PREDICTIVE ANALYSIS USING VEHICLE LICENSE PLATE RECOGNITION

• US 20140254866A1
• Filed: 03/08/2013
• Published: 09/11/2014
• Est. Priority Date: 03/08/2013
• Status: Abandoned Application

• Current Assignee: Next Level Security Systems, Inc.
• Original Assignee: Next Level Security Systems, Inc.
• Inventors: Jankowski, Peter A., Yen, Chen-Lan, Anderson, Rand D.
• Application Number:
  US13/790,389
• Publication Number:
  US 20140254866A1
• Time in Patent Office: Days
• US Class Current: 382/103
• 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 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules

Abstract

A method and a system for predictive analysis using vehicle license plate recognition are described. The system has a gateway, a web server, and a client device. The gateway is coupled to security devices. The web server has a management application configured to communicate with the gateway. The client device communicates with the gateway identified by the web server. The gateway monitors data from security devices coupled to the gateway. A predictive behavioral model is generated using historical data from the monitoring data comprising identified characters in license plates of vehicles monitored by the security devices.

Claims

1. A gateway comprising:

a memory;

a processor coupled to the memory, the processor comprising a communication module, a remote device management module, and a license plate module,

the communication module configured to communicate with a web server, a client device introduced to the gateway by the web server, and at least one other gateway and to copy a configuration of the gateway to the at least one other gateway;

the remote device management module configured to aggregate monitoring data from a plurality of security devices coupled to the gateway and from at least one other security device respectively coupled to the at least one other gateway, the at least one other gateway correlated with the gateway by the web server, and to enable the client device to monitor the plurality of security devices coupled to the gateway and the at least one other security device coupled to the at least one other gateway; and

the license plate module configured to generate a predictive behavioral model using historical data from the monitoring data comprising identified characters in license plates of vehicles monitored by the at least one other security device.

2. The gateway of claim 1, wherein the license plate module comprises:

a historical data analysis module configured to access the historical data collected with a license plate recognition module configured to identify characters in the license plates in a picture from a non-infrared camera coupled to the gateway;

a prediction module configured to generate the prediction behavioral model using statistical computation on the historical data; and

an alert module configured to compare current data generated from a current picture from the non-infrared camera with the prediction behavioral model, and to generate an alert based on the comparison.

3. The gateway of claim 2, wherein the license plate module is configured to simultaneously processes the license plates and identify the characters in the license plates of a portion of the plurality vehicles using the non-infrared camera coupled to the gateway, and to generate indicators corresponding to the license plates on the picture generated by the non-infrared camera.

4. The gateway of claim 3, wherein the license plate module comprises:

a preset configuration module configured to generate a plurality of preset camera positions of the non-infrared camera to cover a location;

a camera position control module configured to move the camera according to the plurality of preset camera positions; and

a license plate analysis module configured to identify the license plates with each preset camera positions and to compare the characters of each license plate with each preset camera position with a database to correlate the license plates with the plurality of preset camera positions.

5. The gateway of claim 3, wherein the license plate module further comprises:

a vehicle identification module configured to identify a make and model of each vehicle in the picture from the non-infrared camera.

6. The gateway of claim 5, wherein the license plate module further comprises:

a license plate verification module configured to access data corresponding to a license plate of the vehicle based on the license plate recognition module; and

a license plate display module configured to generate a first set of indicators associated with the accessed data corresponding to the license plate and a second set of indicators associated with the make and model of the vehicle, the first and second set of indicators adjacent to a picture of the vehicle in a display.

7. The gateway of claim 2, wherein the license plate recognition module is configured to:

set a detection zone from a target scene in the picture;

read an OCR table from a database file, each character in the OCR table containing numbers indicating their feature sets;

read a new frame;

convert the new frame into gray scale;

break down to small bricks based on an image size of picture;

loop through all bricks in each scale level with local normalization for every brick, removal of isolated bricks, association of connected brick regions, and determination of the maximum and minimum brick region by probabilities;

sort extracted brick regions by density;

loop through all brick regions to determine possible license plates by normalizing brick regions, and filtering unlike plate region by checking minimum and maximum pixel size;

loop through license plates to determine overlap;

segment characters in the license plate;

determine a rotation of the license plate;

determine a fade out direction of the license plate;

calculate a point to pivot and the shear pivot;

re-sample the license plate to counteract till; and

merge existing license plates from historical results.

8. The gateway of claim 1, wherein the processor further comprises:

an application programming interface (API) module configured to interface the gateway with a client device;

an application module configured to monitor and control the plurality of security devices coupled to the gateway;

a device driver configured to enable interaction of the application module with the corresponding security device; and

the communication module further configured to receive additional APIs, respective application modules, and respective device drivers.

