Method for classifying at least one object according to height

Abstract

It is proposed a method for classifying at least one object according to an object height on the basis of data of an ultrasonic signal reflected by the object, the method comprising the steps of: receiving data of a reflected ultrasonic signal; determining a first sum value, wherein the first sum value is a sum of values or power values of the reflected ultrasonic signals in a first preset range near a global maximum value of the reflected ultrasonic signals; determining a second sum value, wherein the second sum value is a sum of values or power values of the reflected ultrasonic signals in a second preset range immediately upstream of the first preset range; determining a third sum value, wherein the third sum value is the sum of the values or the power values of the reflected ultrasonic signals in a third preset range close to the downstream of the first preset range; determining a first difference value based on a difference generated from the third sum value and the first sum value; determining a second difference value based on a difference generated from the second sum value and the first sum value; and classifying the at least one object into one of the at least two height categories based on the first difference and the second difference.

Description

Field of the Invention

[0001] The present invention relates to a method for classifying at least one object according to the height of the object. Background Art

[0002] The height of an object can be determined by means of ultrasonic signals, or the object can be classified according to its height.

[0003] In the prior art, in a method for classifying an object according to height by means of reflected ultrasonic waves, one maximum value or a plurality of maximum values of the reflected ultrasonic wave signals are observed. An object that at least partially extends upward beyond the height position of the ultrasonic transmitter / ultrasonic receiver is identified based on two local maximum values of the ultrasonic wave signals reflected by the object. However, especially in the case of outdoor motor vehicles, this kind of identification or classification is unreliable.

[0004] Other possible solutions for classifying an object according to the height of the object by means of the reflected ultrasonic waves are to classify the object by means of a neural network, that is, to analyze the ultrasonic wave signals reflected by the object by means of a neural network. However, its disadvantage is that the neural network must be trained individually, especially depending on the installation height of the ultrasonic receiver. Summary of the Invention

[0005] The object underlying the present invention is to provide a method for classifying at least one object according to height, which is technically simple and reliable.

[0006] In particular, this object is achieved by a method for classifying at least one object according to the height of the object based on data of ultrasonic signals reflected by the object, wherein the method comprises the following steps: receiving data of the reflected ultrasonic signals; determining a first sum value, wherein the first sum value is the sum of the values of the ultrasonic signals reflected in a first preset range near the global maximum value of the reflected ultrasonic signals, or the first sum value is the sum of the power values of the ultrasonic signals reflected in a first preset range near the global maximum value of the reflected ultrasonic signals; determining a second sum value, wherein the second sum value is the sum of the values of the ultrasonic signals reflected in a second preset range immediately upstream of the first preset range, or the second sum value is the sum of the power values of the ultrasonic signals reflected in a second preset range immediately upstream of the first preset range; determining a third sum value, wherein the third sum value is the sum of the values of the ultrasonic signals reflected in a third preset range immediately downstream of the first preset range, or the third sum value is the sum of the power values of the ultrasonic signals reflected in a third preset range immediately downstream of the first preset range; determining a first difference based on the difference, in particular a weighted difference, generated by the third sum value and the first sum value; determining a second difference based on the difference, in particular a weighted difference, generated by the second sum value and the first sum value; and classifying the at least one object into one of at least two height categories based on the first difference and the second difference, in particular based on the signs of the first difference and the second difference.

[0007] The advantage here is that the method is technically simple or can be carried out using fewer technical resources. This particularly means that only a small computational effort is required to carry out the method. Therefore, the method can be carried out with inexpensive hardware. In addition, the method or classification is very reliable. In addition, the method operates independently of the installation height or position height of the ultrasonic transmitter / ultrasonic receiver, that is to say, the method does not have to be specifically adapted to the height of the ultrasonic transmitter / ultrasonic receiver.

[0008] This object is particularly achieved by a computer program product having instructions readable by a processor of a computer, which instructions, when executed by the processor, cause the processor to carry out the above method. This object is particularly also achieved by a computer-readable medium on which such a computer program is stored.

[0009] This object is achieved in particular by an evaluation device for evaluating ultrasonic signals reflected by an object, wherein the evaluation device is designed to - receive data of the reflected ultrasonic signals, - determine a first sum value, where the first sum value is the sum of the values of the reflected ultrasonic signals within a first preset range near the global maximum of the reflected ultrasonic signals, or the first sum value is the sum of the power values of the reflected ultrasonic signals within a first preset range near the global maximum of the reflected ultrasonic signals, - determine a second sum value, where the second sum value is the sum of the values of the reflected ultrasonic signals within a second preset range immediately upstream of the first preset range, or the second sum value is the sum of the power values of the reflected ultrasonic signals within a second preset range immediately upstream of the first preset range, - determine a third sum value, where the third sum value is the sum of the values of the reflected ultrasonic signals within a third preset range immediately downstream of the first preset range, or the third sum value is the sum of the power values of the reflected ultrasonic signals within a third preset range immediately downstream of the first preset range, - determine a first difference based on the difference, in particular a weighted difference, generated by the third sum value and the first sum value, - determine a second difference based on the difference, in particular a weighted difference, generated by the second sum value and the first sum value, and - classify the at least one object into one of at least two height categories based on the first difference and the second difference, in particular based on the signs of the first difference and the second difference.

