METHOD FOR IDENTIFYING AND CLASSIFYING OBJECTS, AND MOTOR VEHICLE

Abstract

A method for identifying and classifying objects in the surroundings of a motor vehicle, which method uses merely a single sensor for object detection. The method is characterized in that this single sensor moves in space while the object is being detected. In this case, during the measurement, the single sensor would act to a certain extent like a second sensor. The echo signals, reflected by the object, of different measurement cycles can be used to determine the differential speed, distance and angle. The method provides the possibility of being able to classify, by means of a single sensor, objects and items in the surroundings of a motor vehicle in terms of their size.

Claims

1. A method of detecting and classifying an object disposed in surroundings of a motor vehicle, the method comprising: emitting, by a sensor disposed in or on the motor vehicle and configured to detect the object, active radiation; classifying with regard to a spatial extent of the object, including, moving the sensor relative to the object from one measurement cycle to at least one subsequent measurement cycle, and recording echo signals reflected from the object during the one measurement cycle and the at least one subsequent measurement cycle, and statistically evaluating information contained in the recorded echo signals.

2. The method of claim 1, wherein the sensor is a single sensor.

3. (canceled)

4. The method of claim 1, wherein the sensor is a lidar sensor or an ultrasonic sensor.

5. The method of claim 1, wherein the sensor is a component of a vehicle door, and the moving step is accomplished by performing an opening and/or closing process of the vehicle door.

6. The method of claim 1, further comprising: determining a feature vector from the information contained in the recorded echo signals, and the feature vector is employed for the statistically evaluating step and the classifying step.

7. The method of claim 1, further comprising: using a tracking algorithm to track the object over time.

8. The method of claim 6, wherein the classifying step includes comparing the determined feature vector with a first feature vector for an ideal pole and a second feature vector for an ideal wall, and classifying the object as a wall or as a pole depending on the comparing step.

9. The method of claim 8, wherein the comparing step includes determining distances bewteen the determined feature vector and the first feature vector and bewteen the determined feature vector and the second feature vector, wherein the object is selected as a classified object based on a distance of the distance which is smallest.

10. The method of claim 9, wherein the object is classified neither as an ideal pole nor as an ideal wall if the distances exceed a predetermined distance.

11. The method of claim 9, further comprising: calculating a Euclidean distance after the determining step., in particular, is calculated.

12. The method of claim 6, wherein the determining step includes determining at least one of: a differential angle; a maximum angle of change; a total distance travelled during the measurement cycles averaged over a time required thereof; a differential path from the one measurement cycle to the at least one subsequent measurement cycle; and a maximum change of a phase angle.

13. The method of claim 1, further comprising: detecting the surroundings, wherein the sensor is a component of a vehicle door, and, the detecting the surroundings step includes performing an opening process of the vehicle door, and outputting a warning signal if an imminent collision of the vehicle door with the object is detected based on the detecting the surroundings step.

14. A method of detecting and classifying objects disposed in surroundings of a motor vehicle, the method comprising: emitting active radiation by sensor during a plurality of successive measurement cycles; recording echo radiation reflected by the object; moving the sensor relative to the object after each measurement cycle of the plurality of successive measurement cycles; evaluating the recorded echo radiation recorded during each measurement cycle by statistical methods; and classifying the object based on the evaluating step.

15. A motor vehicle provided with at least one vehicle door, the motor vehicle comprising: at least one sensor device including a radar sensor, the radar sensor configured to emit active radiation during a plurality of successive measurement cycles, during which the radar sensor is moved relative to an object after each measurement cycle of the plurality of successive measurement cycles; and an evaluation device configured to evaluate, by statistical methods, recorded echo radiation reflected by the object and recorded for each measurement cycle of the plurality of successive measurement cycles, and classify the object based on the statistical methods.

16. The motor vehicle of claim 15, wherein the radar sensor is installed in a door handle, and/or behind a cover.

17. The motor vehicle of claim 15, further comprising: an electric drive configured to automatically open or close the vehicle door.

18. The motor vehicle of claim 15, wherein the sensor is a radar-emitting radar sensor.

19. The motor vehicle of claim 15, wherein the sensor is an FMCW radar sensor.

20. The method of claim 1, wherein the sensor is a component of a vehicle door, and the moving step is accomplished by a motorized opening and/or closing process of the vehicle door.

21. The method of claim 9, further comprising: calculating a weighted Euclidean distance after the determining step.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present disclosure is explained in more detail below with reference to the embodiments shown in the schematic figures, wherein:

[0034] FIG. 1 is a flow chart of a method according to the invention for detecting and classifying objects detected by using radar beams;

[0035] FIG. 2 is a schematic representation explaining the classification process in shown FIG. 1;

[0036] FIG. 3 is a simplified block diagram of a vehicle according to the invention;

[0037] FIG. 4 is a block diagram showing an example of the implementation of the radar sensor.

[0038] The accompanying figures are intended to provide a further understanding of embodiments of the invention. They illustrate embodiments and, in connection with the description, serve to explain principles and concepts of the invention. Further embodiments and many of the advantages mentioned will be apparent when taken in reference to the figures. The elements of the figures are not necessarily shown to scale with respect to each other.

