Method for supporting camera-based environmental recognition of a means of transport using road wetness information from a first ultrasonic sensor

Abstract

Method for supporting camera-based environmental detection of a means of transport (80) by means of road wetness information from a first ultrasonic sensor (30) comprising the steps: • Detection (100) of a first signal representing an environment (60) of the means of transport (80) by means of the first ultrasonic sensor (30) of the means of transport (80), • Capturing (200) a second signal representing the environment (60) of the means of transport (80) by means of a camera (40) of the means of transport (80), • Determining (300) the road wetness information based on the first signal, wherein the road wetness information is determined by comparing a noise level (70) of the first signal with a speed-dependent predefined threshold (75) for a noise level (70), • Selecting (400) a predefined parameter set from a plurality of predefined parameter sets depending on the road wetness information, wherein the plurality of predefined parameter sets represent different configurations for a classifier which is set up to analyze an environment of the means of transport based on the second signal and to detect objects in this environment, and • Performing (500) an environment detection based on the second signal in conjunction with the predefined parameter set.

Description

State of the art

[0001] The present invention relates to a method for supporting camera-based environmental detection of a means of transport using road wetness information from a first ultrasonic sensor.

[0002] State-of-the-art means of transportation are known that perform camera-based environment recognition to obtain information about objects in the vehicle's surroundings. This information is received and used, for example, by driver assistance systems and / or systems for autonomous control of the vehicle. Such environment recognition is based on state-of-the-art algorithms for image analysis and object classification, which typically employ one or more classifiers for specific objects.

[0003] Furthermore, rain sensors for vehicles for detecting the presence of precipitation are known from the prior art. These are usually located in the upper area of ​​a vehicle's windshield and are designed to detect precipitation on the windshield. Wetness information obtained by such a rain sensor can be used to select suitable classifiers for environment detection.

[0004] Furthermore, ultrasonic sensors are known from the prior art, which are often used in conjunction with vehicles for parking assistance systems or similar driver assistance systems. For this purpose, such ultrasonic sensors are usually arranged on the vehicle in such a way that their radiation and detection direction is essentially horizontal to the vehicle, in order to be able to determine the distances of objects in the vicinity of the vehicle from the vehicle based on the signal propagation times of the ultrasonic signals.

[0005] The document DE 10 2016 103 251 A1 discloses a method for operating at least one sensor for detecting the surroundings of a vehicle.

[0006] The document DE 10 2016 122 987 A1 discloses a method for predictively determining a risk of aquaplaning for a motor vehicle.

[0007] The document DE 10 2015 106 408 A1 discloses a sensor arrangement for detecting a condition of a roadway with an ultrasonic sensor.

[0008] The document DE 10 2013 226 631 A1 discloses a method for determining local weather conditions and a local road condition.

[0009] The document DE 10 2006 037 591 A1 discloses a device for detecting a moving object. Disclosure of the invention

[0010] According to a first aspect of the present invention, a method is proposed for supporting camera-based environmental detection of a means of transport using road wetness information from a first ultrasonic sensor. The means of transport can be, for example, a road vehicle (e.g., motorcycle, car, van, truck), a rail vehicle, an aircraft, or a watercraft. Furthermore, the method steps described below can be carried out entirely or partially by a device according to the invention of the means of transport. The device can comprise an evaluation unit, which preferably has a data input. The evaluation unit can be configured, for example, as an ASIC, FPGA, processor, digital signal processor, microcontroller, or similar, and can be connected for information technology purposes to an internal and / or external storage unit.The evaluation unit can furthermore be configured to carry out the method according to the invention in conjunction with a computer program executed by the evaluation unit.

[0011] In a first step of the method according to the invention, a first signal representing the surroundings of the means of transport is detected by means of the first ultrasonic sensor of the means of transport. The ultrasonic sensor can be an ultrasonic sensor of the means of transport that is also used / can be used for other purposes. Alternatively or additionally, a dedicated ultrasonic sensor can also be used for the method according to the invention. The ultrasonic sensor of the means of transport can, for example, be an ultrasonic sensor of a parking assistance system or another driver assistance system of the means of transport. The ultrasonic sensor can, for example, be arranged in a front apron or in the region of a rear of the means of transport or at other positions on the means of transport, so that both the tire noise and the road ahead or behind and their surroundings can be detected.Furthermore, the ultrasonic sensor can be connected directly or indirectly (i.e., for example, via another control unit of the vehicle) to the data input of the evaluation unit according to the invention. The connection can be established, for example, via a bus system (e.g., CAN, LIN, MOST, Ethernet, etc.) of an on-board network of the vehicle. The first signal from the first ultrasonic sensor received by the evaluation unit can initially be stored in the memory unit connected to the evaluation unit for subsequent processing by the evaluation unit.