[0010] Advantageously, the evaluation device can be technically designed to be simple and cost - effective. In particular, the evaluation device only requires low computing power. In addition, the evaluation device can perform the classification reliably and correctly. Another advantage is that the evaluation device does not have to be specifically adapted to the installation height of the ultrasonic transmitter / ultrasonic receiver.

[0011] The above object is achieved by a system that includes the above - mentioned evaluation device, an ultrasonic transmitter for sending ultrasonic signals in the direction of the object, and an ultrasonic receiver for receiving the ultrasonic signals reflected by the object and for transmitting the data of the reflected ultrasonic signals to the evaluation device.

[0012] The above object is also achieved by a motor vehicle having the above - mentioned system.

[0013] According to an embodiment of the method, the third sum value is multiplied by a preset factor when determining the first difference, and / or the second sum value is multiplied by a preset factor when determining the second difference. The advantage here is that the classification can be precisely set in this way. That is, the preset factor can determine when to classify or categorize an object into the first category (e.g., a tall object) and when to classify or categorize the same object into a different second category (e.g., a short object).

[0014] According to an embodiment of the method, when both the first difference and the second difference have a negative sign, at least one object is classified as an object that is substantially completely below the height of the ultrasonic receiver for the reflected ultrasonic signal. Thereby, an object that is substantially completely below the height position of the ultrasonic receiver for the reflected ultrasonic signal can be technically simply and reliably classified as such an object. In addition, the object is reliably and correctly classified thereby.

[0015] According to an embodiment of the method, when the first difference has a positive sign or the second difference has a positive sign, the at least one object is classified as an object that is at least partially above the height of the ultrasonic receiver for the reflected ultrasonic signal. Advantageously here, an object (such as a wall or the like) that is at least partially above the height position of the ultrasonic receiver for the reflected ultrasonic signal can be technically simply and reliably classified into the corresponding class or category, or classified as such an object. In addition, the classification of these objects is particularly reliable thereby.

[0016] According to an embodiment of the method, when the first difference has a positive sign and the second difference has a positive sign, the at least one object is classified as an object having a plurality of reflecting surfaces. In this way, an object having a plurality of different surfaces for reflecting the ultrasonic signal is also reliably classified into its own category. Thereby, a so-called complex object, i.e., an object having a plurality of different reflecting surfaces, can be reliably and technically simply classified as such an object.

[0017] According to an embodiment of the method, additional sensor information about the object, in particular visual sensor information, is taken into account in the step of classifying the object. Thereby, in particular in the case of an object having a plurality of reflecting surfaces for the ultrasonic signal, it can be reliably determined whether the object has a height greater than a preset height. In this way, for example, in a motor vehicle, it can be determined whether the object can be driven over by the motor vehicle (without significant expected damage). The additional sensor information can come from, for example, a camera, a lidar device, etc. The recognition unit can summarize the additional information with the classification by means of the ultrasonic signal and make a decision regarding the height of the object.

[0018] According to an embodiment of the method, the ultrasonic signal comprises or is a linear ultrasonic signal having a rising frequency or a falling frequency, in particular a continuously rising frequency or a continuously falling frequency. Advantageously here, the local maxima of the reflected ultrasonic signal can be particularly clearly distinguished from each other. In this way, the classification can be carried out more reliably.

[0019] Furthermore, according to an embodiment of the method, a probability index is determined based on the sum value, and the probability index illustrates the reliability of the classification of the at least one object that has been performed. Advantageously herein, the method not only performs the classification of the height of the object, but also outputs the reliability of the classification as a probability index. Therefore, the clarity or definiteness of the decision regarding the classification can be estimated.

[0020] According to an embodiment of the method, when the sign of the first difference is negative and the sign of the second difference is positive, the at least one object is classified as an object that extends almost up to the height of the ultrasonic receiver that reflects the ultrasonic signal. The advantage herein is that an object that extends to just below the height of the ultrasonic receiver can be clearly or distinctly distinguished from an object whose upper end is significantly lower than the height position of the ultrasonic receiver and an object whose upper end is significantly higher than the height position of the ultrasonic receiver.

