Classification of static and dynamic objects

Abstract

A method classifies dynamic or static objects in a surrounding area with a control device. Sound echoes are generated by at least one sensor over a defined time period. The sound echoes are emitted into the surrounding area, and are detected by the at least one sensor in order to acquire measurement data. The measurement data of the at least one sensor are received by the control device. The received measurement data are recorded in a two-dimensional array. At least one echo trace is extracted from the array. A relative speed of the detected sound echoes with respect to the at least one sensor is determined using a derivative over time of the measurement data of the array. The at least one echo trace is classified based on the determined relative speed.

Claims

1. A method for classifying dynamic or static objects in a surrounding area, comprising: generating sound signals with at least one sensor over a defined time period, the generated sound signals emitted into the surrounding area; detecting sound echoes, based on sound signals, with the at least one sensor in order to generate measurement data, the sound echoes reflected by an object in the surrounding area; receiving the measurement data with a control device operably connected to the at least one sensor; recording the received measurement data in a two-dimensional array; extracting at least one echo trace from the two-dimensional array, the at least one echo trace based on the object; determining a relative speed of the object with respect to the at least one sensor using a derivative over time of the at least one echo trace; and classifying the object as either a dynamic object or a static object based on the determined relative speed.

2. The method according to claim 1, further comprising: calculating an absolute speed of the object based on a speed of the at least one sensor relative to the object.

3. The method according to claim 2, further comprising: classifying the object as the static object when the calculated absolute speed is zero.

4. The method according to claim 3, further comprising: classifying the object as the dynamic object when the calculated absolute speed is non-zero.

5. The method according to claim 1, further comprising: receiving information from an object detection process; and filtering the measurement data based on the received information.

6. The method according to claim 1, further comprising: storing the two-dimensional array at least temporarily in a short-term memory and/or a long-term memory.

7. The method according to claim 1, wherein: the control device is arranged in a mobile unit, and control commands configured to actuate the mobile unit are generated based on the classification of the object.

8. The method according to claim 1, wherein the control device is configured to carry out the method.

9. The method according to claim 1, wherein a computer program comprises commands which, during execution of the computer program by a computer or the control unit, causes the computer or the control unit to carry out the method.

10. The method according to claim 9, wherein a machine-readable storage medium is configured to store the computer program.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

(1) In the text which follows, preferred exemplary embodiments of the disclosure are explained in more detail on the basis of highly simplified schematic illustrations, in which:

(2) FIG. 1 shows a schematic illustration of a vehicle with a control device for carrying out a method according to one embodiment,

(3) FIG. 2 shows schematic illustrations of two-dimensional arrays which are produced from measurement data from different sensors,

(4) FIG. 3 shows a schematic illustration of a combined array composed of arrays shown in FIG. 1, and

(5) FIG. 4 shows a schematic flow chart of a method according to one embodiment.

DETAILED DESCRIPTION

(6) FIG. 1 shows a schematic illustration of a mobile unit 1 which is configured as a vehicle and has a control device 2 for carrying out a method 4 (see FIG. 4) according to one embodiment.

(7) The vehicle 1 or the mobile unit is configured as a vehicle which can be operated in an automated fashion and has, for example, a multiplicity of sensors 6, 8. The sensors 6, 8 are configured as ultrasonic sensors and are arranged at different positions on the vehicle 1.

(8) The sensors 6, 8 are coupled in a data-conducting fashion to the control device 2, so that the control device 2 can receive and evaluate the measurement data of the sensors 6, 8.

(9) The received measurement data of the sensors 6, 8 can be at least temporarily stored, for example, in the control device 2 or in a machine-readable storage medium 10.

(10) The machine-readable storage medium 10 is connected to the control device 2 and has a computer program which can be executed by the control device 2. Through the execution of the computer program, the control device 2 can be used to carry out the method 4.

(11) FIG. 2 shows schematic illustrations of two-dimensional arrays 12 which are produced from measurement data of different sensors 6, 8. The raw measurement data of sound signals can be used for the further processing of the measurement data by the control device 2.

(12) The illustrations show schematic views of the measurement data of the sensors 6, 8 which represent a measurement of a distance d over a time t. All the sound echoes for each sensor 6, 8 are then recorded in a two-dimensional array 12 over a time period.

(13) FIG. 3 is a schematic illustration of a combined array 14 composed of arrays 12 which are shown in FIG. 2. In this context, all the measurement data of the sensors 6, 8 are combined in the array 14. In particular an echogram with a distance d plotted over a time t is illustrated.

(14) The measurement data of the sensors 6, 8 can be acquired here from direct echoes of the respective sensors 6, 8 or from cross echoes from the sensors 6, 8. The measurement data which is illustrated in the two-dimensional array 14 shows that an object or a surface is approaching at least one sensor 6, 8 and subsequently maintains its distance d from the sensor 6, 8.

(15) The respective sections of the measurement data can be described by means of echo traces 16, 17. The echo traces 16, 17 correspond to acoustic energy which is reflected back to the sensor 6, 8 from a surface (not denoted in more detail) and is represented visually in the echogram. The echo traces 16, 17 can be determined or approximated, for example, by a linear regression. In particular, the differentiation between “static” and “dynamic” can be made on the basis of the gradient of the echo traces 16, 17.

(16) The gradient of a first echo trace 16 is zero or infinite, so that a static object can be classified here.

(17) The second exemplary echo trace 17 has a gradient which differs from zero and which corresponds to a speed. Such an echo trace 17 can be used to define a dynamic classification.

(18) FIG. 4 shows a schematic flow chart of a method 4 according to one embodiment. The method 4 serves to classify dynamic or static objects in a surrounding area of the vehicle 1 by means of the control device 2.

(19) In a step 20, measurement data of sound echoes are received by the sensors 6, 8 over a defined time period t. The time period t can be, for example, 1 to 60 seconds. The measurement data of the sensors 6, 8 can result from direct echoes or from cross echoes here.

(20) The received measurement data is recorded 21 in a two-dimensional array 12, 14.

(21) Subsequently, in a further step 22, echo traces 16, 17 are extracted from the arrays 12, 14.

(22) A relative speed of the received sound echoes with respect to the sensors 6, 8 can be determined 23 by means of a derivation over time of the measurement data or of the arrays 12, 14 of the sensors 6, 8.

(23) In an optional step 24, an absolute speed of the object corresponding to the echo traces 16, 17 is formed.

(24) Subsequently, a classification of the echo traces 16, 17 as “static” or as “dynamic” is performed 25 by means of the control device 2.