Method for classifying heights of objects by means of ultrasonic sensor technology
A method for classifying the height of an object by means of at least one ultrasonic sensor of a vehicle is disclosed. The method includes emitting an ultrasonic signal by the ultrasonic sensor of the vehicle in a transmission cycle; and performing a reception cycle, wherein the reception cycle has a reception time window which makes it possible to receive echoes having a transit time which corresponds to at least double a reception range of the ultrasonic sensor. It is checked whether echoes were received in the reception cycle. A detected object is classified in a height class depending on whether at least a first and a second echo were received, wherein the transit time of the second echo is an integer multiple of the transit time of the first echo.
1 . A method for classifying the height of an object by means of at least one ultrasonic sensor of a vehicle, comprising the following steps:
emitting an ultrasonic signal by the ultrasonic sensor of the vehicle in a transmission cycle;
performing a reception cycle, wherein the reception cycle has a reception time window which makes it possible to receive echoes having a transit time which corresponds to at least double a reception range of the ultrasonic sensor;
checking whether at least a first and a second echo were received in the reception cycle, wherein the transit time of the second echo corresponds to an integer multiple of the transit time of the first echo;
classifying a detected object in a height class depending on whether at least a first and a second echo were received, wherein the transit time of the second echo is an integer multiple of the transit time of the first echo,
wherein one of
(a) the vehicle has a computer which, in addition to the height class tion method as a first method, provides at least one further, second method for classifying heights, and the height according to the second method is classified based on a weighted combination of classification results of the first meth the seco method, or
(b) based on probability values which indicate a probability that a current driving situation of the vehicle is to be assigned to a determined capturing scenario, a probability is calculated that an object is to be classed in a determined height and, based on a sum of conditional ability values, wherein the conditional probability values each indicates how high the probability is that the object is to be classed in a determined height category on a condition that a determined capturing scenario exists.
2 . The method according to claim 1 , wherein an object is classified as a high object if a second echo was identified, the transit time of which corresponds to an integer multiple of the transit time of the first echo, wherein a high object has at least a height equal to a vertically measured height at which the ultrasonic sensor is provided on the vehicle.
3 . The method according to claim 1 , wherein an object is classified as a low object if no second echo was identified, the transit time of which corresponds to an integer multiple of the transit time of the first echo, wherein a low object has a height smaller than the vertically measured height at which the ultrasonic sensor is provided on the vehicle.
4 . The method according to claim 1 , wherein, in the event that at least three echoes are received in the reception cycle, wherein the transit time of the second echo is an integer multiple of the first echo and the third echo has a transit time which is not a common multiple of the transit time of the first echo, two objects are detected, wherein a first object which is assigned to the first and second echo is classified as a high object and a second object which is assigned to the third echo is classified as a low object.
5 . The method according to claim 4 , further comprising checking whether the first and second object have the same azimuth angle with respect to the ultrasonic sensor.
6 . The method according to claim 1 , wherein the one of (a) or (b) is (a).
7 . The method according to claim 6 , wherein a machine learning method is used in order to at least one of establish weighting factors or modify the weighting factors after the weighting factors have been established in order to carry out the weighted combination of the classification results of the first and second method, based on the weighting factors.
8 . The method according to claim 6 , further comprising initially determining a capturing scenario depending on a current driving situation and, based on the established capturing scenario, selecting at least one further height classification method based on which a height classification is possible in the established capturing scenario.
9 . The method according to claim 1 , wherein the one of (a) or (b) is (b).
10 . A system for classifying a height of an object, comprising at least one ultrasonic sensor and a computer unit which is configured to evaluate the information provided by the ultrasonic sensor, wherein the system is configured to execute the following:
emitting an ultrasonic signal by the ultrasonic sensor of a vehicle in a transmission cycle;
performing a reception cycle, wherein the reception cycle has a reception time window which makes it possible to receive echoes having a transit time which corresponds to at least double the reception range of the ultrasonic sensor;
checking whether at least a first and a second echo were received in the reception cycle, wherein the transit time of the second echo corresponds to an integer multiple of the transit time of the first echo; and
classifying a detected object in a height class depending on whether at least a first and a second echo were received, wherein the transit time of the second echo is an integer multiple of the transit time of the first echo,
wherein one of
(a) the vehicle has a computer which, in addition to the height classification method as a first method, provides at least one further, second method for classifying heights, and the height according to the second method is classified based on a weighted combination of classification results of the first method and the second method, or
(b) based on probability values which in rate a probability bat a current driving situation of the vehicle is to be assigned to a determined capturing scenario, a probability is calculated that an object is to be classed in a determined height category and, based on a sum of conditional probability values, wherein the conditional probability each indicates how high the probability is that the object is to be classed in a determined height category on a condition that a determined capturing scenario exists.
11 . The system according to claim 10 , wherein the computer unit is configured to classify an object as a high object if a second echo was identified, the transit time of which corresponds to an integer multiple of the transit time of the first echo, wherein a high object has at least a height equal to a vertically measured height at which the ultrasonic sensor is provided on the vehicle.
12 . The system according to claim 10 , wherein the computer unit is configured to classify an object as a low object if no second echo was identified, the transit time of which corresponds to an integer multiple of the transit time of the first echo, wherein a low object has a height smaller than a vertically measured height at which the ultrasonic sensor is provided on the vehicle.
13 . The system according to claim 10 , wherein the computer unit is configured to detect two objects, in the event that at least three echoes are received in the reception cycle, wherein the transit time of the second echo is an integer multiple of the first echo and the third echo has a transit time which is not a common multiple of the transit time of the first echo, wherein a first object which is assigned to the first and second echo is classified as a high object and a second object which is assigned to the third echo is classified as a low object.
14 . The system according to claim 13 , wherein the computer unit is configured to additionally verify whether the first and second object have the same azimuth angle with respect to the ultrasonic sensor.
15 . A vehicle comprising a system according to claim 10 .
16 . The system according to claim 10 , wherein a machine learning method is used in order to at least one of establish weighting factors or modify the weighting factors after the weighting factors have been established in order to carry out the weighted combination of the classification results of the first and second method, based on the weighting factors.
17 . The system according to claim 10 , further comprising initially determining a capturing scenario depending on a current driving situation and, based on the established capturing scenario, selecting at least one further height classification method based on which a height classification is possible in the established capturing scenario.
18 . The system according to claim 10 , wherein the one of (a) or (b) is (b).
19 . The system according to claim 10 , wherein the one of (a) or (b) is (a).