[0021] According to an embodiment of the method, the method further includes the following steps: determining a fourth sum value, where the fourth sum value is the sum of the values of the ultrasonic signals reflected in a fourth preset range near the local maximum of the reflected ultrasonic signal, or the fourth sum value is the sum of the power values of the ultrasonic signals reflected in a fourth preset range near the local maximum of the reflected ultrasonic signal, where the fourth preset range is located after the first preset range; determining a fifth sum value, where the fifth sum value is the sum of the values of the ultrasonic signals reflected in a fifth preset range immediately upstream of the fourth preset range, or the fifth sum value is the sum of the power values of the ultrasonic signals reflected in a fifth preset range immediately upstream of the fourth preset range; determining a sixth sum value, where the sixth sum value is the sum of the values of the ultrasonic signals reflected in a sixth preset range immediately downstream of the fourth preset range, or the sixth sum value is the sum of the power values of the ultrasonic signals reflected in a sixth preset range immediately downstream of the fourth preset range; determining a third difference based on the difference, especially the weighted difference, generated by the sixth sum value and the fourth sum value; determining a fourth difference based on the difference, especially the weighted difference, generated by the fifth sum value and the fourth sum value; wherein, based on the first difference, the second difference, the third difference, and the fourth difference, the step of classifying the at least one object into one of at least two height categories is performed. The advantage herein is that multiple objects can be classified independently of each other, or a complex object with multiple reflecting surfaces can be reliably classified as such an object. Advantageously herein, a complex object, i.e., an object with multiple reflecting surfaces, can be reliably classified.

[0022] "Classifying the height of at least one object" can in particular be understood as determining whether the height of the object belongs to a first category or a second category of heights (or to other categories if necessary). This means that the height of the object is not or does not have to be determined absolutely or precisely, but only whether the height of the object is above or below a first threshold (and if necessary above or below other thresholds). Thus, for example, in the case of two classification categories, it only has to be determined whether the height of the object is greater than or less than the threshold that differentiates the two categories from each other.

[0023] "The height of the object" can in particular be understood as the relative height with respect to the ultrasonic transmitter / ultrasonic receiver or its height position. This means that the absolute height (above the ground or the like) does not have to be determined, but the height of the object relative to the height of the ultrasonic transmitter / ultrasonic receiver can be determined. However, it is conceivable that "the height of the object" is understood as the absolute height of the object above the ground.

[0024] "The sum of the values of the ultrasonic signals reflected in a first preset range around the global maximum of the reflected ultrasonic signals" can in particular refer to the area below the ultrasonic signals reflected in this range. Alternatively, the sum of the squares of the signal values of the ultrasonic signals reflected in this range can be calculated, where the sum of the squares of the measured values corresponds to the energy of the ultrasonic signals reflected in this range. The "range around the global maximum" can extend symmetrically or asymmetrically partly from the maximum in a first direction (e.g., with respect to the propagation time of the signal) and partly from the maximum in a second direction opposite to the first side (e.g., with respect to the propagation time of the signal). It can be said that a specific part before and after the maximum is added to the position of the maximum in order to form the first preset range.

[0025] The ultrasonic signals can in particular be transmitted using an ultrasonic receiver / ultrasonic transmitter system and the reflected ultrasonic signals can be received using this ultrasonic receiver / ultrasonic transmitter system. The ultrasonic transmitter can thus act as an ultrasonic receiver at the same time, or the ultrasonic transmitter can also receive the reflected ultrasonic waves.

[0026] "According to the height of the object" can in particular be understood as determining whether the position up to which the object extends is below the position of the ultrasonic receiver-ultrasonic transmitter system that transmits and receives the ultrasonic signals, or whether the position to which the object extends is above the ultrasonic receiver-ultrasonic transmitter system. Thus, "according to the height of the object" can in particular be the relative height with respect to the height position of the ultrasonic receiver-ultrasonic transmitter system that transmits and receives the ultrasonic signals.

[0027] "Height" can in particular be understood as the position of the uppermost point of an object or the surface of the object, i.e., the position of the point of the object that is furthest from, for example, the ground or the road.

[0028] "A second preset range immediately upstream of the first preset range" can in particular be understood as a range that contains the ultrasonic waves reflected by an object or a part of the object, and the reflecting surface of the object or the part of the object is closer to the ultrasonic transmitter / ultrasonic receiver than the reflecting surface of the object whose reflected ultrasonic waves are in the first preset range. The reflected ultrasonic waves from an object or a reflecting surface that is closer to the ultrasonic transmitter / ultrasonic receiver than an object or a reflecting surface that is further away have a shorter propagation time and are thus in a second range upstream (in terms of time) of the first preset range where the global maximum is located.