[0012] In a second step of the method according to the invention, a second signal representing the surroundings of the means of transport is recorded by a camera of the means of transport. The second signal can preferably be recorded at a substantially identical time as the first signal, so that it can be ensured that the two signals each contain surroundings information that corresponds to one another in time. Due to different sensor types and different signal processing and signal transmission chains, a time offset can occur between the two signals. A preferred range of a time offset between the two signals, which however is not necessarily ensured for the method according to the invention, can be, for example, between a few milliseconds and a few hundred milliseconds, or even in the range of seconds.The camera can, for example, be a 2D or 3D camera with a standard image resolution, an HD or Ultra HD image resolution, or an infrared camera. The camera can preferably be arranged and aligned on the means of transport in such a way that it captures the surroundings ahead of the means of transport. However, such an arrangement and / or alignment of the camera is not limited to this example. Analogous to the first ultrasonic sensor, the camera can be directly or indirectly connected via information technology to the evaluation unit according to the invention via the on-board network of the means of transport. In a preferred embodiment of the present invention, the camera can be connected via information technology to an image processing unit of the means of transport, which is configured to receive image signals from the camera and to process them. Such an image processing unit can, among other things,Component of a driver assistance system or a system for autonomous driving of the means of transport. Furthermore, in this preferred embodiment, the image processing unit can be connected to the evaluation unit according to the invention via information technology, so that the evaluation unit can transmit the road wetness information described in more detail below to the image processing unit. Alternatively or in addition to this embodiment, the image processing unit can be a component of the evaluation unit itself (or vice versa), so that communication between these two components can take place directly and not via the on-board electrical system of the means of transport. This can be implemented, for example, in such a way that logic to be executed by the evaluation unit according to the invention for implementing the method steps according to the invention is executed in the form of a computer program by means of the image processing unit.

[0013] In a third step of the method according to the invention, the road wetness information is determined based on the first signal. For this purpose, the evaluation unit according to the invention compares a noise level of the first signal with a speed-dependent (see original claim 3) predefined threshold value for a noise level, which can be stored in the memory unit connected to the evaluation unit. The predefined threshold value for a noise level is preferably selected such that if the noise level exceeds the predefined threshold value, it can be assumed that the road surface is currently wet. Conversely, if the noise level falls below the predefined threshold value, it can be assumed that the road surface is dry. A result of the determination of the road wetness information can in turn be stored in the memory unit.Alternatively, or in addition to simply distinguishing between a wet and a dry road surface, the evaluation unit can also estimate the degree of wetness if the noise level of the first signal exceeds the predefined threshold by taking into account the extent to which the noise level of the first signal exceeds the predefined threshold. Furthermore, it is also conceivable to use a plurality of predefined thresholds for a noise level, whereby the respective predefined thresholds can correspond to different speeds and / or speed ranges of the means of transport.In other words, it may be advantageous for the evaluation unit to receive information about a current speed of the vehicle provided via the vehicle's on-board electrical system, so that the evaluation unit can select a corresponding, predefined threshold value from a plurality of predefined threshold values ​​depending on a current speed value, since a higher speed is generally associated with a higher noise level in the first signal. This can prevent the evaluation unit from falsely detecting road wetness at a higher speed of the vehicle, even though the road surface is actually dry.

