SYSTEMS AND METHODS FOR CONFIGURING BABY MONITOR CAMERAS TO PROVIDE UNIFORM DATA SETS FOR ANALYSIS AND TO PROVIDE AN ADVANTAGEOUS VIEW POINT OF BABIES

• US 20150288877A1
• Filed: 04/08/2015
• Published: 10/08/2015
• Est. Priority Date: 04/08/2014
• Status: Active Grant

• Current Assignee: Udisense Inc.
• Original Assignee: The Joan and Irwin Jacobs Technion-Cornell Institute
• Inventors: Glazer, Assaf
• Granted Patent: US 9,530,080 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2503/04 Babies, e.g. for SIDS detection
• CPC Class Codes: A61B 5/1114 Tracking parts of the body
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/6891 Furniture
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 23/50 Constructional details
• CPC Class Codes: H04N 23/51 Housings
• CPC Class Codes: H04N 23/56 provided with illuminating means
• CPC Class Codes: H04N 23/631 Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
• CPC Class Codes: H04N 23/661 Transmitting camera control signals through networks, e.g. control via the Internet
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

Systems and methods for monitoring babies with cameras using a centralized computation and storage center that allows using visual output signals for computer vision and machine learning analysis and high-level reasoning of baby movements. The system comprises a camera located at a predefined working point above a baby'"'"'s crib, and one or more communication networks between components of the system including a web-based network for in-depth computer vision and machine learning analysis of the visual output signals by an analysis server.

Claims

1. A system for monitoring a baby, the system comprising:

a camera configured at a predefined working point above a crib to obtain visual output signals from the predefined working point, the camera comprising;

a camera housing including a lens, infrared light emitting diodes (IR LED) lights, a light sensor, and power and data cabling; and

a mount including;

an upper arm connected to the camera housing, the upper arm including a first interior conduit configured to receive the power and data cabling of the camera housing;

a lower arm connected to the upper arm, the lower arm including a second interior conduit configured to receive the power and the data cabling of the camera housing from the upper arm; and

a crib attachment configured to attach the mount to the crib at the predefined working point above the crib; and

a network interface controller configured to;

transfer the visual output signals from the predefined working point to an analysis server, the analysis server configured to perform computer vision and machine learning analysis on the visual output signals from the predefined working point, compare the computer vision and machine learning analysis to comparative data, correlate the computer vision and machine learning analysis to events based on the comparison, and transmit messages based on the events correlating to the computer vision and machine learning analysis to client devices.

2. The system of claim 1 wherein the light sensor is configured on the camera to sense intensity of ambient light and infrared light from the IR LED lights.

3. The system of claim 2 wherein the IR LED light are configured by a processor based on the intensity of ambient light and infrared light from the IR LED lights.

4. The system of claim 1 wherein the camera utilizes infrared (IR) filters to filter IR light.

5. The system of claim 1 wherein the IR LED lights include a wavelength of approximately 850 nm to 940 nm such that a red glare is not visible to a baby lying under the camera.

6. The system of claim 1 wherein the upper arm includes at least one of speakers, night lights, temperature and humidity sensors.

7. The system of claim 1 wherein the camera housing further includes a lens mount operable for positioning with a rotational adjustment of 15 degrees of pan along a horizontal axis relative to the crib.

8. The system of claim 1 wherein the camera housing is configured to allow the camera to rotate 15 degrees of pan relative to the upper arm.

9. The system of claim 1 wherein the mount is attached to an outer side of the crib.

10. The system of claim 1 further including a sensitive white night light configured on the top, outer side of the upper arm, and directed away from an underside of the camera and upwards towards a ceiling.

11. The system of claim 1 wherein the mount comprises a universal mount with a bird'"'"'s-eye view.

12. The system of claim 1, wherein the camera is configured to transfer the visual output signals to client devices over a local area network.

13. The system of claim 1, wherein the camera is configured to transfer visual output signals to the analysis server over a web-based network connected to a centralized computation and storage center.

14. The system of claim 1, the camera and the predefined working point are substantially the same for monitoring different babies.

15. The system of claim 1, wherein the analysis server is further operable to:

generate notifications based on the computer vision and machine learning analysis; and

transmit the notifications to the client devices.

16. The system of claim 15, wherein the notifications include baby waking up, baby falling asleep, baby self-soothes.

17. The system of claim 1, wherein the analysis server is further operable to:

generate alerts based on the computer vision and machine learning analysis; and

transmit the alerts based on the computer vision and machine learning analysis.

18. The system of claim 17, wherein the alerts include baby rolled over, baby is crying, baby is climbing, baby spits up, foreign object in crib, aspiration event, flip event, seizures event, leg stuck event, and head covered event.

19. The system of claim 1, wherein the analysis server is further operable to perform computer vision and machine learning processing on the visual output signals as part of performing the computer vision and machine learning analysis on the visual output signals.

20. The system of claim 20, wherein the computer vision and machine learning processing includes at least one of background subtraction algorithms, baby region of interest detection, head detection processes, parental intervention detection, action rectangle identification, behavioral classification, hands detection, and baby presence detection methods.