[0029] "A third preset range immediately downstream of the first preset range" can in particular be understood as a range that contains the reflected ultrasonic waves received from an object or the reflecting surface of the object, and the reflected ultrasonic waves are further away from the ultrasonic transmitter / ultrasonic receiver than the reflected ultrasonic waves in the first preset range where the global maximum is located. Therefore, the ultrasonic waves have a longer propagation time in the third preset range and the third range is immediately downstream of the first range in terms of time. This means that the reflected ultrasonic waves received in the third range are received later than the reflected ultrasonic waves received in the first preset range.

[0030] "A third preset range immediately downstream of the first preset range" can in particular be understood as a range that contains the reflected ultrasonic waves received from an object or the reflecting surface of the object, and the object or the reflecting surface of the object is further away from the ultrasonic transmitter / ultrasonic receiver than the object or the reflecting surface of the object whose reflected ultrasonic waves are in the first preset range where the global maximum is located.

[0031] The term "upstream" can in particular be understood such that the propagation time of the signal or measurement value of the reflected ultrasonic wave signal in a range is shorter than the propagation time of the signal in the "downstream" range. Therefore, the signal or measurement value in the upstream range comes from a reflecting surface closer to the ultrasonic receiver, and the signal or measurement value in the downstream range comes from a reflecting surface further away from the ultrasonic receiver. Description of the Drawings

[0032] Preferred embodiments are derived from the dependent claims. The present invention will be explained in more detail below based on the drawings of exemplary embodiments. In the drawings:

[0033] Figure 1 A schematic diagram showing an exemplary first embodiment of a motor vehicle according to the present invention;

[0034] Figure 2 A schematic diagram showing the ultrasonic wave signal emitted when the object is not tall or is short;

[0035] Figure 3 A schematic diagram showing the ultrasonic signal reflected in the case of the Figure 2 object shown;

[0036] Figure 4 A schematic diagram showing the ultrasonic signal in the case of a higher object;

[0037] Figure 5 A schematic diagram showing the ultrasonic signal reflected in the case of the Figure 4 object shown;

[0038] Figure 6 A schematic diagram showing the ultrasonic signal in the case of an object of medium height;

[0039] Figure 7 A schematic diagram showing the ultrasonic signal reflected in the case of the Figure 6 object shown;

[0040] Figure 8 A schematic diagram showing the ultrasonic signal in the case of a complex object; and

[0041] Figure 9 A schematic diagram showing the ultrasonic signal reflected in the case of the Figure 8 object shown. DETAILED DESCRIPTION

[0042] In the following description, the same reference numerals are used for the same and functionally identical parts.

[0043] Figure 1 A schematic diagram showing an exemplary first embodiment of a motor vehicle 10 according to the present invention is shown.

[0044] The motor vehicle 10 includes a system 20, which in turn has an ultrasonic transmitter for transmitting an ultrasonic signal 35 and an ultrasonic receiver 30 for receiving the reflected ultrasonic signal 37 and for transmitting data to an evaluation device 25. The ultrasonic transmitter can act as the ultrasonic receiver 30.

[0045] Furthermore, the motor vehicle 10 or the system 20 includes an evaluation device 25 for evaluating the reflected ultrasonic signal 37, the reflected ultrasonic signal being received by the ultrasonic receiver 30 and the data of the reflected ultrasonic signal being transmitted to the evaluation device 25.

[0046] The system 20 can be a parking assistance device or an alarm assistance device for the motor vehicle 10.

[0047] The following method is performed in the motor vehicle 10 or the system 20.

[0048] First, an ultrasonic transmitter transmits or emits an ultrasonic signal 35. The ultrasonic signal 35 can be a linear chirp signal, i.e., a linear ultrasonic signal with a continuously increasing frequency (positive chirp) or a linear ultrasonic signal with a continuously decreasing frequency (negative chirp).

[0049] The ultrasonic signal 35 is reflected by the surface of the object 40 and / or the ground 45, and the reflected ultrasonic signal 37 is received by the ultrasonic receiver 30. The received reflected ultrasonic signal 37 or the data of the received reflected ultrasonic signal 37 is transmitted by the ultrasonic receiver 30 to the evaluation device 25 and evaluated by the evaluation device 25. The evaluation device 25 classifies or categorizes at least one object 40 according to or based on the height in at least two different categories.

[0050] This method classifies one or more objects 40 (such as objects located near a vehicle) according to or based on or in accordance with the height of the object. The object 40 is classified into at least one of two categories according to its determined height: 1. The object 40 is a tall object, that is, the height of the object 40 extends (significantly) above the height at which the ultrasonic transmitter / ultrasonic receiver 30 is arranged. 2. The object 40 is a non-tall object, that is, the object 40 does not extend to the height at which the ultrasonic transmitter / ultrasonic receiver 30 is arranged.

[0051] To perform this classification, the reflected ultrasonic signal 37 (echo) or its data is analyzed or evaluated.