[0014] In a fourth step of the method according to the invention, a predefined parameter set is selected from a plurality of predefined parameter sets depending on the road wetness information. According to the invention, the plurality of predefined parameter sets represents, for example, different configurations for a classifier which is set up to analyze an environment of the means of transport on the basis of the second signal and to recognize objects in this environment. Such a classifier can preferably be part of a computer program which is executed by the image processing unit and / or the evaluation unit. In the event that the evaluation unit according to the invention and the image processing unit are implemented as separate components, the selection of the predefined parameter set by the image processing unit can be carried out depending on the road wetness information and possibly further information (e.g.about a speed of the means of transport), which can be made available by the evaluation unit via the on-board network of the means of transport. One aim of using different predefined parameter sets is to use predefined parameter sets for environment recognition that are adapted to a current environment (i.e. wet or dry). The reason for this is that a classifier trained for a dry environment can generally only ensure inadequate or unreliable results in the course of environment recognition in a wet environment, for example due to water being stirred up (spray) by vehicles traveling ahead. Conversely, a classifier trained for a wet environment can often not deliver optimal recognition results in a dry environment.In the event that the wetness information provided by the evaluation unit contains information about a wetness degree in addition to a pure wet / dry distinction, a predefined parameter set tailored to the respective measuring degree can be selected depending on the wetness degree.

[0015] In a fifth step of the method according to the invention, environment detection is performed based on the second signal in conjunction with the predefined parameter set. Since adapted, predefined parameter sets can be used for environment detection based on the available wetness information, the detection performance of the environment detection can be optimized accordingly. The resulting increased reliability of the environment detection can, in turn, lead to greater safety when using the means of transport.

[0016] The subclaims show preferred developments of the invention.

[0017] In an advantageous embodiment of the present invention, the road wetness information can additionally be determined depending on a speed and / or acceleration and / or engine speed of the vehicle. The advantageous consideration of a current speed when determining current road wetness information has already been described in detail above. Analogously, values ​​received via the vehicle's electrical system regarding a current acceleration and / or current engine speed of the vehicle can be advantageously considered in a similar manner.

[0018] In a further advantageous embodiment of the present invention, the predefined parameter set can represent a configuration of a trained, self-learning system. This means that the classifier described above can be implemented on the basis of a self-learning system, such as a neural network (e.g., with a deep learning structure). Furthermore, other types of self-learning systems can also be used. In this way, using such a self-learning system, training runs of the vehicle can be carried out in different wet conditions, and the respective trained configurations of the self-learning system can be stored in the form of different predefined parameter sets.

[0019] In a further advantageous embodiment of the present invention, the predefined parameter set can be selected alternatively or additionally depending on a change in the noise level and / or a current temperature and / or a quantity of water present in the vicinity of the vehicle. A change in the noise level can, as described above, be caused by varying amounts of water on a road surface. Furthermore, a change in the noise level can also be caused by a change in the distance to vehicles ahead. In both cases, it may be expedient to use appropriately adapted parameter sets for surroundings detection due to the associated changes in visibility conditions.A distinction as to whether a change in the noise level is caused by a change in the amount of water or by changes in the distance of vehicles ahead can be made by additionally analyzing the second signal, for example by determining a change in the size of vehicles immediately ahead. Alternatively or additionally, signals from other environmental sensors of the vehicle can also be used to assess a current situation. In this case, it can be particularly advantageous to take into account distance information about vehicles ahead from a LIDAR and / or a radar system of the vehicle. The predefined parameter sets generated and used for the above-mentioned cases can ensure that vehicles partially obscured by a cloud of spray are detected better and / or more quickly, even if the camera can only capture vague outlines of vehicles ahead.

[0020] Furthermore, it may be useful to consider the current outside temperature when selecting the predefined parameter set, since an outside temperature below 4 °C and especially below 0 °C allows for a conclusion about the potential presence of snow at the edge of the road and / or on the road itself. The probability that snow is present at least at the edge of the road can be particularly high if the outside temperature is 0 °C or below and, at the same time, road wetness is detected. Based on this information, another suitable predefined parameter set can be selected and used during environment detection, so that, for example, a road boundary can be reliably detected even in the presence of snow.

[0021] In a further advantageous embodiment of the present invention, the road wetness information can be determined depending on the freedom from interference of the first signal. Freedom from interference here is understood to mean the absence of a wide variety of interfering influences that make reliable road wetness detection difficult or even impossible, such as buildings along the roadside and / or other means of transport in the immediate vicinity of the means of transport. Such interfering influences can be determined, for example, based on the second signal or on signals from other environmental sensors, such as LIDAR and / or radar sensors. In the event that such an interfering influence is present, the evaluation unit can transmit road wetness information to the image processing unit that represents the road wetness condition prior to the occurrence of the interfering influence.This value can be used preferentially by the overall system as road wetness information until the interfering influence(s) in the vehicle's environment have disappeared. This advantageously avoids temporary interfering influences, as their brief appearance and disappearance do not lead to undesirably frequent changes in the road wetness information. This, in turn, prevents undesirably frequent changes to the predefined parameter sets.

