System and method for monitoring a fall state of a patient while minimizing false alarms
Various embodiments concern a system for monitoring a patient in a bed, the system comprising a camera, a user interface comprising a screen, and a computing system. The computing system can be configured to monitor, with the camera, for motion within each of a plurality of zones, the plurality of zones comprising a one or more inner zones extending adjacent along the bed, one or more outer zones extending adjacent along the one or more inner zones, and one or more end zones. Motion within the inner zones can trigger a fall alert while motion within the outer or end zones can suspend one or more functions to prevent the fall alert from being issued. The end zones can comprise a bottom zone and one or more top zones.
1. A system comprising at least one processor, the at least one processor being configured to:
obtain a video frame of a patient room from a camera, the patient room comprising a patient support surface;
define a first zone in the video frame, the first zone being disposed adjacent to the patient support surface in the video frame, the first zone comprising a left inner zone that extends adjacently along a left side boundary outside of the patient support surface by a predetermined number of pixels and a right inner zone that extends adjacently along a right side boundary outside of the patient support surface by a predetermined number of pixels;
define a second zone in the video frame relative to the first zone, the first zone being disposed between the second zone and the patient support surface in the video frame, the second zone comprising a left outer zone extending laterally outward from the left inner zone by a predetermined number of pixels and a right outer zone extending laterally outward from the right inner zone by a predetermined number of pixels;
detect a motion in the second zone based at least in part on the video frame; and
disarm alert monitoring for motion in the first zone based at least in part on the detected motion in the second zone.
2. The system of claim 1 , wherein the second zone is defined adjacent to the first zone.
3. The system of claim 1 , wherein the second zone is spaced apart from the first zone.
4. The system of claim 1 , wherein the first and second zones are defined on a plane that is aligned with the patient support surface.
5. The system of claim 1 , wherein the at least one processor is further configured to define a buffer zone between the patient support surface and the first zone.
6. The system of claim 1 , wherein disarming the alert monitoring for motion in the first zone based at least in part on the detected motion in the second zone comprises disarming the alert monitoring for a predetermined amount of time.
7. The system of claim 6 , wherein the at least one processor is further configured to:
obtain a second video frame from the camera while the alert monitoring is disarmed for the predetermined amount of time;
detect a second motion in the first zone based at least in part on the second video frame; and
extend the predetermined amount of time by an additional amount of time based at least in part on the detected second motion.
8. The system of claim 6 , wherein the at least one processor is configured to:
arm the alert monitoring after the predetermined amount of time has elapsed;
obtain a second video frame from the camera while the alert monitoring is armed;
detect a second motion in the first zone based at least in part on the second video frame; and
issue an alert based at least in part on the detected second motion.
9. The system of claim 1 , wherein the at least one processor is configured to define the first and second zones automatically based at least in part on a detection of the patient support surface in the video frame.
10. A method performed by at least one processor comprising hardware, the method comprising:
obtaining a video frame of a patient room from a camera, the patient room comprising a patient support surface;
defining a first zone in the video frame, the first zone being disposed adjacent to the patient support surface in the video frame, the first zone comprising a left inner zone that extends adjacently along a left side boundary outside of the patient support surface by a predetermined number of pixels and a right inner zone that extends adjacently along a right side boundary outside of the patient support surface by a predetermined number of pixels;
defining a second zone in the video frame relative to the first zone, the first zone being disposed between the second zone and the patient support surface in the video frame, the second zone comprising a left outer zone extending laterally outward from the left inner zone by a predetermined number of pixels and a right outer zone extending laterally outward from the right inner zone by a predetermined number of pixels;
detecting a motion in the second zone based at least in part on the video frame; and
disarming alert monitoring for motion in the first zone based at least in part on the detected motion in the second zone.
11. The method of claim 10 , wherein the second zone is defined adjacent to the first zone.
12. The method of claim 10 , wherein the second zone is spaced apart from the first zone.
13. The method of claim 10 , wherein disarming the alert monitoring for motion in the first zone based at least in part on the detected motion in the second zone comprises disarming the alert monitoring for a predetermined amount of time.
14. The method of claim 13 , wherein the method further comprises:
obtaining a second video frame from the camera while the alert monitoring is disarmed for the predetermined amount of time;
detecting a second motion in the first zone based at least in part on the second video frame; and
extending the predetermined amount of time by an additional amount of time based at least in part on the detected second motion.
15. The method of claim 13 , wherein the method further comprises:
arming the alert monitoring after the predetermined amount of time has elapsed;
obtaining a second video frame from the camera while the alert monitoring is armed;
detecting a second motion in the first zone based at least in part on the second video frame; and
issuing an alert based at least in part on the detected second motion.
16. The method of claim 10 , wherein the method further comprises defining the first and second zones automatically based at least in part on a detection of the patient support surface in the video frame.
17. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause the at least one processor to:
obtain a video frame of a patient room from a camera, the patient room comprising a patient support surface;
define a first zone in the video frame, the first zone being disposed adjacent to the patient support surface in the video frame, the first zone comprising a left inner zone that extends adjacently along a left side boundary outside of the patient support surface by a predetermined number of pixels and a right inner zone that extends adjacently along a right side boundary outside of the patient support surface by a predetermined number of pixels;
define a second zone in the video frame relative to the first zone, the first zone being disposed between the second zone and the patient support surface in the video frame, the second zone comprising a left outer zone extending laterally outward from the left inner zone by a predetermined number of pixels and a right outer zone extending laterally outward from the right inner zone by a predetermined number of pixels;
detect a motion in the second zone based at least in part on the video frame; and
disarm alert monitoring for motion in the first zone based at least in part on the detected motion in the second zone.
18. The non-transitory computer readable medium of claim 17 , wherein disarming the alert monitoring for motion in the first zone based at least in part on the detected motion in the second zone comprises disarming the alert monitoring for a predetermined amount of time.
19. The non-transitory computer readable medium of claim 18 , wherein the instructions further cause the at least one processor to:
obtain a second video frame from the camera while the alert monitoring is disarmed for the predetermined amount of time;
detect a second motion in the first zone based at least in part on the second video frame; and
extend the predetermined amount of time by an additional amount of time based at least in part on the detected second motion.
20. The non-transitory computer readable medium of claim 18 , wherein the instructions further cause the at least one processor to:
arm the alert monitoring after the predetermined amount of time has elapsed;
obtain a second video frame from the camera while the alert monitoring is armed;
detect a second motion in the first zone based at least in part on the second video frame; and
issue an alert based at least in part on the detected second motion.