[0052] Figure 2 A schematic diagram of the ultrasonic signal 35 in the case where the object is non-tall or short is shown. Figure 3 Shown in Figure 2 A schematic diagram of the reflected ultrasonic signal 37 in the case of the object 40 shown.

[0053] Figure 2 The object 40 in [[ ]] can be, for example, a curbstone, a low curb (such as at a garage entrance), etc. The ultrasonic transmitter / ultrasonic receiver 30 is significantly higher than the upper edge of the object 40, that is, the height position of the ultrasonic transmitter / ultrasonic receiver 30 is significantly higher than the upper edge of the object 40. The short object 40 is about 10 cm high, while the ultrasonic transmitter / ultrasonic receiver 30 is arranged at a height of about 50 cm or about 80 cm above the ground 45.

[0054] In [[ ]] Figure 2 the height of the object 40 extends from bottom to top.

[0055] In [[ ]] Figure 3 a time curve or the distance between the corresponding reflecting surface and the ultrasonic transmitter / ultrasonic receiver 30 is depicted on the x-axis, and the intensity of the signal or the corresponding measured value is depicted on the y-axis.

[0056] In this method, within a preset range 50 near the global maximum, the values of the reflected ultrasonic signals 37 are added together. This means that the area under the curve of the reflected ultrasonic signals 37 near the global maximum is determined or calculated. This sum or area is the first sum value. Alternatively, the first sum value can be generated by adding the powers (such as squares) of the measured values within the range 50 near the local maximum or global maximum. The sum of the squares of the measured values corresponds to the energy within this first range 50.

[0057] In Figure 3 , the first range 50 or the measured values within the first range 50 are marked with asterisks as measurement points. In Figure 3 , the first range 50 includes 12 measured values.

[0058] A second range 60 is arranged immediately before (and thus directly adjacent to) the first range 50. The second sum value is generated by adding the measured values within this second range 60. This corresponds to the area under the curve of the measured values within the second range 60. Alternatively, the squares of the measured values within the second range 60 can be added to generate the second sum value. The measured values within the second range 60 are marked with circles in Figure 3 In Figure 3 , the second range 60 includes 19 measured values.

[0059] A third range 70 is arranged immediately after (and thus directly adjacent to) the first range 50. The third sum value is generated by adding the measured values within the third range 70. This corresponds to the area under the curve of the measured values within the third range 70. Alternatively, the squares of the measured values within the third range 70 can be added to generate the third sum value. The measured values within the third preset range 70 are marked with crosses in Figure 3 In Figure 3 , the third range 70 has 20 measured values.

[0060] The first range 50 can be arranged symmetrically around the maximum value. This means that the global maximum is located at the center of the first range 50. However, it is also conceivable that the first range 50 is arranged asymmetrically with respect to the maximum value.

[0061] The first range 50 can, for example, include the maximum value, five measured values immediately upstream of the maximum value, and five measured values immediately downstream of the maximum value in time.

[0062] The widths of the first range 50, the second range 60, and the third range 70 can be of the same magnitude. For example, the widths can be 1.5 times or 2 times that of the first range 50, respectively. However, it is conceivable that the magnitude of the first range 50 is half that of the second range 60 and half that of the third range 70. The magnitude of the second range 60 or the third range 70 can also be three times that of the first range 50, respectively.

[0063] The widths of the different ranges 50, 60, 70 can be determined empirically.

[0064] Now, the three sum values are related to each other. Subsequently, they are compared with a threshold value.

[0065] A first difference is generated by multiplying the third sum value by a first preset factor and subtracting the first sum value therefrom:

[0066] First difference = first preset factor * third sum value - first sum value.

[0067] The first preset factor determines when the first difference has a positive sign and when it has a negative sign. Therefore, the threshold or threshold value for classifying the object 40 as tall, medium height, or short or not tall can be determined therefrom.

[0068] A second difference is generated by multiplying the second sum value by a second preset factor and subtracting the first sum value therefrom:

[0069] Second difference = second preset factor * second sum value - first sum value.

[0070] The second preset factor can be the same as the first preset factor. It is conceivable that the two factors are different.

[0071] The first preset factor and the second preset factor are set or selected such that the signs of the first difference and the second difference of the corresponding object are obtained in the following manner.

[0072] The first preset factor or the second preset factor can be in the range starting from approximately 3, especially when the sums themselves are added.

[0073] If the powers (such as squares) of the measured values are added, the first preset factor or the second preset factor can be in the range of approximately 12 to 20, for example, 16.

[0074] Now, classification is performed based on the signs of the first difference and the second difference.

[0075] When the first difference has a negative sign and the second difference has a negative sign, the object 40 is classified as a low or short or not tall object.

[0076] When the first difference has a positive sign or the second difference has a positive sign, object 40 is classified as a high object. The "or" can be an "exclusive or".