[0039] In the figures, identical, functionally identical and identically acting elements, features and components are—unless otherwise stated—each provided with the same reference numerals.

DETAILED DESCRIPTION

[0040] As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention that may be embodied in various and alternative forms. The figures are not necessarily to scale; some features may be exaggerated or minimized to show details of particular components. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present invention.

[0041] A known method and device, in which several radar sensors are employed in order to classify obstacles, are described, for example, in DE 102 42 808 B4. DE 102 42 808 B4 describes distinguishing between at least two types of objects, i.e. a more point-like object from a more planar object, by use of a radar sensor with very high spatial resolution or alternatively several radar sensors.

[0042] FIG. 1 shows a flow chart of a method according to the invention for detecting and classifying objects detected by means of radar beams in the surroundings of a door or cover of a vehicle. For these purposes, a single, mobile radar sensor and an evaluation device are provided. In order to provide mobility to the radar sensor, the radar sensor is integrated in a vehicle door, for example in a door handle or a side mirror 29.

[0043] In a first step S1, the radar sensor or its transmitting antenna emits radar radiation, for example a pulsed HF signal, in the direction of an object to be detected. The radar sensor may be an FMCW (frequency modulated continuous wave) radar unit, although a pulse radar or other modulation methods are also conceivable.

[0044] In a subsequent step S2, echo signals are picked up by the radar sensor or its receiving antenna, and are evaluated accordingly. The echo signals are generated by reflection of the radar signal on a surface of the object.

[0045] Then, in the subsequent step S3, the radar sensor is moved relative to the object to be detected for at least one subsequent measurement cycle, for example by opening the door. Subsequently, the two steps S1, S2 are carried out again. The iteration loop of steps S1 to S3 may be run through several times.

[0046] By means of steps S1, S2, a differential angle with respect to the object and, due to the known distance of the transmitting and receiving antenna, the point in space, and thus also the angle of the object with respect to the radar sensor or the vehicle may be determined.

[0047] The radar sensor may be a so-called FMCW radar sensor. When using FMCW, the distance is determined by a Fast Fourier Transformation (FFT). A second FFT makes it then possible to determine the speed. Upon comparison of the phases of the combinable receiving and transmitting antennas, the azimuth angle may be determined for a given distance/velocity combination, and, if the antenna array is two-dimensional, the elevation angle may also be determined.

[0048] By means of an evaluation device, the recorded echo signals are temporally evaluated during step S4 using statistical procedures and methods. Based on the information thus obtained, a feature vector is calculated. The feature vector contains various numeric parameters which are extracted from the evaluated echo signals, which parameters characterize the characteristic properties of the object to be detected.

[0049] Finally, in step S5, the object is classified accordingly on the basis of the feature vector determined in this way. In this classification, it is at least determined whether the object to be detected is an ideal pole or an ideal wall. Optionally, a classification may also be made in such a way that the object is neither an ideal pole nor an ideal wall.

[0050] FIG. 2 shows an illustration for explaining the classification process according to steps S4 and S5 shown in FIG. 1.

[0051] In FIG. 2, reference numeral 10 denotes a feature vector determined by measurement. The feature vector 10 has been obtained by evaluation from the recorded echo signals according to step S4. This feature vector 10 contains various contents (or features) depending on the application and system settings, such as the statistical evaluation of the angle information, distance travelled, resolution and accuracy of the measurement, duration of a measurement cycle, etc. The feature vector 10 may also be employed for other purposes. Statistical methods for the temporal analysis of the information include the median, mean, variance, temporal maximum and minimum, or the calculation of these parameters by limitation to a fixed number of measurements in the past (sliding window), etc.

[0052] In order to perform the classification in step S5, a first feature vector 11 and a second feature vector 12 are then provided. The two feature vectors 11, 12 have been calculated empirically, wherein the first feature vector 11 represents an ideal pole, and the second feature vector 12 represents an ideal wall. In order to perform the classification in step S5, a distance between the feature vector 10 and the two feature vectors 11, 12 is then calculated, for example by determining a first weighted Euclidean distance D1 between the feature vectors 10 and 11 on the one hand (for a comparison to an ideal pole), and a second weighted Euclidean distance D2 between the feature vectors 10 and 12 on the other hand (for a comparison to an ideal wall). If D1>D2, then it is assumed that the object to be detected has more in common with a wall, and is therefore classified as a wall. If, on the other hand, D1<D2, then it is assumed that the object to be detected has more in common with a pole, and is therefore classified as a pole. The comparison of the vectors is not limited to the Euclidean distance as an evaluation criterion.

[0053] If the calculated distances D1, D2 are too large, i.e. if D1>Dmax and at the same time D2>Dmax, then it must be assumed that the object to be detected is neither a wall nor a pole, but is rather a diffuse object that cannot be detected exactly, such as in the case of a wire mesh fence, a bush, a hedge, a plant or the like. In this case, there is no classification, but at least an indication that the object cannot be mapped in a two-class classification.

