Three dimensional traffic sign detection

A method of detecting a three-dimensional position of a traffic sign and controlling a feature of a vehicle based on the three-dimensional position of the traffic sign, the method comprising:

• receiving, via at least one processor, an image from a camera;
• processing the image using a neural network, wherein the neural network includes a traffic sign class block regressing a traffic sign class for a traffic sign included in the image and a rotation block regressing an orientation for the traffic sign, wherein the neural network regresses location and dimensions of a two-dimensional (2D) bounding box around the traffic sign in image coordinates;
• calculating azimuth and elevation angle data, for functions thereof, via the at least one processor, based on the location of the 2D bounding box;
• retrieving, via the at least one processor and from a traffic sign information database, dimensions for the traffic sign based on the traffic sign class;
• solving for Z, via the at least one processor, one or more equations based on position and dimensions of the 2D bounding box, the orientation and dimensions of the traffic sign, the azimuth and elevation angle data, or functions thereof, and intrinsic parameters of the camera, wherein Z is a forward distance from the camera to the traffic sign in camera coordinates;
• determining, via the at least one processor, a three-dimensional (3D) position of the traffic sign based on the location of the 2D bounding box and Z;
• and
• controlling, via the at least one processor, at least one feature of the vehicle based on the 3D position of the traffic sign.