine a size and bodily position of the potential human object; and based on the size of the potential object, confirming that the potential human object is an actual human, thereby confirming the potential human object as a target. The method further includes determining that the first event has occurred based on the determined bodily position of the target.
-
Citations
37 Claims
-
1-20. -20. (canceled)
-
21. A method of monitoring the health of a person in a home, the method comprising:
-
capturing a video sequence from a first camera disposed within the home, including capturing two-dimensional image data for the video sequence; receiving depth data corresponding to the two-dimensional data, and associating the depth data with the video sequence as metadata; setting a plurality of events to monitor associated with the person, the events defined to include actions captured from the first camera, at least a first event including the person'"'"'s body being in a particular bodily position; performing video content analysis on the video sequence to determine whether the events have occurred, wherein the video content analysis includes; automatically detecting a potential human object from the video sequence based on the two-dimensional image data; using the depth data to determine a size and bodily position of the potential human object; and based on the size of the potential object, confirming that the potential human object is an actual human, thereby confirming the potential human object as a target; and determining that the first event has occurred based on the determined bodily position of the target. - View Dependent Claims (22, 23, 24, 25, 26)
-
-
27. A method of monitoring people, the method comprising:
-
capturing a video sequence from a first camera disposed in a particular location within a building, including capturing two-dimensional image data; receiving depth data for the video sequence, the depth data corresponding to the two-dimensional image data; associating the depth data with the video sequence as metadata; setting a plurality of events to monitor associated with the people, at least a first event including a person'"'"'s body being in a particular bodily position; performing video content analysis on the video sequence to determine whether the events have occurred, wherein the video content analysis includes; (a) automatically detecting a potential human object from the video sequence based on the two-dimensional image data; (b) using the depth data to determine a size and bodily position of the detected potential human object; and (c) based on the determined size of the detected potential human object, confirming that the detected potential human object is an actual human, thereby confirming the detected potential human object as a target; and determining that the first event has occurred based on the determined bodily position of the target. - View Dependent Claims (28, 29, 30, 31, 32)
-
-
33. A video surveillance system comprising:
-
a first video camera that captures two-dimensional image data and depth data; and a video content analysis system configured to; receive a video sequence from the first video camera, including receiving two-dimensional image data and depth data for the video sequence; associate the depth data with the video sequence as metadata; set a plurality of events to monitor associated with people; perform video content analysis on the of video sequence to determine whether the events have occurred, wherein the video content analysis includes; (a) automatically detecting a potential human object from the video sequence based on the two-dimensional image data; (b) using the depth data to determine a size and bodily position of the potential human object; and (c) based on the size of the potential object, confirming that the potential human object is an actual human, thereby confirming the potential human object as a target; and determining that the first event has occurred based on the determined bodily position of the target. - View Dependent Claims (34, 35, 36, 37)
-
Specification