System and method for home health care monitoring

A method of monitoring the health of a person in home, the method comprising:ncapturing a plurality of video sequences from a plurality of respective cameras disposed in different locations within the patient's home, including capturing two-dimensional image data and depth data for each video sequence;defining a plurality of events to monitor associated with the patient, the events including, during a predetermined time period, at least (1) the patient's body being in a particular position for at least a predetermined amount of time;performing depth-enhanced video content analysis on the plurality of video sequences to determine whether the event (1) has occurred, wherein the video content analysis includes:for each of at least two cameras:automatically detecting a human object based on the two-dimensional image data;using the depth data associated with the detected human object to confirm whether the human object is in the particular position, without using depth data associated with other parts of the two-dimensional image in the confirmation; andbased on the confirmation, tracking an amount of time that the human object is in the particular position; anddetermining that the event (1) has occurred based on the collective tracked amount of time.

A home health monitoring system, comprising:na plurality of cameras in different rooms in a home, the different cameras configured to capture two-dimensional image data and depth data from a plurality of respective video images;a central computer system configured to perform video content analysis based on the two-dimensional image data and the depth data; andone or more communication media configured to transmit data from the plurality of cameras to the central computer system,wherein the video content analysis includes:setting a plurality of events to monitor associated with an inhabitant in the home, the events including, during a predetermined time period, (1) the patient's body being in a particular position for at least a predetermined period of time;performing video content analysis on the plurality of video sequences to determine whether the event (1) has occurred, wherein the video content analysis includes:for each of at least two cameras:automatically detecting a human object based on the two-dimensional image data;using the depth data associated with the detected human object to confirm whether the human object is in the particular position, without using depth data associated with other parts of the two dimensional image in the confirmation;based on the confirmation, tracking an amount of time that the human object is in the particular position; anddetermining that the event (1) has occurred based on the tracked amount of time.