IP Library Granted Patent US 12,142,005
Granted Patent B2
US 12,142,005 · App. 17/500,882 · Granted Nov 12, 2024

Camera based distance measurements

Inventor: Igal Raichelgauz (Tel Aviv, IL)
Assignee: AUTOBRAINS TECHNOLOGIES LTD
G06T7/80G01S17/931G06T7/50G06T7/60G05D1/0248
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,142,005
App. No.
17/500,882
Granted
Nov 12, 2024
Kind
B2
Abstract

Systems, and method and computer readable media that store instructions for distance measurement, the method may include obtaining, from a camera of a vehicle, an image of a surroundings of the vehicle; searching, within the image, for an anchor, wherein the anchor is associated with at least one physical dimension of a known value; and when finding the anchor, determining a distance between the camera and the anchor based on, (a) the at least one physical dimension of a known value, (b) an appearance of the at least one physical dimension of a known value in the image, and (c) a distance-to-appearance relationship that maps appearances to distances, wherein the distance-to-appearance relationship is generated by a calibration process that comprises obtaining one or more calibration images of the anchor, and obtaining one or more distance measurements to the anchor.

Claims (38)

1. A method for distance measurement, the method comprises:

obtaining, from a camera of a vehicle, an image of a surroundings of the vehicle;

searching, within the image, for an anchor, wherein the anchor is associated with at least one physical dimension of a known value;

when finding the anchor, determining a distance between the camera and the anchor based on, (a) the at least one physical dimension of a known value, (b) an appearance of the at least one physical dimension of a known value in the image, and (c) a distance-to-appearance relationship that maps appearances to distances, wherein the distance-to-appearance relationship is generated by a calibration process that comprises obtaining one or more calibration images of the anchor, and obtaining one or more distance measurements to the anchor;

wherein the method further comprises executing the calibration process;

wherein the camera is a first camara, the one or more calibration images are multiple calibration images acquired at different distances from a second camera;

wherein the one or more distance measurements are indicative of the different distances; and

wherein the executing of the calibration process comprises calculating the distance-to-appearance relationship based on the appearances of the at least one physical dimension of a known value in the multiple calibration images and the different distances.

2. The method according to claim 1 , wherein the one or more distance measurements are executed by an active sensor, wherein the executing of the calibration process comprises searching the anchor in one or more images acquired by the active sensor and searching for the anchor, by applying an object detection algorithm, in the one or more calibration images.

3. The method according to claim 1 , wherein the one or more distance measurements are executed by an active sensor, wherein the executing of the calibration process comprises utilizing a spatial relationship between pixels of the images acquired by the active sensor and pixels of the one or more calibration images, to detect the anchor in the images acquired by the active sensor.

4. The method according to claim 1 wherein the at least one physical dimension of a known value of the anchor is a dimension of the anchor.

5. The method according to claim 1 wherein the at least one physical dimension of a known value of the anchor is a distance between the anchor and another anchor.

6. The method according to claim 1 comprising approximating the anchor by a bounding box, and measuring at least one dimension of the bounding box to provide a value indicative of the appearance of the at least one physical dimension of the known value in the image.

7. A non-transitory computer readable medium that stores instructions executable by a processor for:

obtaining, from a camera of a vehicle, an image of a surroundings of the vehicle;

searching, within the image, for an anchor, wherein the anchor is associated with at least one physical dimension of a known value;

when finding the anchor, determining a distance between the camera and the anchor based on, (a) the at least one physical dimension of a known value, (b) an appearance of the at least one physical dimension of a known value in the image, and (c) a distance-to-appearance relationship that maps appearances to distances, wherein the distance-to-appearance relationship is generated by a calibration process that comprises obtaining one or more calibration images of the anchor, and obtaining one or more distance measurements to the anchor; and

executing the calibration process;

wherein the camera is a first camara, the one or more calibration images are multiple calibration images acquired at different distances from a second camera;

wherein the one or more distance measurements are indicative of the different distances; and

wherein the executing of the calibration process comprises calculating the distance-to-appearance relationship based on the appearances of the at least one physical dimension of a known value in the multiple calibration images and the different distances.

8. The non-transitory computer readable medium according to claim 7 wherein the one or more distance measurements are executed by an active sensor, wherein the executing of the calibration process comprises searching the anchor in one or more images acquired by the active sensor and searching for the anchor, by applying an object detection algorithm, in the one or more calibration images.

9. The non-transitory computer readable medium according to claim 7 wherein the one or more distance measurements are executed by an active sensor, wherein the executing of the calibration process comprises utilizing a spatial relationship between pixels of the images acquired by the active sensor and pixels of the one or more calibration images, to detect the anchor in the images acquired by the active sensor.

10. The non-transitory computer readable medium according to claim 7 wherein the at least one physical dimension of a known value of the anchor is a dimension of the anchor.

11. The non-transitory computer readable medium according to claim 7 wherein the at least one physical dimension of a known value of the anchor is a distance between the anchor and another anchor.

12. The non-transitory computer readable medium according to claim 7 that stores instructions executable by a processor for approximating the anchor by a bounding box, and measuring at least one dimension of the bounding box to provide a value indicative of the appearance of the at least one physical dimension of the known value in the image.

13. A computerized system comprising a processor that is configured to:

receive, from a camera of a vehicle, an image of a surroundings of the vehicle;

search, within the image, for an anchor, wherein the anchor is associated with at least one physical dimension of a known value;

when finding the anchor, determine a distance between the camera and the anchor based on, (a) the at least one physical dimension of a known value, (b) an appearance of the at least one physical dimension of a known value in the image, and (c) a distance-to-appearance relationship that maps appearances to distances, wherein the distance-to-appearance relationship is generated by a calibration process that comprises obtaining one or more calibration images of the anchor, and obtaining one or more distance measurements to the anchor; and

execute the calibration process;

wherein the camera is a first camara, the one or more calibration images are multiple calibration images acquired at different distances from a second camera,

wherein the one or more distance measurements are indicative of the different distances; and

wherein the executing of the calibration process comprises calculating the distance-to-appearance relationship based on the appearances of the at least one physical dimension of a known value in the multiple calibration images and the different distances.

14. The computerized system according to claim 13 wherein the one or more distance measurements are executed by an active sensor, wherein the processor is configured to execute the calibration process by searching the anchor in one or more images acquired by the active sensor and searching for the anchor, by applying an object detection algorithm, in the one or more calibration images.

15. The computerized system according to claim 13 wherein the one or more distance measurements are executed by an active sensor, wherein the processor is configured to execute the calibration process by utilizing a spatial relationship between pixels of the images acquired by the active sensor and pixels of the one or more calibration images, to detect the anchor in the images acquired by the active sensor.

16. The computerized system according to claim 13 wherein the at least one physical dimension of a known value of the anchor is a dimension of the anchor.

17. The computerized system according to claim 13 wherein the at least one physical dimension of a known value of the anchor is a distance between the anchor and another anchor.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2021
From: RAICHELGAUZ, IGAL
To: AUTOBRAINS TECHNOLOGIES LTD.
Reel/Frame 057986/0868 →
Continuity (2)
Provisional Application 63091303 · Oct 13, 2020
Related Publication 20220114756A1 · Apr 14, 2022