[0077] When the first difference has a positive sign and the second difference has a positive sign, object 40 is classified as a complex object. A complex object has multiple reflecting surfaces and thus does not have a single or simple geometric structure.

[0078] In Figure 2 a shorter object 40 (e.g., a curbstone) is shown, i.e., an object 40 whose upper end (apparently) lies below the ultrasonic transmitter / ultrasonic receiver 30. In Figure 3 it can be seen that the echo or the reflected ultrasonic signal 37 consists essentially of a main signal or peak or echo signal in a first range 50 that is substantially entirely near the global maximum. Thus, the signs of the first difference and the second difference are negative and object 40 is classified as a low or short or not-high object.

[0079] Figure 4 A schematic diagram of the ultrasonic signal 35 in the case where the object is higher is shown. Figure 5 Shown in Figure 4 is a schematic diagram of the reflected ultrasonic signal 37 in the case of the object 40 shown in

[0080] Object 40 extends significantly beyond the height at which the ultrasonic transmitter / ultrasonic receiver 30 is arranged. Object 40 can be, for example, a house wall or a pipe or a duct.

[0081] The reflected ultrasonic signal 37 or echo has a relatively high direct maximum / echo and subsequently, in time, has a smaller signal or local maximum or echo generated by the corner reflector (object 40 / ground 45).

[0082] In this case, the first difference has a positive sign or the second difference has a positive sign.

[0083] Figure 6 A schematic diagram of the ultrasonic signal 35 in the case where the object is of medium height is shown. Figure 7 Shown in Figure 6 is a schematic diagram of the reflected ultrasonic signal 37 in the case of the object 40 shown in

[0084] The object of medium height extends up to just below the height at which the ultrasonic transmitter / ultrasonic receiver 30 is located. Here, the main sound lobe of the transmitted ultrasonic signal 35 sweeps across the upper edge of object 40, which results in a small but distinct echo or local maximum that is (in time) upstream of the absolute maximum.

[0085] In this way, objects extending to a height slightly below or just below the ultrasonic transmitter / ultrasonic receiver 30 (e.g., up to about 10 cm below this height) can be classified into their own category.

[0086] In this case, the second difference has a negative sign and the first difference has a positive sign.

[0087] Figure 8 A schematic diagram of the ultrasonic signal 35 in the case of a complex object is shown. Figure 9 Shown in Figure 8 A schematic diagram of the reflected ultrasonic signal 37 in the case of the object 40 shown.

[0088] The complex object has multiple reflecting surfaces (at different distances) for the ultrasonic signal 35. Shown in Figure 8 is a bush, but the complex object can also be the front or rear of a vehicle (e.g., a sedan or a motorcycle), a person, an animal, etc.

[0089] In the case of a complex object, there is an absolute maximum of the signal. The first difference has a negative sign and the second difference has a negative sign. The first range 50 is arranged near the absolute maximum of the signal. In addition, there is a significantly prominent local maximum, which is almost as high as the absolute maximum although it is outside the first range 50, the second range 60, and the third range 70. Outdoors or in the open air, the maximum value can change continuously.

[0090] The fourth range 80 is arranged near the right local maximum (overall the third highest value). The sixth range 82 is arranged immediately after the fourth range 80 and the fifth range 81 is arranged immediately before the fourth range 80.

[0091] According to the generation method of the first sum value, the second sum value, and the third sum value, a fourth sum value, a fifth sum value, and a sixth sum value are generated by means of the fourth range 80, the fifth range 81, and the sixth range 82. This means that: the fourth sum value is generated by adding the measured values in the fourth range 80; the fifth sum value is generated by adding the measured values in the fifth range 81; the sixth sum value is generated by adding the measured values in the sixth range 82.

[0092] Subsequently, according to the generation method of the first difference and the second difference, a third difference and a fourth difference are generated:

[0093] Third difference = preset factor * sixth sum value - fourth sum value,

[0094] Fourth difference = preset factor * fifth sum value - fourth sum value.

[0095] Subsequently, classification of the object 40 is performed according to the signs of the third difference and the fourth difference, where the same sign combination rule as for the first difference and the second reference value also applies to this classification.

[0096] That is to say, the signal can be said to be divided into two sections and the respective global maximum values are determined in these two sections. Then, the differences between these two sections are independent of each other. These two sections can overlap with each other.

[0097] It can be said that after the third range 70 or to the right of the third range 70, the signal or the global peak or the global maximum value is set to zero again and the global maximum value is determined again.

[0098] When the sign of the first difference or (especially exclusively or) the sign of the second difference is positive in the first section and the sign of the third difference or (especially exclusively or) the sign of the fourth difference is positive, a complex object is considered to exist, that is, an object having different reflecting surfaces for the ultrasonic transmitter / ultrasonic receiver 30.

