Method and system for determining ground level using an artificial neural network
A method for determining the roadway plane in the surrounding area of a vehicle, the vehicle comprising a stereo camera system for capturing stereo images of the surrounding area of the vehicle and an artificial neural network for processing the image information provided by the stereo camera system, wherein the neural network determines disparity information of the surrounding area of the vehicle, wherein, on the basis of the disparity information, distance information is calculated which contains information regarding the distance of the objects displayed on the image information from the stereo camera system or the vehicle, wherein roadway distance information is extracted from the distance information, wherein the roadway plane is determined on the basis of the roadway distance information.
1 . A method for determining a roadway plane in a surrounding area of a vehicle, wherein the vehicle has a stereo camera system for capturing stereo images of the surrounding area of the vehicle and a trained artificial neural network for processing the image information provided by the stereo camera system, the method comprising:
by the trained artificial neural network, determining disparity information of the surrounding area of the vehicle;
by the trained artificial neural network, on the basis of the disparity information, calculating distance information, which contains information relating to the distance of objects displayed on the image information from the stereo camera system or the vehicle;
extracting roadway distance information from the distance information, wherein a roadway surface captured in the stereo images is represented by the roadway distance information; and
while the vehicle is in operation, determining the roadway plane on the basis of the roadway distance information by placing an assumed roadway plane that approximates the roadway surface represented by the roadway distance information in such a way that the total error resulting between the assumed roadway plane and the roadway distance information is minimized.
2 . The method according to claim 1 , wherein the extraction of the roadway distance information from the distance information is performed on the basis of object information that is provided by an environment model of a driving assistance system of the vehicle.
3 . The method according to claim 1 , wherein the extraction of the roadway distance information from the distance information is performed by subtracting or eliminating information included in an environment model of a driving assistance system of the vehicle from information included in a stereo image or from the distance information contained in the stereo image.
4 . The method according to claim 1 , wherein the trained artificial neural network compensates for calibration inaccuracies resulting from a relative movement of the two cameras of the stereo camera system with respect to one another by a nonlinear correlation of the image information.
5 . The method according to claim 1 , further comprising checking on the basis of the roadway plane whether objects are present on the roadway in the surrounding area of the vehicle.
6 . The method according to claim 5 , wherein the size of an object or the height of an object in the roadway area is checked on the basis of the information relating to the roadway plane.
7 . The method according to claim 5 further comprising:
identifying an object on the roadway; and
determining height of the identified object, wherein, on the basis of the height of the identified object, the object is classified.
8 . The method according to claim 1 , wherein the trained artificial neural network is retrained on the basis of information from stereo images acquired while the vehicle is in motion and which are labeled as information associated with the roadway.
9 . The method according to claim 1 , wherein the trained artificial neural network provides the disparity information and the calculation of the distance information from the disparity information is performed in a separate computing unit, or the trained artificial neural network provides the distance information as output information.
10 . A system for identifying a roadway plane in a surrounding area of a vehicle, comprising:
a stereo camera system for capturing stereo images of the surrounding area of the vehicle; and
a trained artificial neural network for processing the image information provided by the stereo camera system,
wherein the trained artificial neural network is configured to determine disparity information of the surrounding area of the vehicle,
wherein the trained artificial neural network is configured to calculate, on the basis of the disparity information, distance information which contains information regarding the distance of objects displayed on the image information from the stereo camera system or the vehicle,
wherein the trained artificial neural network or a computing unit provided separately from the trained artificial neural network is configured to
extract roadway distance information from the distance information, wherein a roadway surface captured in the stereo images is represented by the roadway distance information, and
while the vehicle is in operation, determine the roadway plane from the roadway distance information by placing an assumed roadway plane that approximates the roadway surface represented by the roadway distance information in such a way that the total error resulting between the assumed roadway plane and the roadway distance information is minimized.
11 . The system according to claim 10 , wherein the system is configured to receive object information provided by an environment model of a driving assistance system of the vehicle and in that the system is designed to extract the roadway distance information from the distance information on the basis of the object information.
12 . The system according to claim 10 , wherein the system is configured to extract the roadway distance information from the distance information by subtracting and/or eliminating information included in an environment model of a driving assistance system of the vehicle from information included in a stereo image or from the distance information contained in the stereo image.
13 . The system according to claim 10 , wherein the system is configured to check, on the basis of the roadway plane, whether objects are present on the roadway in the surrounding area of the vehicle.
14 . The system according to claim 13 , wherein the system is configured to check, on the basis of the roadway plane, the size of an object or the height of an object in the roadway area.
15 . A vehicle comprising a system according to claim 10 .
16 . The system according to claim 10 , wherein the stereo camera system comprises inertial sensors configured to detect movement of cameras in the stereo camera system, and wherein measurement data from the inertial sensors is used to train the artificial neural network such that weighting factors of the artificial neural network and calculation of the distance information are adjusted based on changed orientation of the cameras.