Canine security system

• US 7,800,506 B2
• Filed: 12/27/2006
• Issued: 09/21/2010
• Est. Priority Date: 03/17/2005
• Status: Expired due to Fees

• Current Assignee: Eyal Zehavi
• Original Assignee: Eyal Zehavi
• Inventors: Zehavi, Eyal
• Primary Examiner(s): Nguyen; Tai T
• Application Number:
  US11/616,379
• Publication Number:
  US 20080018481A1
• Time in Patent Office: 1,364 Days
• Field of Search: 340/573.1, 340/573.2, 340/573.4, 340/870.16, 340/539.11, 119/51.02, 119/174, 600/303, 600/600
• US Class Current: 340/573.1
• CPC Class Codes: A01K 15/021 Electronic training devices specially adapted for dogs or cats
• CPC Class Codes: G08B 13/00 Burglar, theft or intruder alarms
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Abstract

A computerized security system which enhances the security provided by watchdogs on a given premises by analyzing the auditory and physiological indications given by the dogs to assess the level of security at any point in time. By attaching sensors to the dogs and placing microphones in their proximity the system continuously collects information about the dogs'"'"' auditory and physiological behavior, and according to predetermined parameters it assesses the watchdogs'"'"' physiological and emotional state. Having concluded that any of the dogs sense a threat or has been neutralized in any way the system may update the state of security on the users'"'"' security terminals. The system determines between three possible security states: no alert when no irregular activity is registered, medium alert if the dogs indicate a state of moderate alertness and high incase there are indications for a definite hostile presence.

Claims

1. A system for detecting a security condition, based on at least one dog behavior, said system comprising:

at least one audio sensor functionally associated with a dog for sampling dog sounds;

a controller adapted to analyze a pattern of an associated series of barks detected by said sensor and to determine an alarm condition based on one or more parameters extracted from the pattern analysis.

2. The system of claim 1 wherein the controller is further programmed for differentiating between different signal sources and identifying single barks in accordance with received measurements.

3. The system of claim 1 wherein the pattern analysis further includes determining an alert level by comparing identified characteristics of bark patterns to predefined values.

4. The system of claim 1 further comprising at least one biological sensor for measuring dog physiological status.

5. The system of claim 4 wherein the physiological status further is selected from the group consisting of heartbeat rate, breathing rate and depth, dog'"'"'s gross motor activity, muscle tonus, skin conductivity and blood pressure.

6. The system of claim 1 wherein the controller further analyses at least one of the sound signal patterns related to sniffing, panting, or breathing.

7. The system of claim 1 wherein characteristics of barks patterns include:

time intervals between single barks signals, mean and variant of time intervals, bark rate variability, barking rate and a distribution variance of the barks.

8. The system of claim 1 wherein the characteristics of barks patterns include signal frequency domain parameters.

9. The system of claim 1 wherein the frequency domain parameters includes a pitch measurement for identifying single sound patterns and differentiating between signal sources.

10. The system of claim 2 wherein identifying the characteristic of a single sound signal pattern is achieved by detecting a signal energy pattern in the time domain.

11. The system of claim 1 wherein at least one sensor is attached to the dog'"'"'s body.

12. The system of claim 1 wherein at least one sensor is located in the dog'"'"'s vicinity.

13. The system of claim 1 wherein at least one sensor is implanted in the dog'"'"'s body.

14. A method of detecting a security condition based on detected sound samples of at least one dog, said method comprising the step of:

determining an alarm condition based on one or more parameters extracted by analyzing a pattern of associated series of barks detected by an audio sensor functionally associated with a dog.

15. The method of claim 14 further comprising the steps of:

differentiating between different signal sources;

identifying single sound patterns; and

comparing extracted parameters to pre-defined values for determining alert levels.

16. The method of claim 14 further comprising the steps of integrating the information given by the analysis of sounds and physiological data to provide a representation of a security status as it is sensed by the dog.

17. The method of claim 14 wherein the physiological status is further selected from the group consisting of heartbeat rate, breathing rate and depth, dog'"'"'s gross motor activity, muscle tonus, skin conductivity and blood pressure.

18. The method of claim 14 wherein patterns analysis includes analyzing time domain parameters.

19. The method of claim 16 wherein the time domain parameters include time intervals between single barks sound pattern, barking rate, the distribution variance of the barks and bark rate variability.

20. A system for detecting a security condition comprising:

at least one audio sensor functionally associated with a dog for sampling dog sounds;

a controller adapted to analyze a pattern of associated series of barks detected by said sensor and to determine an alarm condition based on one or more parameters extracted from the pattern analysis, said controller further adapted to determine a condition based on analyzing one or more physiological parameters associated with the first dog or with a second dog.