[0099] The classification result of the object 40 can be output to a person and / or a data interface.

[0100] In Figure 9 the third range 70 and the fifth range 81 partially overlap; in these ranges 70, 81, the measurement points are marked with circles and crosses.

[0101] Combined with Figures 2 to 7 the method described above can be executed twice. Here, the ranges (along the x-axis) for executing the combined Figures 2 to 7 the method described above can overlap. For example, in Figure 9 the third range 70 overlaps with the fifth range 81. This means that the complex object extends over a long range or has reflecting surfaces at different distances from the ultrasonic transmitter / ultrasonic receiver 30, so that the method has to be executed twice, where for the two runs or executions of the combined Figures 2 to 7 the method described above, there are assumed to be two different absolute maximum values (in two different parts along the x-axis).

[0102] In this method, a probability index can be determined or output. The probability index P represents the reliability or credibility of correctly classifying the object 40 into the corresponding category. The probability index can be a number between 0 and 1. The probability index can be determined by the Sigmoid function:

[0103] P = sigmoid(β * ((α * First difference / Second difference) - 1))

[0104] where

[0105] α is a factor that is multiplied by the first sum value and / or the third sum value when generating the corresponding differences, and

[0106] β is a preset number that makes the P value fall between 0 and 1.

[0107] The ultrasonic signal 35 can be an ultrasonic signal with a rising frequency.

[0108] In addition, the motor vehicle 10 can have a camera 90, such as a rearview camera. The classification of the evaluation device 25 can be combined with the data or images of the camera 90, and the higher-level recognition unit can perform a reliable recognition of the object height by means of the classification and the camera data. In particular, the recognition unit can determine whether the motor vehicle 10 can drive over the object 40 without damage. If the object cannot be driven over by the motor vehicle 10 without expected damage, the recognition unit can output a warning signal and / or brake the motor vehicle 10.

[0109] The first preset factor or the second preset factor can be, for example, in the range of approximately 3 to approximately 4, especially when the sum itself is added.

[0110] The second reference value can be the second difference.

[0111] List of reference numerals

[0112] 10 Motor vehicle

[0113] 20 System

[0114] 25 Evaluation device

[0115] 30 Ultrasonic transmitter / ultrasonic receiver

[0116] 35 Transmitted ultrasonic signal

[0117] 37 Reflected ultrasonic signal

[0118] 40 Object

[0119] 45 Ground

[0120] 50 First range

[0121] 60 Second range

[0122] 70 Third range

[0123] 80 Fourth range

[0124] 81 Fifth range

[0125] 82 Sixth range

[0126] 90 Camera

Claims

1. A method for classifying at least one object (40) according to the height of the object (40) based on data of an ultrasonic signal (37) reflected by the object (40), wherein: The method comprises the following steps: receiving data of the reflected ultrasonic signal (37); Determining a first sum value, wherein the first sum value is the sum of the values ​​of the ultrasonic signal (37) reflected in a first preset range (50) around the global maximum value of the reflected ultrasonic signal (37), or the first sum value is the sum of the power values ​​of the ultrasonic signal (37) reflected in a first preset range (50) around the global maximum value of the reflected ultrasonic signal (37); Determining a second sum value, wherein the second sum value is the sum of the values ​​of the ultrasonic signals (37) reflected in a second preset range (60) immediately upstream of the first preset range (50), or the second sum value is the sum of the power values ​​of the ultrasonic signals (37) reflected in the second preset range (60) immediately upstream of the first preset range (50); Determining a third sum value, wherein the third sum value is the sum of the values ​​of the ultrasonic signals (37) reflected in a third preset range (70) immediately downstream of the first preset range (50), or the third sum value is the sum of the power values ​​of the ultrasonic signals (37) reflected in the third preset range (70) immediately downstream of the first preset range (50); determining a first difference value based on a difference, in particular a weighted difference, generated from the third sum value and the first sum value; determining a second difference value based on a difference, in particular a weighted difference, generated from the second sum value and the first sum value; and Based on the first difference value and the second difference value, in particular based on the signs of the first difference value and the second difference value, the at least one object (40) is classified into one of at least two height categories.

2. The method according to claim 1, wherein: The third sum value is multiplied by a preset factor when determining the first difference value, and / or the second sum value is multiplied by a preset factor when determining the second difference value.

3. The method according to claim 1 or 2, wherein: When both the first difference value and the second difference value have a negative sign, the at least one object (40) is classified as an object substantially completely below the height of the ultrasonic receiver (30) of the reflected ultrasonic signal (37).

4. The method according to any one of the preceding claims, wherein: When the first difference value has a positive sign or the second difference value has a positive sign, the at least one object (40) is classified as an object at least partially above the height of the ultrasonic receiver (30) of the reflected ultrasonic signal (37).

