ACTIVITY MONITOR

• US 20130182107A1
• Filed: 12/18/2012
• Published: 07/18/2013
• Est. Priority Date: 01/16/2012
• Status: Active Grant

• Current Assignee: HiPass Design, LLC
• Original Assignee: HiPass Design, LLC
• Inventors: Anderson, Charles William
• Granted Patent: US 8,743,200 B2
• Time in Patent Office: Days
• US Class Current: 348/143
• CPC Class Codes: A61B 5/002 Monitoring the patient using a local or closed circuit, e.g. in a room or building A61B5/0017 takes precedence
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/7435 Displaying user selection data, e.g. icons in a graphical user interface
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: A61B 5/747 in case of emergency, i.e. alerting emergency services
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G08B 21/02 Alarms for ensuring the safety of persons
• CPC Class Codes: G08B 21/0476 Cameras to detect unsafe condition, e.g. video cameras
• CPC Class Codes: G08B 21/0492 Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

An activity monitor system monitors a location using a sensor system and detects and responds to “interesting events.” The system may detect events based on video processing of a substantially live sequence of images from a video camera. The system may use multi-region processing including modifying event detection based on motion in one or more regions, motion transitions, and/or motion entry and/or exit points. Events may be detected based on other sensors and the system may use a combination of sensor data to detect events. The system may store event data from the one or more sensors (e.g., video, audio, etc.) for interesting events and/or trigger alarm actions. Alarm actions may include sounding an audible alarm and enabling a substantially live video display on a monitoring device concurrently with the audible alarm. In embodiments, the activity monitor system is implemented using a smartphone and a wireless network camera.

Claims

1. A system for monitoring a patient, comprising:

a video camera that captures images of a patient location;

a video processing device coupled with the video camera, the video processing device configured to;

receive a substantially live sequence of the captured images;

compare each image of the sequence of images with one or more preceding images to determine motion levels associated with each of the sequence of images;

determine a motion alert level signal based at least in part on an integration function of the motion levels;

compare the motion alert level signal with a motion alarm threshold; and

generate a motion alarm signal based at least in part on determining that the motion alert level signal exceeds the motion alarm threshold.

2. The system for monitoring a patient of claim 1, further comprising:

a video display device coupled with the video camera; and

an alarm processor coupled with the motion alarm signal, the alarm processor configured to;

trigger an audible alarm based at least in part on the motion alarm signal; and

enable, concurrently with the audible alarm, a substantially live display of the sequence of images on the video display device.

3. The system for monitoring a patient of claim 1, further comprising:

a microphone that captures an audio signal from the patient location; and

an audio detector coupled with the microphone, the audio detector configured to;

receive the audio signal; and

determine an audio meter signal based at least in part on the received audio signal; and

an audio alert integrator configured to;

determine an audio level signal based at least in part on an integrating function of a plurality of values of the audio meter signal;

compare the audio level signal with an audio alarm threshold; and

generate an audio alarm signal responsive to detecting that the audio level signal exceeds the audio alarm threshold.

4. The system for monitoring a patient of claim 3, wherein determining the audio level signal comprises:

comparing the plurality of values of the audio meter signal to a high audio threshold;

increasing the audio level signal based on values of the audio meter signal that exceed the high audio threshold; and

decreasing the audio level signal based on values of the audio meter signal that do not exceed the high audio threshold.

5. The system for monitoring a patient of claim 3, wherein the audio alert integrator is further configured to:

compare the plurality of audio values of the audio meter signal to a low audio threshold to produce a low audio detection signal;

determine a low audio level signal based at least in part on the low audio detection signal;

compare the low audio level signal with a low audio alarm threshold; and

generate a low audio alarm signal responsive to detecting that the low audio level signal exceeds the low audio alarm threshold.

6. The system for monitoring a patient of claim 3, further comprising:

an alarm processor coupled with the motion alarm signal and the audio alarm signal, the alarm processor configured to;

trigger an alarm action based on one or more of the motion alarm signal and the audio alarm signal.

7. A method for monitoring a patient, comprising:

receiving a substantially live sequence of images of a patient location;

comparing each image of the sequence of images with one or more preceding images to determine motion levels associated with the image;

determining a motion alert level signal based at least in part on an integrating function of the motion levels;

comparing the motion alert level signal with a motion alarm threshold; and

generating a motion alarm signal based at least in part on detecting that the motion alert level signal exceeds the motion alarm threshold.

8. The method of claim 7, further comprising:

triggering an audible alarm at a monitoring device based on the motion alarm signal; and

enabling a substantially live display of the sequence of images on a display device of the monitoring device concurrently with the audible alarm.

9. The method of claim 7, further comprising:

initiating bidirectional audio communication between the patient and a monitoring device based on the motion alarm signal.

