Method for radar classification of a road surface

Patent metadata

Field	Value
Publication number	US-11500087-B2
Application number	US-201816756447-A
Country	US
Kind code	B2
Filing date	Oct 15, 2018
Priority date	Oct 16, 2017
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

A method for classification of ground conditions in the vicinity of a vehicle using a radar sensor, comprising: receiving reflected portions of a radar signal at a receiver unit of a radar system; calculating information derived from the received portions of the radar signal for discrete spatial regions by the radar system or a control unit connected thereto; assigning the information to data structure units associated with a geographical location and the assignment of the information taking into account movement of the vehicle; collecting pieces of information in the respective data structure units, the pieces of information being obtained from reflected portions of radar signals transmitted at different times; evaluating the information contained in the data structure using a classifier to obtain information regarding the ground condition; assigning ground condition types to the data structure units based on evaluation results obtained by the classifier.

First claim

The invention claimed is:

1. A method for classification of ground conditions in a vicinity of a vehicle using a radar sensor, comprising the following steps:
receiving reflected portions of a radar signal at a receiver unit of a radar system;
calculating information derived from the received portions of the radar signal for discrete spatial regions by said radar system or a control unit connected thereto;
assigning the information to data structure units of a data structure, each data structure unit being associated with a fixed geographical location and the assignment of the information taking into account movement information of said vehicle;
collecting a plurality of pieces of information in the respective data structure units, the pieces of information being obtained from reflected portions of radar signals transmitted at different times;
evaluating the information contained in the data structure using a classifier in order to obtain information regarding the ground condition, wherein, in the evaluation of the information contained in said data structure using a classifier, only information with an amplitude or signal strength below a threshold value or a threshold value curve is used; and
assigning ground condition types characterizing the ground condition to said data structure units based on evaluation results obtained by said classifier.

2. The method according to claim 1 , characterized in that only information generated due to reflections on non-moving targets is used for the classification of the ground condition.

3. The method according to claim 1 , characterized in that the information stored in the data structure is signal values or measurement values proportional to the power of the reflected portion of the radar signal in a discrete spatial region or quantities derived therefrom.

4. The method according to claim 1 , characterized in that the information stored in the data structure is signal values or measurement values assigned to the data structure units without magnitude limitation or without trimming in a lower amplitude range of the signal values, or quantities derived therefrom.

5. The method according to claim 1 , characterized in that each data structure unit is assigned to a raster region of a two-dimensional or three-dimensional radar map.

6. The method according to claim 5 , characterized in that information associated with a particular discrete spatial region is assigned to a single data structure unit or that information associated with a particular discrete spatial region is assigned to a plurality of data structure units, said data structure units being correlated with adjacent raster regions of the two-dimensional or three-dimensional radar map.

7. The method according to claim 1 , characterized in that the evaluation of the information contained in said data structure is carried out separately based on the information contained in one data structure unit.

8. The method according to claim 7 , characterized in that the information contained in a data structure unit of said data structure is evaluated with regard to temporal/spectral properties.

9. The method according to claim 1 , characterized in that the evaluation of the information contained in said data structure is performed based on groups of data structure units, each group of data structure units containing a plurality of data structure units correlated with adjacent raster regions of a two-dimensional or three-dimensional radar map.

10. The method according to claim 9 , characterized in that the information contained in a plurality of data structure units of said data structure is evaluated across data structure units with regard to temporal/spectral and/or spatial properties.

11. The method according to claim 1 , characterized in that the classifier uses statistical classifiers, machine-learning or model-based methods.

12. The method according to claim 1 , characterized in that a correction step is carried out, wherein ground structure types at least partially assigned to the data structure units are corrected based on information from data structure units correlated with adjacent raster regions of a two-dimensional or three-dimensional radar map.

13. The method according to claim 1 , characterized in that a course of a road is estimated based on the ground condition types assigned to the data structure units.

14. A computer program product for classification of the ground conditions in the vicinity of a vehicle by means of a radar sensor, the computer program product comprising a computer-readable storage medium including program instructions, the program instructions being executable by a processor in order to cause the processor to execute a method comprising:
receiving reflected portions of a radar signal at a receiver unit of a radar system;
calculating information derived from the received portions of the radar signal for discrete spatial regions by said radar system or a control unit connected thereto;
assigning the information to data structure units of a data structure, each data structure unit being associated with a fixed geographical location and the assignment of the information taking into account movement information of said vehicle;
collecting a plurality of pieces of information in the respective data structure units, the pieces of information being obtained from reflected portions of radar signals transmitted at different times;
evaluating the information contained in the data structure using a classifier in order to obtain information regarding the ground condition, wherein, in the evaluation of the information contained in said data structure using a classifier, only information with an amplitude or signal strength below a threshold value or a threshold value curve is used; and
assigning ground condition types characterizing the ground condition to said data structure units based on evaluation results obtained by said classifier.

15. A radar system for a vehicle comprising a radar sensor and a control unit, by means of which reflected portions of a radar signal received by said radar sensor are evaluated, said control unit being configured to:
calculate information from the received portions of the radar signal related to a particular discrete spatial region;
assign the information to data structure units of a data structure, each data structure unit being associated with a fixed geographical location and the assignment of the information taking into account movement information of the vehicle;
store a plurality of pieces of information obtained from reflected portions of radar signals transmitted at different times in the respective data structure units;
evaluate the information contained in the data structure by means of a classifier in order to obtain information regarding a ground condition in a vicinity of said vehicle, wherein, in the evaluation of the information contained in said data structure by means of a classifier, only information with an amplitude or signal strength below a threshold value or a threshold value curve is used;
assign ground condition types characterizing the ground condition to said data structure units based on the evaluation results obtained by said classifier.

Assignees

• Conti Temic Microelectronic Gmbh
• Volkswagen Ag

Inventors

• Bagdonat Thorsten
• Meinecke Marc-Michael
• Löffler Andreas
• Fechner Thomas

Classifications

• G01S7/415

  Identification of targets based on measurements of movement associated with the target · CPC title

• G01S7/412

  based on a comparison between measured values and known or stored values · CPC title

• G01S13/931

  of land vehicles · CPC title

• G01S2013/93271

  in the front of the vehicles · CPC title

• G01S2013/932

  using own vehicle data, e.g. ground speed, steering wheel direction · CPC title