Correlation of Sensory Inputs to Identify Unauthorized Persons

• US 20150287301A1
• Filed: 08/20/2014
• Published: 10/08/2015
• Est. Priority Date: 02/28/2014
• Status: Active Grant

• Current Assignee: Tyco Fire & Security GmbH (Johnson Controls International plc)
• Original Assignee: Tyco Fire & Security GmbH (Johnson Controls International plc)
• Inventors: Locke, Robert B.
• Granted Patent: US 11,747,430 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01S 5/0236 Assistance data, e.g. base station almanac
• CPC Class Codes: G01S 5/0284 Relative positioning
• CPC Class Codes: G01S 5/0294 Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06N 5/027 Frames
• CPC Class Codes: G07C 9/20 involving the use of a pass
• CPC Class Codes: G08B 13/00 Burglar, theft or intruder alarms
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/19697 Arrangements wherein non-video detectors generate an alarm themselves
• CPC Class Codes: G08B 13/22 Electrical actuation
• CPC Class Codes: G08B 13/2451 Specific applications combined with EAS
• CPC Class Codes: G08B 13/2491 Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
• CPC Class Codes: G08B 25/009 Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range
• CPC Class Codes: G08B 25/10 using wireless transmission systems G08B25/009 takes precedence
• CPC Class Codes: G08B 7/062 indicating emergency exits
• CPC Class Codes: G08B 7/066 guiding along a path, e.g. evacuation path lighting strip
• CPC Class Codes: H04L 45/74 Address processing for routing
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04W 4/02 : Services making use of location information
• CPC Class Codes: H04W 4/029 : Location-based management or tracking services
• CPC Class Codes: H04W 4/80 : Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
• CPC Class Codes: H04W 84/18 : Self-organising networks, e.g. ad-hoc networks or sensor networks
• CPC Class Codes: H04W 88/16 : Gateway arrangements

Abstract

A networked system for managing a physical intrusion detection/alarm includes an upper tier of server devices, comprising: processor devices and memory in communication with the processor devices, a middle tier of gateway devices that are in communication with upper tier servers, and a lower level tier of devices that comprise fully functional nodes with at least some of the functional nodes including an application layer that execute routines to provide node functions, and a device to manage the lower tier of devices, the device instantiating a program manager that executes a state machine to control the application layer in each of the at least some of the functional nodes.

Claims

1. A system for physical intrusion detection/alarm monitoring comprises:

one or more computing devices, comprising processor devices and memory in communication with the processor devices, configured to;

receive from reader devices sensory inputs from credentials or badges within a monitored premises;

receive video information from camera devices disposed throughout the monitored premises;

continually correlate the received sensory inputs with the received video to;

determine the number of unique credentials or badges within the monitored premises;

determine the number of individuals within the monitored premises from the captured video;

detect a presence of a possible non-credentialed individual by determining that the number of unique credentials or badges within the monitored premises is less than the number of individuals within the monitored premises.

2. The system of claim 1 further configured to:

apply one or more facial recognition algorithms to the captured video to recognize the detected individuals in the captured video;

track each recognized individual in the video until the recognized individual departs an area with a valid reading of a credential or badge, with any remaining individual or individuals that depart an area covered by the video without a like number of valid reading or readings of a credential or badge including the non-credentialed individual; and

produce an alert to send to a control center to alert authorities to the location of the non-credentialed individual, with the location being based on locations of the cameras and readers.

3. The system of claim 1 configured to:

apply video recognition to identify the number of people in a certain area and correlate that data with data from one or more remote badge readers to identify the appropriately number of badged individuals in a group of individuals within a monitored area.

4. The system of claim 3 further configured to:

determine a mismatch between the number of individuals in the area and a number of read badges or credentials.

5. The system of claim 4 further configured to:

continually track all individuals and their movements throughout the premises;

correlate those movements with different readings of valid credentials or badges to isolate one or more non-credentialed individuals.

6. The system of claim 1 wherein the one or more computing devices include an application layer that executes routines to provide node functions that are dynamically changed.

7. The system of claim 1 wherein the systems receives sensory inputs from credential readers.

8. The system of claim 1 wherein the system comprises nodes and with certain of the nodes configured to:

apply video recognition to frames of captured video to recognize features that correspond to individuals appearing in the captured frames; and

determine a number of people within the image.

9. The system of claim 8 wherein in one or more of the certain nodes, the one or more of the certain nodes are configured to:

change the video recognition algorithm that is applied to find features that correspond to a number of individuals.

10. The system of claim 1 configured to:

correlate paths taken by different individuals with different readings of valid credentials or badges from the same or different sets of cameras/readers.

11. A system for physical intrusion detection/alarm monitoring comprises:

a network of plural computing devices comprising processor devices and memory in communication with the processor devices, the network of plural computing devices executing an application layer that executes routines to provide node functions that are dynamically changed, with the network configured to;

receive from reader device nodes sensory inputs from credentials or badges within a monitored premises;

receive video information from camera device nodes disposed throughout the monitored premises;

continually correlate by one or more computing devices the received sensory inputs from the reader device nodes with the received video from the camera device nodes;

determine the number of unique credentials or badges within the monitored premises;

determine the number of individuals within the monitored premises from the captured video; and

detect a presence of a possible non-credentialed individual by determining that the number of unique credentials or badges within the monitored premises is less than the number of individuals within the monitored premises; and

the system further configured to;

dynamically change algorithms on the one or more computing device during tracking of the individuals.

12. The system of claim 11 configured to dynamically change algorithms that detect the presence of a number of individuals to algorithms that apply video recognition to recognize individuals.

13. The system of claim 11 wherein one or more of the nodes are configured to:

dynamically change video recognition algorithm that is applied to find features that correspond to a number of individuals.

14. The system of claim 11 the one or more of the nodes are configured to:

dynamically change recognition algorithms; and

correlate paths taken by different individuals with different readings of valid credentials or badges from the same or different sets of cameras/readers.