SYSTEMS AND METHODS FOR DEWARPING IMAGES

• US 20180144439A1
• Filed: 01/22/2018
• Published: 05/24/2018
• Est. Priority Date: 08/19/2016
• Status: Active Grant

• Current Assignee: Intelligent Security Systems (ISS)
• Original Assignee: Intelligent Security Systems (ISS)
• Inventors: Stepanenko, Oleg Vladimirovich
• Granted Patent: US 10,565,680 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 15/20 Perspective computation
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 3/12 Panospheric to cylindrical image transformations
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 5/80 Geometric correction
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture

Abstract

A computer-implemented method comprises: extracting a setting from a description file of a virtual pan-tilt-zoom (PTZ) camera used to capture an original image through a wide-angle lens; determining a first set of coordinates of a pixel of the original image for each cell of a sparse conversion map represented as a first look-up table, wherein the sparse conversion map corresponds to a sparse grid of pixels of an output image; determining, via interpolating the first set of coordinates, a second set of coordinates of a pixel of the original image for each cell of a full conversion map, wherein the second set of coordinates is represented as a second look-up table, wherein the full conversion map corresponds to a full grid of pixels of the output image; instructing a display to present the output image, wherein the original image is less rectilinear than the output image.

Claims

1. A method comprising:

receiving, by a processor, a first imagery from a first camera and a second imagery from a second camera, wherein the first imagery is warped, wherein the first imagery depicts a bottom of a vehicle, wherein the second imagery depicts an identifier of the vehicle;

dewarping, by the processor, the first imagery;

stitching, by the processor, the first imagery such that a first image is formed;

extracting, by the processor, a set of symbols from the second imagery, wherein the set of symbols corresponds to the identifier;

storing, by the processor, the first image and the set of symbols in a database such that the first image is associated with the set of symbols;

retrieving, by the processor, the first image from the database;

comparing, by the processor, a second image against the first image, wherein the second image depicts the bottom;

determining, by the processor, whether the second image satisfies a comparison threshold with respect to the first image; and

requesting, by the processor, a barrier to be opened responsive to the comparison threshold being satisfied such that the vehicle can pass the barrier.

2. The method of claim 1, further comprising:

recording, by the processor, a date value and a time value associated with a capture of the second image via the first camera; and

storing, by the processor, the second image, the date value, and the time value into the database such that the second image, the date value, and the time value are associated with the set of symbols.

3. The method of claim 1, wherein the database includes an in-memory database.

4. The method of claim 1, wherein the dewarping is less than full.

5. The method of claim 1, wherein the bottom is illuminated via a light source such that the first camera captures the first imagery.

6. The method of claim 5, wherein the first camera and the light source are hosted via a housing.

7. The method of claim 6, wherein the first camera includes a dome that includes a transparent portion through which the first imagery is captured, wherein the housing hosts the dome.

8. The method of claim 1, further comprising:

requesting, by the processor, the barrier to remain closed responsive to the comparison threshold not being satisfied.

9. The method of claim 1, wherein the first imagery includes a third image, wherein the dewarping includes:

determining, by the processor, based on the setting, a first set of coordinates of a pixel of the third image, wherein the determining of the first set of coordinates is for each cell of a sparse conversion map represented as a first look-up table, wherein the sparse conversion map corresponds to a sparse grid of pixels of a fourth image; and

determining, by the processor, via interpolating the first set of coordinates, a second set of coordinates of a pixel of the third image such that the third image would be less rectilinear than the fourth image when displayed, wherein the determining of the second set of coordinates is for each cell of a full conversion map, wherein the second set of coordinates is represented as a second look-up table, wherein the full conversion map corresponds to a full grid of pixels of the fourth image.

10. The method of claim 9, wherein the first look-up table and the second look-up table are comprised in a single data structure.

11. The method of claim 9, wherein the first look-up table and the second look-up table are comprised in a plurality of distinct data structures.

12. A system comprising:

a server configured to;

receive a first imagery from a first camera and a second imagery from a second camera, wherein the first imagery is warped, wherein the first imagery depicts a bottom of a vehicle, wherein the second imagery depicts an identifier of the vehicle;

dewarp the first imagery;

stitch the first imagery such that a first image is formed;

extract a set of symbols from the second imagery, wherein the set of symbols corresponds to the identifier;

store the first image and the set of symbols in a database such that the first image is associated with the set of symbols;

retrieve the first image from the database;

compare a second image against the first image, wherein the second image depicts the bottom;

determine whether the second image satisfies a comparison threshold with respect to the first image; and

request a barrier to be opened responsive to the comparison threshold being satisfied such that the vehicle can pass the barrier.

13. The system of claim 12, wherein the server is further configured to:

record a date value and a time value associated with a capture of the second image via the first camera; and

store the second image, the date value, and the time value into the database such that the second image, the date value, and the time value are associated with the set of symbols.

14. The system of claim 12, wherein the database includes an in-memory database.

15. The system of claim 12, wherein the server dewarps the first imagery less than full.

16. The system of claim 12, wherein the bottom is illuminated via a light source such that the first camera captures the first imagery.

17. The system of claim 16, wherein the first camera and the light source are hosted via a housing.

18. The system of claim 17, wherein the first camera includes a dome that includes a transparent portion through which the first imagery is captured, wherein the housing hosts the dome.

19. The system of claim 12, wherein the server is further configured to:

request the barrier to remain closed responsive to the comparison threshold not being satisfied.

20. The system of claim 12, wherein the first imagery includes a third image, wherein the server dewarps based on:

determining based on the setting, a first set of coordinates of a pixel of the third image, wherein the determining of the first set of coordinates is for each cell of a sparse conversion map represented as a first look-up table, wherein the sparse conversion map corresponds to a sparse grid of pixels of a fourth image; and

determining, via interpolating the first set of coordinates, a second set of coordinates of a pixel of the third image such that the third image would be less rectilinear than the fourth image when displayed, wherein the determining of the second set of coordinates is for each cell of a full conversion map, wherein the second set of coordinates is represented as a second look-up table, wherein the full conversion map corresponds to a full grid of pixels of the fourth image, wherein the first look-up table and the second look-up table are comprised in a plurality of distinct data structures.