Method, system and computer program product for identifying a location of an object within a video sequence

1. A method performed by a combination of electronic circuitry components for identifying a location of an object within a video sequence, the method comprising:

detecting motion of the object within a field of view of a passive infrared sensor, in response to signals from the passive infrared sensor;

in response to the detecting of the motion of the object within the field of view of the passive infrared sensor, enabling a three-dimensional sensor to operate in a two-dimensional operating mode;

detecting motion of the object within a field of view of the three-dimensional sensor, in response to signals from the three-dimensional sensor operating in the two-dimensional operating mode;

in response to the detecting of the motion of the object within the field of view of the three-dimensional sensor, enabling the three-dimensional sensor to operate in a three-dimensional operating mode;

determining whether the motion is a human type of movement, in response to signals from the three-dimensional sensor operating in the three-dimensional operating mode;

in response to determining that the motion is the human type of movement, identifying the location within the video sequence of the object that does the motion; and

in response to the identifying of the location of the object within the video sequence, partitioning the located object into multiple segments, and identifying human skeleton points of the multiple segments;

wherein determining whether the motion is the human type of movement includes: detecting features of the motion; computing three-dimensional motion vectors of the features between successive frames of the video sequence from the three-dimensional sensor; and comparing the features and three-dimensional motion vectors to characteristics that distinguish the human type of movement from a non-human type of movement.

2. The method of claim 1 , and comprising:

outputting an image to a display device for displaying the human skeleton points.

3. The method of claim 1 , and comprising:

in response to the detecting of the motion of the object within the field of view of the three-dimensional sensor, illuminating a space within the field of view of the three-dimensional sensor.

4. The method of claim 3 , wherein illuminating the space includes: illuminating the space with an infrared light emitting diode.

5. The method of claim 1 , and comprising:

in response to determining that the motion is the non-human type of movement, updating a database of information to improve accuracy for a determination of whether subsequent motion is the human type of movement.

6. A system for identifying a location of an object within a video sequence, the system comprising:

a combination of electronic circuitry components for: detecting motion of the object within a field of view of a passive infrared sensor, in response to signals from the passive infrared sensor; in response to the detecting of the motion of the object within the field of view of the passive infrared sensor, enabling a three-dimensional sensor to operate in a two-dimensional operating mode; detecting motion of the object within a field of view of the three-dimensional sensor, in response to signals from the three-dimensional sensor operating in the two-dimensional operating in response to the detecting of the motion of the object within the field of view of the three-dimensional sensor, enabling the three-dimensional sensor to operate in a three-dimensional operating mode; determining whether the motion is a human type of movement, in response to signals from the three-dimensional sensor operating in the three-dimensional operating mode; in response to determining that the motion is the human type of movement, identifying the location within the video sequence of the object that does the motion; and, in response to the identifying of the location of the object within the video sequence, partitioning the located object into multiple segments, and identifying human skeleton points of the multiple segments;

wherein determining whether the motion is the human type of movement includes: detecting features of the motion; computing three-dimensional motion vectors of the features between successive frames of the video sequence from the three-dimensional sensor; and comparing the features and three-dimensional motion vectors to characteristics that distinguish the human type of movement from a non-human type of movement.

7. The system of claim 6 , wherein the combination of electronic circuitry components is for outputting an image to a display device for displaying the human skeleton points.

8. The system of claim 6 , wherein the combination of electronic circuitry components is for: in response to the detecting of the motion of the object within the field of view of the three-dimensional sensor, illuminating a space within the field of view of the three-dimensional sensor.

9. The system of claim 8 , wherein illuminating the space includes: illuminating the space with an infrared light emitting diode.

10. The system of claim 6 , wherein the combination of electronic circuitry components is for: in response to determining that the motion is the non-human type of movement, updating a database of information to improve accuracy for a determination of whether subsequent motion is the human type of movement.

11. A non-transitory

computer-readable medium storing instructions that are processable by an instruction execution apparatus for causing the apparatus to perform a method comprising: detecting motion of an object within a field of view of a passive infrared sensor, in response to signals from the passive infrared sensor; in response to the detecting of the motion of the object within the field of view of the passive infrared sensor, enabling a three-dimensional sensor to operate in a two-dimensional operating mode; detecting motion of the object within a field of view of the three-dimensional sensor, in response to signals from the three-dimensional sensor operating in the two-dimensional operating mode; in response to the detecting of the motion of the object within the field of view of the three-dimensional sensor, enabling the three-dimensional sensor to operate in a three-dimensional operating mode; determining whether the motion is a human type of movement, in response to signals from the three-dimensional sensor operating in the three-dimensional operating mode; in response to determining that the motion is the human type of movement, identifying a location within a video sequence of the object that does the motion; and, in response to the identifying of the location of the object within the video sequence, partitioning the located object into multiple segments, and identifying human skeleton points of the multiple segments;

wherein determining whether the motion is the human type of movement includes: detecting features of the motion; computing three-dimensional motion vectors of the features between successive frames of the video sequence from the three-dimensional sensor; and comparing the features and three-dimensional motion vectors to characteristics that distinguish the human type of movement from a non-human type of movement.

12. The computer-readable medium of claim 11 , wherein the method comprises outputting an image to a display device for displaying the human skeleton points.

13. The computer-readable medium of claim 11 , wherein the method comprises: in response to the detecting of the motion of the object within the field of view of the three-dimensional sensor, illuminating a space within the field of view of the three-dimensional sensor.

14. The computer-readable medium of claim 13 , wherein illuminating the space includes: illuminating the space with an infrared light emitting diode.

15. The computer-readable medium of claim 11 , wherein the method comprises: in response to determining that the motion is the non-human type of movement, updating a database of information to improve accuracy for a determination of whether subsequent motion is the human type of movement.