[0022] As already described above, the first ultrasonic sensor can be arranged on the means of transport such that a detection range of the first ultrasonic sensor lies in the direction of travel or opposite to the direction of travel of the means of transport. Furthermore, the surroundings of the means of transport can be additionally detected on the basis of a second ultrasonic sensor and in particular detected by a second ultrasonic sensor which is arranged on the means of transport such that a detection range of the second ultrasonic sensor lies in the direction of travel or opposite to the direction of travel of the means of transport. In a preferred variant, for example, the first ultrasonic sensor can be aligned in the direction of travel and the second ultrasonic sensor opposite to the direction of travel of the means of transport.In this way, the road wetness information can be determined based on both ultrasonic sensors, thereby enabling additional plausibility checks of the road wetness information obtained from the respective first signals. Alternatively, the road wetness information can be determined alternately based on the first or on the second ultrasonic sensor by evaluating the first signal from the ultrasonic sensor with regard to road wetness that has the lowest proportion of interference at a current time. In this context, it should be noted that, in addition to the first and second ultrasonic sensors, further ultrasonic sensors can be used for the method according to the invention. This means that, for example, third, fourth and more ultrasonic sensors can be used, which can be combined and used analogously to the embodiments described above.An arrangement of the first, second, third, fourth and possibly further ultrasonic sensors is explicitly not limited to the front and / or rear area of ​​the means of transport.

[0023] In a further advantageous embodiment of the present invention, the road wetness information determined from the first signal can be verified for plausibility by road wetness information determined from the second signal. This can be done based on an analysis of reflections from light sources in the camera image, for example, by checking whether these light sources are above or apparently below road surface level. Furthermore, the road wetness information can also be verified for plausibility by additional sensors and / or control units of the vehicle. Examples of suitable sensors include a rain sensor arranged on a windshield of the vehicle, or even additional sensors of the vehicle.

[0024] Information about objects in the vicinity of the vehicle determined by the environment recognition can then be transmitted to, among other things, a driver assistance system and / or a system for autonomous control of the vehicle and used there.

[0025] According to a second aspect of the present invention, a device is proposed for supporting camera-based environmental detection of a means of transport using road wetness information from a first ultrasonic sensor. The device comprises an evaluation unit and a data input. The evaluation unit can be configured, for example, as an ASIC, FPGA, processor, digital signal processor, microcontroller, or similar, and can be connected to an internal and / or external storage unit for information technology purposes. The evaluation unit can also be configured to carry out the method according to the invention in conjunction with a computer program executed by the evaluation unit.Furthermore, the evaluation unit is configured, in conjunction with the data input, to detect a first signal, determined by the first ultrasonic sensor of the means of transport, representing the surroundings of the means of transport, and to detect a second signal, determined by a camera of the means of transport, representing the surroundings of the means of transport. The ultrasonic sensor can preferably be an existing ultrasonic sensor of the means of transport. Furthermore, the ultrasonic sensor can be arranged, for example, in a front apron or in the area of ​​a rear of the means of transport, or at other positions on the means of transport, so that either the road ahead or the road behind and their surroundings can be detected. The camera can, for example, be a 2D or 3D camera with a standard image resolution, an HD or an ultra-HD image resolution, or an infrared camera.Preferably, the camera can be arranged and aligned on the vehicle such that the camera can capture the surroundings ahead of the vehicle. The evaluation unit can be directly and / or indirectly connected to the ultrasonic sensor and the camera via an on-board electrical system of the vehicle. Furthermore, the evaluation unit is configured to determine road wetness information based on the first signal, select a predefined parameter set from a plurality of predefined parameter sets depending on the road wetness information, and perform surroundings detection based on the second signal in conjunction with the predefined parameter set. Short description of the drawings

[0026] Embodiments of the invention are described in detail below with reference to the accompanying drawings. Fig. 1 is a flowchart illustrating steps of an embodiment of a method according to the invention; Fig. 2 a block diagram of a device according to the invention in connection with a means of transport; and Fig. 3 a diagram of a speed-dependent noise level of a first ultrasonic sensor. Embodiments of the invention