10. The method of claim 7, wherein the comparing of each image of the sequence of images with one or more preceding images comprises:

comparing a first region of each image of the sequence of images with the first region of the one or more preceding images to generate a first motion level associated with the first region for each of the sequence of images;

comparing the first motion level to a first threshold to generate a first motion detection signal associated with the first region;

comparing a second region of each image of the sequence of images with the second region of the one or more preceding images to generate a second motion level associated with the second region for each of the sequence of images; and

comparing the second motion level to the first threshold to produce a second motion detection signal associated with the second region.

11. The method of claim 10, wherein determining the motion alert level signal comprises:

applying a first weighting coefficient to the first motion detection signal;

applying a second weighting coefficient to the second motion detection signal; and

determining the motion alert level signal based at least in part on the weighted first motion detection signal and the weighted second motion detection signal.

12. The method of claim 10, further comprising:

determining, for a motion event of the patient based on the comparing of the first and second regions, a region transition from the first region to the second region; and

suppressing triggering of alarm actions based on the motion alarm signal for a predetermined time period based on the region transition for the motion event.

13. The method of claim 10, wherein the first region comprises a center region and the second region comprises an edge region.

14. The method of claim 10, further comprising:

receiving user input identifying a first portion of a display screen; and

determining one of the first region or the second region based at least in part on the received user input.

15. The method of claim 14, wherein receiving the user input comprises:

enabling a substantially live display of the sequence of images on the display device; and

receiving user input corresponding to a selection of the first portion of the display screen.

16. The method of claim 7, further comprising:

comparing the motion level signal with a motion event threshold; and

storing, responsive to the motion level signal exceeding the motion event threshold, a time period of the sequence of images.

17. The method of claim 16, wherein the time period is based at least in part on an elapsed time of the motion level signal exceeding the motion event threshold.

18. The method of claim 16, wherein storing the time period of the sequence of images comprises storing a predetermined time period of the sequence of images received prior to the motion level signal exceeding the motion event threshold.

19. The method of claim 16, further comprising:

associating a value of the motion level signal for each stored subset of the sequence of images; and

displaying a stored event list, wherein each stored event of the stored event list comprises a stored time period of the sequence of images and the associated motion level signal value.

20. The method of claim 7, wherein determining the motion level signal based on the motion detection signal comprises:

comparing the motion detection signal to a motion threshold;

increasing the motion level signal responsive to determining that the motion detection signal exceeds the motion threshold; and

decreasing the motion level signal responsive to determining that the motion detection signal is less than the motion threshold.

21. The method of claim 20, wherein an increase step value of the motion level signal is greater than a decrease step value of the motion level signal.

22. A computer program product for monitoring a patient, comprising:

a non-transitory computer-readable medium comprising;

code for causing a computer to receive a substantially live sequence of images of a patient location;

code for causing the computer to compare each image of the sequence of images with one or more preceding images to determine a motion level associated with the image;

code for causing the computer to determine a motion alert level signal based at least in part on an integrating function of the motion levels of the sequence of images;

code for causing the computer to compare the motion alert level signal with a motion alarm threshold; and

code for causing the computer to generate a motion alarm signal responsive to detecting that the motion level signal exceeds the motion alarm threshold.

23. The computer program product of claim 22, wherein the non-transitory computer-readable medium further comprises:

code for causing the computer to trigger, responsive to the motion alarm signal, an audible alarm at a monitoring device; and

code for causing the computer to enable, concurrently with the audible alarm, a substantially live display of the sequence of images on a display device of the monitoring device.

24. The computer program product of claim 22, wherein the code for causing the computer to compare of each image of the sequence of images with the one or more preceding images comprises:

code for causing the computer to compare a first region of each image of the sequence of images with the first region of the one or more preceding images to generate a first motion level associated with the first region for each of the sequence of images;

code for causing the computer to compare the first motion level to a first threshold to generate a first motion detection signal associated with the first region;

code for causing the computer to compare a second region of each image of the sequence of images with the second region of the one or more preceding images to generate a second motion level associated with the second region for each of the sequence of images; and

code for causing the computer to compare the second motion level to the first threshold to produce a second motion detection signal associated with the second region.

25. The computer program product of claim 24, wherein the non-transitory computer-readable medium further comprises:

code for causing the computer to apply a first weighting coefficient to the first motion detection signal;

code for causing the computer to apply a second weighting coefficient to the second motion detection signal; and

code for causing the computer to determine the motion alert level signal based at least in part on the weighted first motion detection signal and the weighted second motion detection signal.

26. The computer program product of claim 22, wherein the non-transitory computer-readable medium further comprises:

code for causing the computer to compare the motion level signal with a motion event threshold; and

code for causing the computer to store, responsive to the motion level signal exceeding the motion event threshold, a time period of the sequence of images.