Detector for chemical, biological and/or radiological attacks

• US 20120106782A1
• Filed: 03/01/2011
• Published: 05/03/2012
• Est. Priority Date: 01/29/2007
• Status: Active Grant

• Current Assignee: IntelliVision Technologies Corp. (Melrose Industries Plc)
• Original Assignee: IntelliVision Technologies Corp. (Melrose Industries Plc)
• Inventors: Nathan, Anoo, Gope, Chandan, Kay, Albert
• Granted Patent: US 9,036,902 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/426 Graphical representations
• CPC Class Codes: G06V 10/478 Contour-based spectral representations or scale-space representations, e.g. by Fourier analysis, wavelet analysis or curvature scale-space [CSS]
• 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: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 17/12 Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
• CPC Class Codes: G08B 21/14 Toxic gas alarms G08B21/16 takes precedence

Abstract

This specification generally relates to methods and algorithms for detection of chemical, biological, and/or radiological attacks. The methods use one or more sensors that can have visual, audio, and/or thermal sensing abilities and can use algorithms to determine by behavior patterns of people whether there has been a chemical, biological and/or radiological attack.

Claims

1. A system comprising:

a sensor system including at least one sensor that measures behavioral data associated with one or more persons;

an alarm system including at least one alarm;

a processor system including at least one processor;

at least one memory storing one or more machine instructions, which when implemented cause the processor system to perform a method including at least

the processor analyzing the data;

the processor determining whether the data indicates an attack based on the analyzing;

if the determining result in a determination of an attack, sending a signal to the alarm system that causes an alert to be sent.

2. The system of claim 1, the sensor system including at least a plurality of sensors and the system combines information from each of the sensors to determine whether an attack is in progress.

3. The system of claim 1, wherein the sensor system includes at least one thermal sensor.

4. The system of claim 1, wherein the sensor system comprises a plurality of cameras and audio sensors.

5. The system of claim 1, wherein the sensor system comprises at least one camera and at least one thermal sensor.

6. The system of claim 1, the method further including at least

capturing data;

learning a background;

separating a foreground from the background;

establishing a bounding box based on the foreground;

determining an aspect ratio of the bounding box;

determining whether the aspect ratio changed;

determining whether an abnormal behavior is occurring based on the change in the aspect ratio; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring.

7. The system of claim 1, the method further including at least

capturing data;

learning a background;

separating a foreground from the background;

analyzing a bounding contour of a person;

computing shape descriptors of the bounding contour;

matching the shape descriptors with training descriptors;

determining whether an abnormal behavior is occurring based on the matching; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring, wherein said abnormal behavior is associated with an attack.

8. The system of claim 1, the method further including:

capturing data;

selecting feature points in a scene;

identifying objects by a clustering of feature points;

determining movement of the feature points;

determining whether a behavior is abnormal based on the movement; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring.

9. The system of claim 1, the method further including:

capturing data;

selecting feature points in a scene;

identifying objects by a clustering of feature points;

determining movement of the feature points;

determining whether a behavior is abnormal based machine learning algorithm of behavior data; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring.

10. The system of claim 1, the method further including

capturing data in the form of pixel values;

searching for patterns within the pixel captured;

applying a learning algorithm to the patterns found;

determining whether there is an abnormal behavior based on the applying of the learning algorithm to the patterns found; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring.

11. The system of claim 1, the method further including

capturing thermal data;

identifying regions of elevated heat;

analyzing the regions of elevated heat to determine locations of people;

identifying a changes the regions of elevated heat that correspond to people;

determining whether an abnormal behavior is present based on a learning algorithm of abnormal behavior related to body heat; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring.

12. The system of claim 1, the method further comprising capturing data;

identifying background noise;

identifying a signal of interest, identifying known categories of audio duress;

determining whether duress is occurring based on a learning algorithm of duress; and

determining whether to send an alert to at least one interested party, based on the determining of whether the abnormal behavior is occurring, wherein said abnormal behavior is associated with a chemical, biological and/or radiological attack

13. The system of claim 1, wherein the processor is located within a sensor.

14. The system of claim 13, wherein the sensor is a camera and the processor implements the analyzing.

15. The system of claim 1, wherein the one or more sensors include a camera communicatively connected to an external computing device that implements the analyzing.

16. The system of claim 1, wherein the attack is a chemical, biological and/or radiological attack.

17. The system of claim 1, wherein the analyzing includes at least analyzing the behavior of people to determine whether elements of the behavior correspond to duress or distress conditions.

18. A system for the detection of a chemical, biological and/or radiological attack, comprising:

an input system for inputting attack detection parameters;

at least one sensor for measuring behavior data;

at least one transmitter for transmitting the behavior data to a remote unit;

a housing for enclosing the at least one sensor and the transmitter;

at least one remote unit, which is a unit remote from the sensor, including at least a receiver for receiving behavior data from the sensor;

a memory for storing attack characteristics;

an algorithm for analyzing the behavioral data measured, comparing the attack characteristics to the behavior data measured, and determining whether to send an alert based on the comparing;

a processor that implements the algorithm and causes the transmitter to transmit the alert based on the algorithm; and

a transmitter that transmits the alert in response to signals received from the processor resulting from the processor determining that an attack occurred based on the processor implementing the algorithm, attack settings and status information for display on the housing.

19. The system of claim 18, further comprising an external systems and server unit, a display being attached to the external systems unit for displaying attack settings and status information, and the input system being attached to the external systems unit in a manner in which the attack settings may be entered by a person.

20. A method for detection of a chemical, biological and/or radiological attack, comprising:

collecting data related to behavior associated with one or more persons;

analyzing the data collected to determine one or more values characterizing the behavior;

comparing the one or more values characterizing the behavior to one or more values characterizing behavior of one or more persons during a chemical, biological or radiological attack;

determining whether an attack has occurred based on the comparing; and

activating an alert that an attack has occurred, if as a result of the determining it is determined that an attack has occurred, wherein the data is collected via at least one sensor.

21. The method of claim 20, wherein the collecting data is by using a sensor chosen from a camera, a thermal camera, an audio sensor, an infrared sensor, a chemical sensor, a biological sensor, a radiological sensor, and mixtures thereof.

22. The method of claim 20, wherein the activating of the alert includes at least sending a message indicating that an attack has occurred to a device associated with a concerned party.

23. The method of claim 20, wherein the behavior during a chemical, biological, or radiological attack is chosen from falling, motionless, struggling, kneeling, squirming, coughing, staggering, walking sideways, disorientation, screaming, crying, an increase in body temperature, and mixtures thereof.

24. The method of claim 20, further comprising providing reports based on data collected from the at least one sensor.