9. The gateway of claim 8, wherein the communication module comprises:

a user authentication module configured to authenticate a user at the client device based on a user profile of the user;

a user access policy module configured to limit or grant the user at the client device access to at least one of the plurality of security devices;

a web server authentication module configured to authenticate a communication between the gateway and the web server; and

a transport module configured to enable peer-to-peer communication between gateways, the client device, and the web server.

10. The gateway of claim 8, wherein the remote device management module comprises:

an analytics module configured to analyze audio, video, and data from the plurality of security devices and to generate events based on the analysis;

an event aggregation module configured to aggregate events generated from the analytics module;

an event-based control module configured to communicate a command to at least one of the security device of the corresponding gateway based on an event identified in the aggregated events based on an event configuration; and

a client-based control module configured to communicate a command to the at least one security device of the corresponding gateway based on a command communicated from the client device.

11. The gateway of claim 8, wherein the security device comprises a camera control device, an audio control device, a switch, a HVAC system, a video device, an audio device, a biometric sensor, an access control device, a temperature sensor, an RFID device, or a motion-controlled sensor.

12. The gateway of claim 8, wherein the web server comprises a web-based gateway management application configured to identify a gateway associated with a user at the client device, to authenticate with the user at the client device, to authenticate with the identified gateway, and to correlate the identified gateway with the other gateways.

13. The gateway of claim 12, wherein the web-based gateway management application comprises:

a gateway directory manager configured to identify a gateway associated with a user profile;

a user authentication module configured to authenticate with the user at the client device based on the user profile; and

a gateway authentication module configured to authenticate the identified gateway,

wherein the gateway directory manager comprises a service manager module configured to enable an add-on service to the user at the client device.

14. The gateway of claim 13, wherein the add-on service comprises remote storage, remote audio, two-way audio, dynamic backup, reporting based on the user profile, organization topology mapping, or gateway access configuration.

15. The gateway of claim 8, wherein the client device is configured to communicate with a first gateway identified by the web server, to receive monitoring data from a second security device coupled to a second gateway, to control the second security device coupled to the second gateway by communicating with the first gateway coupled to a first security device, the first gateway correlated with the second gateway by the web server.

16. A method comprising:

identifying at a gateway, a web server, a client device, and at least one other gateway;

aggregating monitoring data from a plurality of security devices coupled to the gateway and from at least one other security device respectively coupled to the at least one other gateway, the at least one other gateway correlated with the gateway by the web server;

enabling the client device to monitor and control the plurality of security devices coupled to the gateway and the at least one other security device coupled to the at least one other gateway; and

generating a predictive behavioral model using historical data from the monitoring data comprising identified characters in license plates of vehicles monitored by the at least one other security device.

17. The method of claim 16, further comprising:

detecting and identifying characters in the license plates depicted in a picture from a non-infrared camera coupled to the gateway;

accessing the historical data collected with the identifying;

generating the prediction behavioral model using statistical computation on the historical data;

comparing current data generated from a current picture from the non-infrared camera with the prediction behavioral model; and

generating an alert based on the comparing.

18. The method of claim 16, further comprising:

simultaneously identifying the characters in the license plates of a portion of the plurality vehicles using a non-infrared camera coupled to the gateway; and

generating indicators corresponding to the license plates on a picture generated by the non-infrared camera.

19. The method of claim 16, further comprising:

setting a detection zone from a target scene in the picture;

reading an OCR table from a database file, each character in the OCR table containing numbers indicating their feature sets;

reading a new frame;

converting the new frame into gray scale;

breaking down to small bricks based on an image size of picture;

looping through all bricks in each scale level with local normalization for every brick, removal of isolated bricks, association of connected brick regions, and determination of the maximum and minimum brick region by probabilities;

sorting extracted brick regions by density;

looping through all brick regions to determine possible license plates by normalizing brick regions, and filtering unlike plate region by checking minimum and maximum pixel size;

looping through license plates to determine overlap;

segmenting characters in the license plate;

determining a rotation of the license plate;

determining a fade out direction of the license plate;

calculating a point to pivot and the shear pivot;

re-sampling the license plate to counteract till; and

merging existing license plates from historical results.

20. A non-transitory computer-readable storage medium storing a set of instructions that, when executed by a processor, cause the processor to perform operations, comprising:

identifying at a gateway, a web server, a client device, and at least one other gateway;

aggregating monitoring data from a plurality of security devices coupled to the gateway and from at least one other security device respectively coupled to the at least one other gateway, the at least one other gateway correlated with the gateway by the web server;

enabling the client device to monitor and control the plurality of security devices coupled to the gateway and the at least one other security device coupled to the at least one other gateway; and

generating a predictive behavioral model using historical data from the monitoring data comprising identified characters in license plates of vehicles monitored by the at least one security device.