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
First Claim
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.
1 Assignment
0 Petitions
Accused Products
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).
23 Citations
13 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
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. - View Dependent Claims (12, 13)
-
Specification