Object identification using radar data
An evaluation device for obtaining a segmentation of an environment from a radar recording of the environment, that has an input interface configured to obtain initial training data, where the initial training data comprise radar data of the radar recording and initial characteristics of objects located in the environment recorded with a radar sensor that generates the radar recordings, and where the evaluation device is configured to forward propagate an artificial neural network with the initial training data to obtain second characteristics of the objects determined with the artificial neural network in the forward propagation, and to obtain weighting factors for neural connections of the artificial neural network through backward propagation of the artificial neural network with the differences between the second characteristics and the initial characteristics, in order to obtain the segmentation of the environment through renewed forward propagation with these radar data.
1. An evaluation device for obtaining a segmentation of a radar recording of an environment of a radar sensor, comprising:
an input interface configured to obtain initial training data,
wherein the initial training data comprises radar data of the radar recording and initial characteristics of objects located in the environment recorded with the radar sensor,
wherein the radar sensor generates the radar recording,
wherein the radar data comprises the respective distances of these objects to the radar sensor, and the respective azimuth and elevation angles between the objects and the radar sensor belonging to these distances and the speed of the objects relative to the radar sensor, and
wherein the evaluation device is configured to forward propagate an artificial neural network with the initial training data,
wherein the evaluation device is configured to obtain second characteristics of the objects determined with the artificial neural network in the forward propagation,
wherein the evaluation device is configured to obtain weighting factors for neural connections of the artificial neural network through backward propagation of the artificial neural network with the differences between the second characteristics and the initial characteristics, and
wherein the evaluation device obtains the segmentation of the environment from a renewed forward propagation with the radar data,
wherein the evaluation device obtains a four dimensional data range containing the following dimensions of the objects: the distance of the objects, the speed of the objects, the azimuth angle of the objects, and the elevation angle of the objects relative to the radar sensor, and
wherein the evaluation device is electrically connected to a driver assistance system of a vehicle, the driver assistance system being electrically connected to the radar sensor and configured to recognize traffic objects based on the four dimensional data range.
2. The evaluation device according to claim 1 , wherein the evaluation device is configured to obtain a virtual image of the environment from the radar recording with the artificial neural network based on the initial characteristics and the segmentation.
3. The evaluation device according to claim 1 , wherein the initial characteristics are characteristics of at least one of the following: at least one street, objects on or adjacent to at least one street, traffic signs, and crash barriers or other vehicle retention systems.