[0027] Fig. 1 shows a flowchart illustrating steps of an embodiment of a method according to the invention for supporting camera-based environmental detection of a means of transport 80 using road wetness information from a first ultrasonic sensor 30. In the first step 100, a first signal representing an environment 60 of the means of transport 80 is detected by means of the first ultrasonic sensor 30 of the means of transport 80 using an evaluation unit 10 according to the invention, which is a microcontroller. The first ultrasonic sensor 30 is arranged in a front apron of the means of transport 80 and oriented in the direction of travel of the means of transport 80. The evaluation unit 10 receives the first signal via a data input 12 of the evaluation unit 10 and stores environmental information represented by the first signal in an internal memory unit 20 of the microcontroller.In step 200, a second signal representing the surroundings 60 of the means of transport 80 is captured by a camera 40 of the means of transport 80. The camera 40 is arranged in an interior of the means of transport 80 in an upper region of a windshield of the means of transport 80 and is aligned such that the camera 40 can capture the surroundings 60 ahead of the means of transport 80. The second signal from the camera 40 is received by an image processing unit of the means of transport 80, which is connected to the camera 40 for information purposes. The first signal from the ultrasonic sensor 30 and the second signal from the camera 40 are captured at essentially the same time. In step 300, road wetness information is determined based on the first signal using a computer program executed by the evaluation unit 10.For this purpose, the evaluation unit 10 compares a noise level 70 of the first signal with a predefined threshold value 75 for a noise level 70. If the noise level 70 exceeds the predefined threshold value 75, this indicates the presence of wet road conditions in the surroundings 60 of the means of transport 80. Since, in this case, wet road conditions are detected based on the predefined threshold value 75, the evaluation unit 10 sends a corresponding signal, which includes the current wet road condition information, to the image processing unit via a vehicle bus of an on-board electrical system of the means of transport 80. In step 400 of the method according to the invention, the image processing unit selects a predefined parameter set from a plurality of predefined parameter sets depending on the received wet road condition information.The parameter set selected by the image processing unit in this case represents a configuration of a neural network-based classifier that was trained at an earlier point in time (e.g., during a development phase of the vehicle 80) under similar wet road conditions. Subsequently, in step 500, the image processing unit performs environment recognition based on the second signal in conjunction with the predefined parameter set. Information about objects in the environment 60 of the vehicle 80 determined by the environment recognition is then transmitted to a system for autonomously controlling the vehicle 80 via the vehicle's electrical system, and used by the system in the course of the autonomous control of the vehicle 80.

[0028] Fig. 2 shows a block diagram of a device according to the invention in connection with a means of transport 80. The device comprises an evaluation unit 10, which here is a microcontroller and has a data input 12. By means of the data input 12, the evaluation unit 10 is connected for information purposes via an on-board network of the means of transport 80 to a first ultrasonic sensor 30 oriented in the direction of travel of the means of transport 80 and to a second ultrasonic sensor 35 oriented opposite to the direction of travel. The evaluation unit 10 is also connected for information purposes via the on-board network of the means of transport 80 to a camera 40 oriented in the direction of travel of the means of transport 80 via the data input 12.Furthermore, the evaluation unit 10 is connected for information technology purposes to an external storage unit 20, which is configured to store information received by the evaluation unit 10 for subsequent processing by the evaluation unit 10. By means of the first ultrasonic sensor 30, the second ultrasonic sensor 35 and the camera 40, the evaluation unit 10 is able to capture an environment 60 of the means of transport 80 at essentially identical times. In this example, all steps of the method according to the invention are carried out in the evaluation unit 10 itself, i.e.that the evaluation unit 10 is not only configured to determine road wetness information on the basis of first signals from the first ultrasonic sensor 30 and the second ultrasonic sensor 35, but is also configured to select a predefined parameter set corresponding to the road wetness information and to carry out environmental detection by means of the predefined parameter set on the basis of a second signal from the camera 40.

