Method for classifying a traffic sign, or road sign, in an environment region of a motor vehicle, computational apparatus, driver assistance system and motor vehicle

• US 10,896,337 B2
• Filed: 09/28/2017
• Issued: 01/19/2021
• Est. Priority Date: 09/29/2016
• Status: Active Grant

• Current Assignee: Valeo Schalter und Sensoren GmbH (Valeo SE)
• Original Assignee: Valeo Schalter und Sensoren GmbH (Valeo SE)
• Inventors: Sergeev, Nikolai
• Primary Examiner(s): Milord, Marceau
• Application Number:
  US16/337,700
• Publication Number:
  US 20200034641A1
• Time in Patent Office: 1,209 Days
• Field of Search: 382104
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G08G 1/09623 Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle G08G1/0967 takes precedence

Abstract

The invention relates to a method for classifying a traffic sign (7) in an environment region (4) of a motor vehicle (1) as a traffic sign sticker (9) located on an industrial or commercial vehicle (10) or as a stationary traffic sign (8), wherein in the method at least one first image (11, 12) of the environment region (4), captured by a camera (3) of the motor vehicle (1), is received and the traffic sign (7) is recognized in the at least one first image (11, 12), wherein a geometric dimension (D1′, D2′) of the traffic sign (7) in the first image (11, 12) is determined on the basis of said first image (11, 12), a first reference dimension (Dmin, Dmax), which is characteristic of a stationary traffic sign (8), is prescribed for the captured traffic sign (7), a first position (Pmin, Pmax) of the traffic sign (7) in the environment region (4) is estimated based on the geometric dimension (D1′, D2′) of the traffic sign (7) in the first image (11, 12) and on the basis of the first reference dimension (Dmin, Dmax), and the traffic sign (7) is classified as the traffic sign sticker (9) or as the stationary traffic sign (8) based on the estimated first position (Pmin, Pmax). The invention additionally relates to a computational apparatus (6), a driver assistance system (2) and a motor vehicle (1).

Claims

1. A method for classifying a traffic sign in an environment region of a motor vehicle as one of a traffic sign sticker located on an industrial or commercial vehicle or as a stationary traffic sign, the method comprising:

receiving at least one first image of the environment region captured by a camera of the motor vehicle;

detecting the traffic sign in the at least one first image;

determining a geometric dimension of the traffic sign in the first image on the basis of said first image;

prescribing a first reference dimension characteristic of a stationary traffic sign for the captured traffic sign;

estimating a first position of the traffic sign in the environment region based on the geometric dimension of the traffic sign in the first image and on the basis of the first reference dimension; and

classifying the traffic sign as the traffic sign sticker or as the stationary traffic sign based on the estimated first position,

wherein a movement progression of the traffic sign in the images is determined in image coordinates on the basis of the first image and at least one second image, which has been captured by the camera, a first movement progression characterizing a stationary traffic sign is determined in the image coordinates proceeding from the first estimated position in the environment region, and the captured traffic sign is classified as the stationary traffic sign or as the traffic sign sticker on the basis of a comparison of the movement progression of the captured traffic sign to the first characterizing movement progression.

2. The method according to claim 1, further comprising:

specifying a second reference dimension characteristic of the stationary traffic sign for the captured traffic sign;

estimating a second position in the environment region on the basis of the dimension of the traffic sign in the image and on the basis of the second reference dimension; and

classifying the traffic sign as the traffic sign sticker or the stationary traffic sign on the basis of the estimated first and second positions.

3. The method according to claim 1, wherein a predetermined minimum diameter of 40 cm, characteristic of the stationary traffic sign, is specified as the first reference dimension, and a predetermined maximum diameter of 2 m, characteristic of the stationary traffic sign, is specified as a second reference dimension.

4. The method according to claim 1, wherein a distance between the traffic sign and the motor vehicle is determined at least on the basis of the first position and the traffic sign is classified as the stationary traffic sign when the distance falls below a predetermined threshold value, and the traffic sign is classified as the traffic sign sticker when the distance at least exceeds the predetermined threshold value.

5. The method according to claim 1, wherein a second position of the traffic sign in the environment region is additionally estimated on the basis of the first image and on the basis of a second predetermined reference dimension of the stationary traffic sign, a second movement progression characterizing a stationary traffic sign in the image coordinates is determined on the basis of the second estimated position in the environment region, and the captured traffic sign is classified as the stationary traffic sign or as the traffic sign sticker on the basis of the comparison of the movement progression of the captured traffic sign to the second characterizing movement progression.

6. The method according to claim 5, wherein the captured traffic sign is identified as the stationary traffic sign if the movement progression of the captured traffic sign is located within a corridor that is formed by the first and the second characterizing movement progression, and otherwise is classified as the traffic sign sticker arranged on the industrial vehicle.

7. The method according to claim 5, wherein the first and second characterizing movement progressions are determined under the assumption that the motor vehicle is travelling on a level road.

8. The method according to claim 7, wherein, when comparing the movement progression of the captured traffic sign to the first and second characterizing movement progressions, only image coordinates along a horizontal direction are compared.

9. The method according to claim 1, wherein the traffic sign is recognized as the stationary traffic sign if in at least one of the images a post holding the traffic sign is recognized.

10. The method according to claim 1, wherein information provided by the traffic sign including a maximum speed that applies in the environment region, is made available to a driver assistance system for supporting a driver of the motor vehicle in the form of an input variable if the traffic sign has been classified as the stationary traffic sign, and is ignored if the traffic sign has been classified as the traffic sign sticker arranged on the industrial vehicle.

11. A computational apparatus for a driver assistance system of a motor vehicle, configured to:

receive at least one first image of the environment region captured by a camera of the motor vehicle;

detect the traffic sign in the at least one first image;

determine a geometric dimension of the traffic sign in the first image on the basis of said first image;

prescribe a first reference dimension characteristic of a stationary traffic sign for the captured traffic sign;

estimate a first position of the traffic sign in the environment region based on the geometric dimension of the traffic sign in the first image and on the basis of the first reference dimension; and

classify the traffic sign as the traffic sign sticker or as the stationary traffic sign based on the estimated first position,

wherein a movement progression of the traffic sign in the images is determined in image coordinates on the basis of the first image and at least one second image, which has been captured by the camera, a first movement progression characterizing a stationary traffic sign is determined in the image coordinates proceeding from the first estimated position in the environment region, and the captured traffic sign is classified as the stationary traffic sign or as the traffic sign sticker on the basis of a comparison of the movement progression of the captured traffic sign to the first characterizing movement progression.

12. A driver assistance system for a motor vehicle for classifying a traffic sign in an environment region of the motor vehicle as one of a traffic sign sticker that is affixed to a commercial or industrial vehicle or a stationary traffic sign, the driver assistance system comprising:

at least one camera for capturing at least one first image of the environment region; and

a computational apparatus according to claim 11.

13. A motor vehicle having a driver assistance system according to claim 12.