Fall detection and reporting technology

1. A method comprising:

monitoring output from at least one sensor configured to sense activity associated with a fall;

based on the monitoring of output from the at least one sensor, determining to capture one or more images of an area associated with the at least one sensor;

based on the determination to capture one or more images of the area associated with the at least one sensor, capturing, with a camera, an image of the area associated with the at least one sensor;

detecting, in the captured image, a state of a person included in the captured image;

determining, based on the detected state of the person, a potential fall event in the area associated with the at least one sensor; and

based on the determination of the potential fall event, sending, by a communication device and to a device associated with the person involved in the potential fall event, a message that indicates the potential fall event and provides the person with an opportunity to cancel the potential fall event.

2. The method of claim 1 , further comprising:

determining that the person has not cancelled the potential fall event within a threshold period of time; and

based on determining that the person has not cancelled the potential fall event within the threshold period of time, sending a message to a monitoring server indicating the potential fall event.

3. The method of claim 1 , further comprising:

receiving, from the person, an indication to cancel the potential fall event; and

based on receiving the indication to cancel the potential fall event, determining an overall activity of the person between detecting the potential fall event and receiving the indication to cancel the potential fall event.

4. The method of claim 3 , further comprising:

determining that the overall activity of the person is above a threshold level of activity; and

based on determining that the overall activity of the person is above the threshold level of activity, signaling that the potential fall event was detection of a false fall.

5. The method of claim 3 , further comprising:

determining that the overall activity of the person is below a threshold level of activity; and

based on determining that the overall activity of the person is below the threshold level of activity, determining an orientation of the person.

6. The method of claim 5 , further comprising:

determining that the determined orientation of the person is upright; and

based on determining that the determined orientation of the person is upright, signaling that the potential fall event was detection of a minor fall.

7. The method of claim 5 , further comprising:

determining that the determined orientation of the person is not upright; and

based on determining that the determined orientation of the person is not upright, sending another message to the person that provides the person with another opportunity to cancel the potential fall event.

8. The method of claim 7 , further comprising:

determining that the person has not cancelled the potential fall event within a threshold period of time after sending another message to the person that provides the person with another opportunity to cancel the potential fall event; and

based on determining that the person has not cancelled the potential fall event within the threshold period of time after sending another message to the person that provides the person with another opportunity to cancel the potential fall event, sending a message to a monitoring server indicating the potential fall event.

9. The method of claim 7 , further comprising:

after sending another message to the person that provides the person with another opportunity to cancel the potential fall event, receiving, from the person, an indication to cancel the potential fall event; and

based on receiving the indication to cancel the potential fall event, signaling that the potential fall event was a cancelled fall event.

10. The method of claim 1 :

wherein detecting, in the captured image, the state of the person included in the captured image comprises:

performing image foreground segmentation on the captured image to create a segmented image,

performing template matching on the segmented image to identify a human shape in the segmented image, and

calculating a position and an orientation associated with the identified human shape in the segmented image, and

wherein determining the potential fall event in the area associated with the at least one sensor comprises determining a potential fall event for the person based on the calculated position and the calculated orientation.

11. A system comprising:

at least one processor; and

at least one memory coupled to the at least one processor having stored thereon instructions which, when executed by the at least one processor, causes the at least one processor to perform operations comprising:

monitoring output from at least one sensor configured to sense activity associated with a fall;

based on the monitoring of output from the at least one sensor, determining to capture one or more images of an area associated with the at least one sensor;

based on the determination to capture one or more images of the area associated with the at least one sensor, capturing, with a camera, an image of the area associated with the at least one sensor;

detecting, in the captured image, a state of a person included in the captured image;

determining, based on the detected state of the person, a potential fall event in the area associated with the at least one sensor; and

based on the determination of the potential fall event, sending, by a communication device and to a device associated with the person involved in the potential fall event, a message that indicates the potential fall event and provides the person with an opportunity to cancel the potential fall event.

12. The system of claim 11 , wherein the operations further comprise:

determining that the person has not cancelled the potential fall event within a threshold period of time; and

based on determining that the person has not cancelled the potential fall event within the threshold period of time, sending a message to a monitoring server indicating the potential fall event.

13. The system of claim 11 , wherein the operations further comprise:

receiving, from the person, an indication to cancel the potential fall event; and

based on receiving the indication to cancel the potential fall event, determining an overall activity of the person between detecting the potential fall event and receiving the indication to cancel the potential fall event.

14. The system of claim 13 , wherein the operations further comprise:

determining that the overall activity of the person is above a threshold level of activity; and

based on determining that the overall activity of the person is above the threshold level of activity, signaling that the potential fall event was detection of a false fall.

15. The system of claim 13 , wherein the operations further comprise:

determining that the overall activity of the person is below a threshold level of activity; and

based on determining that the overall activity of the person is below the threshold level of activity, determining an orientation of the person.

16. The system of claim 15 , wherein the operations further comprise:

determining that the determined orientation of the person is upright; and

based on determining that the determined orientation of the person is upright, signaling that the potential fall event was detection of a minor fall.

17. The system of claim 15 , wherein the operations further comprise:

determining that the determined orientation of the person is not upright; and

based on determining that the determined orientation of the person is not upright, sending another message to the person that provides the person with another opportunity to cancel the potential fall event.

18. The system of claim 17 , wherein the operations further comprise:

determining that the person has not cancelled the potential fall event within a threshold period of time after sending another message to the person that provides the person with another opportunity to cancel the potential fall event; and

based on determining that the person has not cancelled the potential fall event within the threshold period of time after sending another message to the person that provides the person with another opportunity to cancel the potential fall event, sending a message to a monitoring server indicating the potential fall event.

19. The system of claim 17 , wherein the operations further comprise:

after sending another message to the person that provides the person with another opportunity to cancel the potential fall event, receiving, from the person, an indication to cancel the potential fall event; and

based on receiving the indication to cancel the potential fall event, signaling that the potential fall event was a cancelled fall event.

20. The system of claim 11 :

wherein detecting, in the captured image, the state of the person included in the captured image comprises:

performing image foreground segmentation on the captured image to create a segmented image,

performing template matching on the segmented image to identify a human shape in the segmented image, and

calculating a position and an orientation associated with the identified human shape in the segmented image, and

wherein determining the potential fall event in the area associated with the at least one sensor comprises determining a potential fall event for the person based on the calculated position and the calculated orientation.