Systems and methods of legibly capturing vehicle markings

• US 10,521,675 B2
• Filed: 09/19/2016
• Issued: 12/31/2019
• Est. Priority Date: 09/19/2016
• Status: Active Grant

• Current Assignee: Digital Ally Incorporated
• Original Assignee: Digital Ally Incorporated
• Inventors: Han, Peng, Dick, Jeremy A.
• Primary Examiner(s): Ustaris, Joseph G
• Assistant Examiner(s): Shahnami, Amir
• Application Number:
  US15/269,144
• Publication Number:
  US 20180082142A1
• Time in Patent Office: 1,198 Days
• Field of Search: 348148
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: H04N 23/60 Control of cameras or camera modules
• CPC Class Codes: H04N 5/77 between a recording apparatus and a television camera
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source
• CPC Class Codes: H04N 9/8205 involving the multiplexing of an additional signal and the colour video signal

Abstract

A system and method for legible capture of vehicle identification data includes video cameras and a computer. Recording attributes such as gain, gain shutter speed, and white balance are adjusted throughout ranges to maximize the likelihood of capturing at least one frame in which characters, such as those on the license plate, are legible. Successful capture of a legible frame may trigger storage of the data, while unsuccessful capture may trigger additional scans.

Claims

1. A method of scanning for a legible marking on a vehicle, the method including the steps of:

acquiring an indication to begin a scan with a video camera,

wherein the video camera has a first recording attribute and a second recording attribute;

sweeping the first recording attribute across a first scan range,

wherein the first scan range is defined by a first lower limit and a first upper limit;

wherein the first recording attribute is swept across the first scan range by uniform increments,

wherein a size of the uniform increments is determined based on a time of day or a sensed ambient light level;

sweeping the second recording attribute across a second scan range,

wherein the second scan range is defined by a second lower limit and a second upper limit;

determining, after said sweeping of said first recording attribute and second recording attribute, an acquisition of the legible marking on a vehicle based at least on a user'"'"'s response to a displayed image of at least a portion of the vehicle; and

storing, in a memory, at least a portion of said scan that includes said legible marking on a vehicle.

2. The method of claim 1,

wherein said first recording attribute remains at a first static value within said first scan range while said second recording attribute is swept across said second scan range, and

wherein said second recording attribute remains at a second static value within said second scan range while said first recording attribute is swept across said first scan range.

4. The method of claim 1, further including the step of sweeping a third recording attribute across a third scan range, wherein said third scan range is defined by a third upper limit and a third lower limit.

13. The method of claim 1, wherein said step of determining an acquisition of the legible marking on a vehicle based at least on a user'"'"'s manual input comprises displaying a selected image of the marking on a vehicle to a user for confirmation that the marking is legible.

16. The method of claim 1, further including the step of extracting and storing textual data from the legible marking.

17. The method of claim 1, further including the step of initiating a second scan upon a determination that the marking on a vehicle has not been legibly captured.

18. The method of claim 16, wherein the textual data from the legible marking is stored in metadata for an audio or video recording.

3. An image capture device including:

a video camera with a first recording attribute and a second recording attribute,

a storage device; and

a processor configured to perform the steps of;

acquiring an indication to begin a scan with the video camera,

sweeping the first recording attribute across a first scan range,

wherein the first scan range is defined by a first lower limit and a first upper limit,

sweeping the second recording attribute across second scan range,

wherein the second scan range is defined by a second lower limit and a second upper limit,

wherein said first upper limit, said first lower limit, said second upper limit, and said second lower limit are selected based on a time of day or a sensed ambient light level,

determining, after said sweeping of said first recording attribute and second recording attribute, a successful capture of an image of a legible marking on a vehicle based on a computer recognition of a valid marking, and

storing at least a portion of said scan within said storage device,

wherein the portion of said scan includes the image of the legible marking on the vehicle.

5. The image capture device of claim 3, wherein the indication to begin the scan is provided automatically based on a trigger parameter.

6. The image capture device of claim 5, wherein said trigger parameter providing the indication to begin the scan is selected from a group consisting of an indication that a vehicle is parked, a computer detection of a subject car, an activation of a vehicle siren, and an activation of signal lights.

7. The method of claim 3, wherein the first recording attribute is swept across the first scan range by uniform increments.

14. The image capture device of claim 3, wherein the step of determining if said marking on a vehicle has been legibly captured comprises extracting textual data from the marking on a vehicle and comparing the extracted textual data to a predetermined character string representing a license plate format.

15. The image capture device of claim 3, wherein the step of determining if said marking on a vehicle has been legibly captured comprises extracting textual data from the marking on a vehicle and comparing the extracted textual data to a license plate database to determine a match.

8. A method of scanning for a legible marking on a vehicle, the method including the steps of:

acquiring an indication to begin a scan with a video camera,

wherein the video camera has a first recording attribute and a second recording attribute;

sweeping the first recording attribute across a first scan range,

wherein the first scan range is defined by a first lower limit and a first upper limit;

sweeping the second recording attribute across a second scan range,

wherein the second scan range is defined by a second lower limit and a second upper limit;

wherein said first upper limit, said first lower limit, said second upper limit, and said second lower limit are selected based on a time of day or a sensed ambient light level; and

determining, after said sweeping of said first recording attribute and second recording attribute, if said marking on a vehicle has been legibly captured based on a computer recognition of a valid marking format.

9. The method of claim 8, wherein a portion of said scan that includes the marking on a vehicle is stored upon a determination that the marking on the vehicle has been legibly captured.

10. The method of claim 8, further including the step of initiating a second scan upon a determination that the marking on the vehicle has not been legibly captured.

11. The method of claim 10, wherein the second scan sweeps the first recording attribute across a first modified scan range, wherein the first modified scan range is not identical to the first scan range.

12. The method of claim 10,

wherein the second scan includes the step of sweeping a third recording attribute across a third scan range,

wherein said third scan range is defined by a third upper limit and a third lower limit.