[0029] Fig.3 shows a diagram of a speed-dependent noise level 70 of a first ultrasonic sensor 30. In a first phase P1 of the diagram, a means of transport 80, which uses the first ultrasonic sensor 30 in accordance with the method according to the invention, travels at a speed v that corresponds to a predefined threshold value 75 of the first phase P1. In other words, due to an initially relatively low speed v of the means of transport 80 in the first phase P1, the predefined threshold value 75 from a plurality of predefined threshold values ​​75 is used for a comparison with the noise level 70 of the first signal, which was previously defined for this speed range. Since the noise level 70 in the first phase P1 is completely above the predefined threshold value 75 of the first phase P1, an evaluation unit 10 according to the invention detects the presence of road wetness.The curve of the speed v shows that the speed v of the means of transport 80 continues to increase over time. When a speed value v1 is reached, a predefined threshold value 75 for a second phase P2 is selected by means of the evaluation unit 10 due to the now higher speed v. This results in the predefined threshold value 75 of the second phase P2 being adapted to the noise level 75 generated by the higher speed v. As in the first phase P1, existing road wetness is again initially detected here, since the noise level 70 at the beginning of the second phase P2 is above the predefined threshold value 75 of the second phase P2.At a time t1 in the second phase P2, the noise level curve 70 drops to such an extent that it falls below the predefined threshold value 75 of the second phase P2. In response, the evaluation unit 10 detects a dry road surface.

Claims

[1] Method for supporting camera-based environmental detection of a means of transport (80) by means of road wetness information from a first ultrasonic sensor (30), comprising the steps: • detecting (100) a first signal representing an environment (60) of the means of transport (80) by means of the first ultrasonic sensor (30) of the means of transport (80), • detecting (200) a second signal representing the environment (60) of the means of transport (80) by means of a camera (40) of the means of transport (80), • Determining (300) the road wetness information on the basis of the first signal, wherein the road wetness information is determined by comparing a noise level (70) of the first signal with a speed-dependent predefined threshold value (75) for a noise level (70), • selecting (400) a predefined parameter set from a plurality of predefined parameter sets depending on the road wetness information, wherein the plurality of predefined parameter sets represent different configurations for a classifier which is configured to analyze an environment of the means of transport on the basis of the second signal and to recognize objects in this environment, and • Carrying out (500) an environment detection based on the second signal in conjunction with the predefined parameter set. [2] The method of claim 1, wherein the first signal and the second signal are detected at a substantially identical time. [3] Method according to one of the preceding claims, wherein the determination (300) of the road wetness information is additionally carried out in dependence • a speed, and / or • an acceleration, and / or • an engine speed of the means of transport (80). [4] Method according to one of the preceding claims, wherein the predefined parameter set represents a configuration of a trained, self-learning system. [5] Method according to one of the preceding claims, wherein the selection (400) of the predefined parameter set is alternatively or additionally carried out in dependence • a change in the noise level (70), and / or • a current outside temperature and / or • a quantity of water present in the environment (60) of the means of transport (80). [6] Method according to one of the preceding claims, wherein the determination (300) of the road wetness information is carried out as a function of the freedom from interference of the first signal. [7] Method according to one of the preceding claims, wherein the first ultrasonic sensor (30) is arranged on the means of transport (80) in such a way that a detection range of the first ultrasonic sensor (30) lies in the direction of travel or opposite to the direction of travel of the means of transport (80). [8] Method according to one of the preceding claims, wherein the surroundings (60) are additionally detected on the basis of a second ultrasonic sensor (35) which is arranged on the means of transport (80) in such a way that a detection range of the second ultrasonic sensor (35) lies in the direction of travel or opposite to the direction of travel of the means of transport (80). [9] Method according to one of the preceding claims, wherein the road wetness information determined from the first signal is verified by road wetness information determined from the second signal. [10] Device for supporting camera-based environmental detection of a means of transport (80) by means of road wetness information from a first ultrasonic sensor (30), comprising: • an evaluation unit (10), and • a data input (12), wherein the evaluation unit (10) is set up, • in connection with the data input (12) ◯ detecting a first signal determined by means of the first ultrasonic sensor (30) of the means of transport (80) representing an environment (60) of the means of transport (80), ◯ to detect a second signal determined by means of a camera (40) of the means of transport (80) representing the environment (60) of the means of transport (80), • to determine road wetness information on the basis of the first signal, wherein the road wetness information is determined by comparing a noise level (70) of the first signal with a speed-dependent predefined threshold value (75) for a noise level (70), • to select a predefined parameter set from a plurality of predefined parameter sets depending on the road wetness information, wherein the plurality of predefined parameter sets represent different configurations for a classifier which is configured to analyze an environment of the means of transport on the basis of the second signal and to recognize objects in this environment, and • to carry out environmental detection based on the second signal in conjunction with the predefined parameter set.

Images