[0054] In addition, a weighting factor may be provided which allows a tendency towards one of the two classes.

[0055] FIG. 3 shows a simplified block diagram of a vehicle 20 according to the invention, which is equipped with one or more vehicle door systems. The vehicle door system designated by reference numeral 21 may include a door 22 and/or a cover 28, a radar sensor 23 and an evaluation device 24.

[0056] The door 22 may be a side door 22 (e.g. including a rear view camera), a sliding door or a rear door. The cover 28 may be a boot lid, a tailgate 28, a tailgate window or the like. The radar sensor 23, which is for example a MIMO radar sensor, may include a transmitting device 25 and a receiving device 26. In the example shown, the radar sensor 23 is integrated in a door handle 27, a door latch or the like.

[0057] FIG. 4 is a block diagram showing an example for implementing a radar sensor.

[0058] The radar sensor 23 may include at least one integrated semiconductor circuit (IC) 30 and an antenna arrangement 31. As an example, the IC 30 as well as the antenna arrangement 31 are mounted on a corresponding printed circuit board (not shown in FIG. 3). This circuit board may be elongated, and oriented, for example, in the longitudinal direction of the door handle 27.

[0059] The antenna arrangement 31 includes transmitting antennas 32 and receiving antennas 33. In one or more embodiments, the antenna arrangement 31 serves both to transmit and to receive transmitted and received radar beams. The antenna arrangement 31 may be designed in such a way that an angle measurement may be carried out in two mutually perpendicular planes, such as an angle measurement in azimuth and elevation. For this purpose, the antenna arrangement 31, as shown in FIG. 4, may have antenna elements 34 arranged in a matrix-like manner in two mutually perpendicular directions, which may be implemented as microstrip patches, for example. However, the antenna elements 31 do not necessarily have to be arranged perpendicular to each other, but may also be arranged in a different more or less ordered arrangement. The spacings 35 of the antenna elements 34 are known, and should correspond to at least half the wavelength (λ/2) of the radar radiation. This allows angular resolution in both azimuth and elevation, provided the antenna arrangement 31 is appropriately aligned within the door handle 13.

[0060] As an example, IC 30 may include the radar transceiver of the radar sensor 23, a digital signal processing (DSP) component and a control device of the radar sensor. In addition, IC 30, which may be designed as a CMOS circuit, typically includes further components, such as a filter, a power IC, a memory device (such as a flash memory) and an interface for coupling the radar sensor 23 to a bus system of the motor vehicle.

[0061] The radar sensor 23 serves the purpose of emitting radar beams by means of the antenna arrangement 31. If there is an object in the surroundings of this radar sensor 23, at least part of the radiation emitted by the radar sensor 23 is reflected by this object, and may be picked up as echo radiation by means of the antenna arrangement 31. The echo radiation recorded in this way is pre-processed accordingly in IC 30.

[0062] The functionality of the evaluation device 24 may, for example, be performed by a corresponding control unit for the respective side door, or may be performed by a central control unit of the vehicle. The evaluation device 24 may also be implemented in a program-controlled device, such as a microcomputer, microprocessor, and so on.

[0063] The method according to the present disclosure, as explained above with reference to FIGS. 1 to 2, is primarily carried out by the radar sensor 23 and by the evaluation device 24, whereas the radar sensor 23 primarily carries out the process steps S1, S2, and whereas the evaluation device 24 primarily carries out the process steps S3, S4, S5.

[0064] Although the present disclosure has been fully described above on the basis of preferred exemplary embodiments, the present invention is not limited thereto, but can be modified in a variety of ways.

[0065] The following is a list of reference numbers shown in the Figures. However, it should be understood that the use of these terms is for illustrative purposes only with respect to one embodiment. And, use of reference numbers correlating a certain term that is both illustrated in the Figures and present in the claims is not intended to limit the claims to only cover the illustrated embodiment.

LIST OF REFERENCE NUMERALS

[0066] 10 Feature vector determined by measurement

[0067] 11 First feature vector for an ideal pole

[0068] 12 Second feature vector for an ideal wall

[0069] 20 Vehicle

[0070] 21 Vehicle door system

[0071] 22 Door

[0072] 23 Radar sensor

[0073] 24 Evaluation device

[0074] 25 Transmitting device

[0075] 26 Receiving device

[0076] 27 Door handle

[0077] 28 Cover

[0078] 29 Exterior mirror

[0079] 30 Semiconductor circuit, IC

[0080] 31 Antenna arrangement

[0081] 32 Transmitting antennas

[0082] 33 Receiving antennas

[0083] 34 Antenna elements

[0084] D1 Weighted Euclidean distance for comparison with an ideal pole

[0085] D2 Weighted Euclidean distance for comparison with an ideal wall

[0086] S1-S5 Process steps

[0087] D Distance

[0088] While exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms of the invention. Rather, the words used in the specification are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the invention. Additionally, the features of various implementing embodiments may be combined to form further embodiments of the invention.