Method for generating synthetic traffic sign data

1 . A computer-implemented method for generating synthetic traffic sign data for training a traffic sign detection model, the method comprises:

extracting, from a sample image depicting a surrounding environment of a vehicle comprising a detected traffic sign, a face of the detected traffic sign, using information indicative of an orientation of the detected traffic sign;

forming a 3D model of the traffic sign having the extracted face of the detected traffic sign; and

generating synthetic traffic sign data by placing the 3D model of the traffic sign in one or more background images, wherein the 3D model is placed in the one or more background images based on a distribution of a placement of real-world traffic signs in a dataset of real-world images.

2 . The method according to claim 1 , further comprising capturing the sample image depicting the surrounding environment of the vehicle by one or more cameras of the vehicle.

3 . The method according to claim 1 , further comprising detecting, by a machine learning model, the traffic sign in the sample image depicting the surrounding environment of the vehicle.

4 . The method according to claim 1 , further comprising updating the dataset of images by adding the generated synthetic traffic sign data to the dataset of images.

5 . The method according to claim 1 , wherein the step of extracting the face of the detected traffic sign is performed in response to the detected traffic sign being classified as a sign comprised within a defined traffic sign class.

6 . The method according to claim 1 , wherein the step of extracting the face of the detected traffic sign comprises forming a 2D representation of the detected traffic sign by projecting the detected traffic sign into 2D, based on the information indicative of the orientation, and

wherein the step of forming the 3D model of the traffic sign comprises extruding the 2D representation of the face of the traffic sign into a 3D representation of the traffic sign.

7 . The method according to claim 1 , wherein placing the 3D model of the traffic sign in one or more background images comprises determining a position, orientation and size of the 3D model within the one or more background images in which the 3D model is to be placed, based on the distribution of the placement of real-world traffic signs in the dataset of real-world images.

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

obtaining a label corresponding to the detected traffic sign, and

assigning the label to the generated synthetic traffic sign data.

9 . The method according to claim 1 , wherein the steps of the method are performed locally in the vehicle, and wherein the method further comprises:

transmitting the generated synthetic traffic sign data to a remote server and/or to a further vehicle.

10 . A non-transitory computer readable storage medium storing instructions which, when executed by a computing device, causes the computing device to carry out the method according to claim 1 .

11 . A method for training a traffic sign detection model, the method comprising:

obtaining a training dataset comprising synthetic traffic sign data generated by the method according to claim 1 ;

training the traffic sign detection model on the obtained training dataset, and

wherein the step of training the traffic sign detection model is performed in a server, or in a vehicle.

12 . A device for generating synthetic traffic sign data for training a traffic sign detection model, the device comprising control circuitry configured to:

extract, from a sample image depicting a surrounding environment of a vehicle comprising a detected traffic sign, a face of the detected traffic sign, using information indicative of an orientation of the detected traffic sign;

form a 3D model of the traffic sign having the extracted face of the detected traffic sign; and

generate synthetic traffic sign data by placing the 3D model of the traffic sign in one or more background images, wherein the 3D model is placed in the one or more background images based on a distribution of a placement of real-world traffic signs in a dataset of real-world images.

13 . The device according to claim 12 , wherein the control circuitry is configured to extract the face of the detected traffic sign in response to the detected traffic sign being classified as a sign comprised within a defined traffic sign class.

14 . The device according to claim 12 , wherein extracting the face of the detected traffic sign comprises forming a 2D representation of the detected traffic sign by projecting the detected traffic sign into 2D, based on the information indicative of the orientation, and

wherein forming the 3D model of the traffic sign comprises extruding the 2D representation of the face of the traffic sign into a 3D representation of the traffic sign.

15 . A vehicle comprising:

one or more sensors, and

a device for generating synthetic traffic sign data for training a traffic sign detection model, according to claim 12 .