Method and device for classifying objects on a roadway in surroundings of a vehicle

1. A method for classifying objects on a roadway in surroundings of a vehicle, the method comprising the following steps:

reading in image data from an interface to at least one vehicle camera of the vehicle, the image data representing an area of the surroundings which includes at least the roadway;

evaluating the image data, wherein in the evaluating, roadway markings of the roadway are identified, a model of a surface of the roadway is generated using the identified roadway markings, and an object on the roadway is identified;

ascertaining first distance values between the at least one vehicle camera and object image points of the object which are represented by the image data, and second distance values between the at least one vehicle camera and roadway image points, defined by the model, of the surface of the roadway in surroundings of the object; and

carrying out a comparison of the first and second distance values to at least one continuity criterion for distinguishing raised objects from flat objects to classify the object as a raised or flat object as a function of a result of the comparison.

2. The method as recited in claim 1 , wherein the model is a three-dimensional model of the surface of the roadway, the image data being evaluated in the step of evaluating to generate the three-dimensional model of the surface of the roadway using interpolation, and using the identified roadway markings.

3. The method as recited in claim 1 , wherein, in the step of ascertaining, the first distance values are ascertained in rows or in strips in at least one image of the surroundings of the vehicle which is represented by the image data.

4. The method as recited in claim 1 , wherein: (i) the first distance values between the vehicle camera and object image points along edges of the object are ascertained in the step of ascertaining, and/or (ii) the comparison with respect to a deviation between the first distance values and the second distance values as a continuity criterion is carried out in the step of carrying out.

5. The method as recited in claim 1 , wherein the at least one continuity criterion includes a continuity criterion which stipulates that for a classification of the object as a raised object a deviation is minimal between the first distance values and the second distance values in a base area of the object sitting on the surface of the roadway defined by the model, increases along lateral edges of the object away from the surface of the roadway, and is maximal in a top area of the object situated opposite the base area.

6. The method as recited in claim 1 , wherein an optical flow of the image data and/or a deviation or disparity of parallaxes of the image data, is used in the step of evaluating and/or in the step of ascertaining.

7. The method as recited in claim 1 , wherein a vehicle movement model representing a movement of the vehicle is evaluated in the step of evaluating to determine a roadway property causing the movement, and to generate the model of the surface of the roadway, using the identified roadway markings and the roadway property.

8. A device configured to classify objects on a roadway in surroundings of a vehicle, the device configured to:

read in image data from an interface to at least one vehicle camera of the vehicle, the image data representing an area of the surroundings which includes at least the roadway;

evaluate the image data, wherein in the evaluating, roadway markings of the roadway are identified, a model of a surface of the roadway is generated using the identified roadway markings, and an object on the roadway is identified;

ascertain first distance values between the at least one vehicle camera and object image points of the object which are represented by the image data, and second distance values between the at least one vehicle camera and roadway image points, defined by the model, of the surface of the roadway in surroundings of the object; and

carry out a comparison of the first and second distance values to at least one continuity criterion for distinguishing raised objects from flat objects to classify the object as a raised or flat object as a function of a result of the comparison.

9. A non-transitory machine-readable memory medium on which is stored a computer program for classifying objects on a roadway in surroundings of a vehicle, the computer program, when executed by a computer, causing the computer to perform the following steps:

reading in image data from an interface to at least one vehicle camera of the vehicle, the image data representing an area of the surroundings which includes at least the roadway;

evaluating the image data, wherein in the evaluating, roadway markings of the roadway are identified, a model of a surface of the roadway is generated using the identified roadway markings, and an object on the roadway is identified;

ascertaining first distance values between the at least one vehicle camera and object image points of the object which are represented by the image data, and second distance values between the at least one vehicle camera and roadway image points, defined by the model, of the surface of the roadway in surroundings of the object; and

carrying out a comparison of the first and second distance values to at least one continuity criterion for distinguishing raised objects from flat objects to classify the object as a raised or flat object as a function of a result of the comparison.