Systems and methods for locating a retroreflective object in a digital image

Patent metadata

Field	Value
Publication number	US-11830256-B2
Application number	US-202217828725-A
Country	US
Kind code	B2
Filing date	May 31, 2022
Priority date	Feb 8, 2018
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

Systems and methods are disclosed for locating a retroreflective object in a digital image and/or identifying a feature of the retroreflective object in the digital image. In certain environmental conditions, e.g. on a sunny day, or when the retroreflective material is damaged or soiled, it may be more challenging to locate the retroreflective object in the digital image and/or to identify a feature of the object in the digital image. The systems and methods disclosed herein may be particularly suited for object location and/or feature identification in situations in which there is a strong source of ambient light (e.g. on a sunny day) and/or when the retroreflective material on the object is damaged or soiled.

First claim

The invention claimed is:

1. An automated license plate recognition system comprising:
a first image acquisition device to acquire at least a first image of a vehicle license plate;
a second image acquisition device to acquire at least a second image of the vehicle license plate with a different exposure level from the first image;
a memory to store at least the first image and the second image;
a processor to:
obtain a plurality of images of the vehicle license plate comprising at least the first image and the second image;
identify a vehicle registration identifier on the vehicle license plate in at least one of the plurality of images selected according to a confidence measure that the vehicle registration identifier is identifiable.

2. The system of claim 1 , wherein the plurality of images further comprise a third image of the vehicle license plate generated based on combining the first image and the second image.

3. The system of claim 1 , wherein the processor is to select the at least one of the plurality of images for identifying the vehicle registration identifier therein based on pixel intensities of the plurality of images.

4. The system of claim 1 , wherein the processor is to execute an auto-exposure algorithm to determine exposure levels for the first image acquisition device to acquire the first image and the second image acquisition device to acquire the second image.

5. The system of claim 4 , wherein the exposure levels are defined by at least one exposure time, gain, or iris.

6. The system of claim 1 , wherein the vehicle license plate has a retroreflective material.

7. The system of claim 1 , wherein the first image of the vehicle license plate is acquired with light emitted from an illuminator, and the second image of the vehicle license plate is acquired without or with less of the light emitted from the illuminator.

8. The system of claim 7 , further comprising the illuminator, and wherein the processor is to control the first image acquisition device to acquire the first image and control the illuminator to emit the light in order to synchronize light emission by the illuminator with acquisition of the first image.

9. The system of claim 1 , wherein the plurality of images further comprise a third image of the vehicle license plate generated by subtracting the second image from the first image.

10. The system of claim 9 , wherein the processor is to align the content of the first image and the second image by obtaining at least one displacement vector representing displacement of the content between the first image and the second image, and applying the at least one displacement vector to pixels of either the first image or the second image.

11. The system of claim 10 , wherein the at least one displacement vector represents static displacement of the content between the first image and the second image.

12. The system of claim 10 , wherein the at least one displacement vector represents static and dynamic displacement of the content between the first image and the second image, and wherein obtaining the at least one displacement vector comprises computing the at least one displacement vector.

13. The system of claim 10 , wherein the at least one displacement vector is a plurality of displacement vectors, each one of the plurality of displacement vectors corresponds to a respective section in the first and second image.

14. The system of claim 1 , wherein the processor is further to align content of the first image and the second image.

15. The system of claim 1 , wherein the processor is to align content of the first image and the second image based on static displacement of content between the first image and the second image.

16. The system of claim 15 , wherein the processor is to align content of the first image and the second image based on the static displacement and dynamic displacement of the content between the first image and the second image.

17. The system of claim 1 , wherein the first image acquisition device is a first infrared camera, the second image acquisition device is a second infrared camera, the first image is a first monochrome image, and the second image is a second monochrome image.

18. The system of claim 1 , wherein the confidence measure includes a confidence score.

19. A method of recognizing a vehicle license plate comprising:
acquiring at least a first image of the vehicle license plate;
acquiring at least a second image of the vehicle license plate with a different exposure level from the first image;
obtaining a plurality of images of the vehicle license plate comprising at least the first image and the second image; and
identifying a vehicle registration identifier on the vehicle license plate in at least one of the plurality of images selected according to a confidence measure that the vehicle registration identifier is identifiable.

20. A non-transitory processor-readable medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
acquiring at least a first image of the vehicle license plate;
acquiring at least a second image of the vehicle license plate with a different exposure level from the first image;
obtaining a plurality of images of the vehicle license plate comprising at least the first image and the second image; and
identifying a vehicle registration identifier on the vehicle license plate in at least one of the plurality of images selected according to a confidence measure that the vehicle registration identifier is identifiable.

Assignees

• Genetec Inc

Inventors

• Blais-Morin Louis-Antoine
• Cassani Pablo Augustin

Classifications

• G06V20/582 Primary

  of traffic signs · CPC title

• G06T7/73

  using feature-based methods · CPC title

• G06V10/143

  Sensing or illuminating at different wavelengths · CPC title

• G06V20/584

  of vehicle lights or traffic lights · CPC title

• G06T2207/30236

  Traffic on road, railway or crossing · CPC title