5. The method according to any one of the preceding claims, wherein: When the first difference value has a positive sign and the second difference value has a positive sign, the at least one object (40) is classified as an object having multiple reflective surfaces.

6. The method according to any one of the preceding claims, wherein: In the step of classifying the object (40), additional sensor information, in particular visual sensor information, about the object (40) is taken into account.

7. The method according to any one of the preceding claims, wherein: The ultrasonic signal comprises or is a linear ultrasonic signal having a rising or falling frequency, in particular a continuously rising or continuously falling frequency.

8. The method according to any one of the preceding claims, wherein: A probability index is further determined based on the sum value, which probability index indicates the reliability of the classification of the at least one object (40) that has been performed.

9. The method according to any one of the preceding claims, wherein: If the sign of the first difference is negative and the sign of the second difference is positive, the at least one object (40) is classified as an object extending almost to the height of the ultrasonic receiver (30) of the reflected ultrasonic signal (37).

10. The method according to any of the preceding claims, wherein: The method further comprises the following steps: Determining a fourth sum value, wherein the fourth sum value is the sum of the values ​​of the ultrasonic signal (37) reflected in a fourth preset range (82) near the local maximum value of the reflected ultrasonic signal (37), or the fourth sum value is the sum of the power values ​​of the ultrasonic signal (37) reflected in a fourth preset range (82) near the local maximum value of the reflected ultrasonic signal (37), wherein the fourth preset range (82) is located after the first preset range (50); Determining a fifth sum value, wherein the fifth sum value is the sum of the values ​​of the ultrasonic signals (37) reflected in a fifth preset range (81) immediately upstream of the fourth preset range (80), or the fifth sum value is the sum of the power values ​​of the ultrasonic signals (37) reflected in the fifth preset range (81) immediately upstream of the fourth preset range (80); Determining a sixth sum value, wherein the sixth sum value is the sum of the values ​​of the ultrasonic signals (37) reflected in a sixth preset range (82) immediately downstream of the fourth preset range (80), or the sixth sum value is the sum of the power values ​​of the ultrasonic signals (37) reflected in the sixth preset range (82) immediately downstream of the fourth preset range (80); determining a third difference value based on a difference, in particular a weighted difference, generated from the sixth sum value and the fourth sum value; and determining a fourth difference value based on a difference, in particular a weighted difference, generated from the fifth sum value and the fourth sum value, in, Based on the first difference, the second difference, the third difference and the fourth difference, a step of classifying the at least one object (40) into one of at least two height categories is performed.

11. A computer program product having instructions readable by a processor of a computer, which instructions, when executed by the processor, cause the processor to perform the method according to one of the preceding claims.

12. A computer readable medium having stored thereon a computer program product according to claim 11.

13. An evaluation device (25) for evaluating an ultrasonic signal (37) reflected by an object (40), wherein: The evaluation device (25) is designed to: - data for receiving the reflected ultrasonic signal (37); - for determining a first sum value, wherein the first sum value is the sum of the values ​​of the ultrasonic signal (37) reflected in a first preset range (50) around the global maximum value of the reflected ultrasonic signal (37), or the first sum value is the sum of the power values ​​of the ultrasonic signal (37) reflected in a first preset range (50) around the global maximum value of the reflected ultrasonic signal (37), - used to determine a second sum value, wherein the second sum value is the sum of the values ​​of the ultrasonic signals (37) reflected in a second preset range (60) immediately upstream of the first preset range (50), or the second sum value is the sum of the power values ​​of the ultrasonic signals (37) reflected in the second preset range (60) immediately upstream of the first preset range (50), - used to determine a third sum value, wherein the third sum value is the sum of the values ​​of the ultrasonic signals (37) reflected in a third preset range (70) immediately downstream of the first preset range (50), or the third sum value is the sum of the power values ​​of the ultrasonic signals (37) reflected in the third preset range (70) immediately downstream of the first preset range (50), for determining a first difference value based on a difference, in particular a weighted difference, generated from the third sum value and the first sum value, for determining a second difference value based on a difference, in particular a weighted difference, generated from the second sum value and the first sum value, and - for classifying the at least one object (40) into one of at least two height categories based on the first difference and the second difference, in particular based on the signs of the first difference and the second difference.

14. A system (20), comprising: An evaluation device (25) according to claim 13; an ultrasonic transmitter for transmitting an ultrasonic signal (35) in the direction of an object (40); as well as An ultrasonic receiver (30) for receiving an ultrasonic signal (37) reflected by the object (40) and for transmitting data of the reflected ultrasonic signal (37) to the evaluation device (25).

15. A motor vehicle (10) comprising a system (20) according to claim 14.

Images