Method for calibrating sensor information of a vehicle and driver assistance system

Abstract

Method for calibrating sensor information of a vehicle (1), wherein the vehicle (1) has at least one sensor (2) of a first sensor type and at least one sensor (3) of a second sensor type different from the first sensor type, the method comprising the following steps: - detecting the environment while the vehicle (1) is traveling by at least one sensor (2) of the first sensor type and providing first sensor information by this sensor (2) of the first sensor type (S10); - detecting the surroundings while the vehicle (1) is traveling by at least one sensor (3) of the second sensor type and providing second sensor information by this sensor (3) of the second sensor type (S11); - Creating a first three-dimensional representation of environmental information from the first sensor information (S 12); - Creating a second three-dimensional representation of environmental information from the second sensor information (S13); - comparing the first and second three-dimensional representation of environmental information or information derived therefrom (S14); - determining deviations between the first and second three-dimensional representation of environmental information or information derived therefrom (S15); - Calculating correction information for calibration parameters of at least one sensor based on the determined deviations (S16); - Calibrating the sensors (2, 3) of the vehicle (1) relative to each other based on the calculated correction information (S17).

Description

[0001] The invention relates to a method for online calibration of sensor information of a vehicle and a driver assistance system.

[0002] For autonomous driving, the most reliable possible perception of the surroundings is essential. The surroundings are recorded using various types of sensors, such as at least one radar sensor, one or more cameras, and preferably also at least one LIDAR sensor. A holistic 360° 3D recording of the environment is preferred, so that all static and dynamic objects in the vehicle's surroundings can be detected.

[0003] To ensure reliable environmental detection, precise calibration of the sensors is essential. Continuous monitoring of the calibration status of the sensor systems and, if necessary, recalibration during the journey are essential for highly automated driving functions, as otherwise a failure of the autonomous driving function would result.

[0004] In existing methods, sensors are calibrated individually relative to a fixed point on the vehicle, but the entire set of sensors is not calibrated relative to each other. This has the disadvantage that the precision required for automatic driving functions often cannot be achieved.

[0005] The publication DE 10 2015 118 874 A1 discloses, among other things, a system for calibrating a sensor system of a motor vehicle. Several sensors of the sensor system are calibrated under steady-state calibration conditions in a test bench equipped with several calibration objects.

[0006] The document DE 10 2009 006 113 A1 discloses a device and a method for sensor fusion with dynamic objects.

[0007] Based on this, it is the object of the invention to provide a method for calibrating sensor information of a vehicle which enables reliable and highly accurate online sensor calibration, ie calibration of sensor information of different sensor types relative to each other while the vehicle is driving.

[0008] This object is achieved by a method having the features of independent patent claim 1. Preferred embodiments are the subject of the dependent claims. A driver assistance system is the subject of independent patent claim 15.

[0009] According to a first aspect, the invention relates to a method for calibrating sensor information of a vehicle. The vehicle has at least one sensor of a first sensor type and at least one sensor of a second sensor type that differs from the first sensor type. "Different sensor type" here means that the sensors use different methods or technologies for environmental detection, for example, environmental detection based on different types of electromagnetic waves (radar, lidar, ultrasound, visible light, etc.).

[0010] The procedure includes the following steps: First, the surroundings are detected while the vehicle is moving by at least one sensor of the first sensor type. Initial sensor information is provided by this sensor of the first sensor type.

[0011] Likewise, the surroundings are detected while the vehicle is moving by at least one sensor of the second sensor type. Second sensor information is provided by this sensor of the second sensor type. The first and second sensor information can be detected simultaneously or at least temporarily with a temporal overlap. It is understood that the first and second sensor information relate at least partially to the same surrounding area and thus have at least partially the same detection range.

[0012] Subsequently, a first three-dimensional representation of environmental information is generated from the first sensor information. The first three-dimensional representation of environmental information is, in particular, a 3D point cloud that represents the vehicle's surroundings based on a large number of points in three-dimensional space.

[0013] In addition, a second three-dimensional representation of environmental information is generated from the second sensor information. The second three-dimensional representation of environmental information is, in particular, a 3D point cloud that represents the vehicle's surroundings based on a large number of points in three-dimensional space.

[0014] Subsequently, the first and second three-dimensional representations of environmental information or information derived therefrom are compared. "Comparing" within the meaning of the present disclosure is understood in particular to mean that the first and second three-dimensional representations are related to one another in order to be able to check the congruence of the first and second three-dimensional representations of environmental information. This can in particular mean determining corresponding regions in the first and second three-dimensional representations of environmental information. "Information derived therefrom" is understood to mean any information that can be obtained from the first and second three-dimensional representations through any type of data processing, for example, through data reduction, filtering, etc.

[0015] Deviations between the first and second three-dimensional representations of environmental information or information derived therefrom are then determined. In particular, it can be checked whether there is an overall deviation between the plurality of corresponding regions in the first and second three-dimensional representations that can be attributed to incorrect calibration of the sensors. For example, an offset between corresponding regions in the first and second three-dimensional representations that increases with distance from the vehicle can result from incorrect calibration of the roll, pitch, and / or yaw angle of a sensor.

[0016] After determining the deviations, correction information for the calibration parameters of at least one sensor is calculated based on the determined deviations. The correction information can, in particular, provide an indication of how the calibration of one or more sensors needs to be changed to achieve improved coverage accuracy of the first and second three-dimensional representations of environmental information.

[0017] Finally, the vehicle's sensors are calibrated relative to each other based on the calculated correction information. Calibrating the sensors particularly includes software calibration, i.e., the sensor information provided by one or more sensors is adjusted based on the correction information in such a way that improved coverage of the first and second three-dimensional representations of environmental information is achieved.

[0018] It is understood that the calibration of sensors of more than two different sensor types is also possible based on the proposed method.

[0019] The technical advantage of the proposed method is that by converting multiple different sensor information into a three-dimensional representation of the surrounding information, the sensor information becomes comparable with each other, enabling online calibration of the sensors based on the surrounding information acquired while the vehicle is moving. This enables highly accurate calibration of the sensors, which is necessary for safe and precise environmental detection for autonomous driving functions of the vehicle.

[0020] According to one embodiment, the first and second three-dimensional representations of environmental information are discrete-time information. In other words, the sensors do not provide continuous-time information, but rather provide environmental information at discrete points in time, for example, at a specific clock rate. Before comparing the first and second three-dimensional representations of environmental information or information derived therefrom, the information is temporally synchronized with each other. This can reduce inaccuracies in the alignment between the first and second three-dimensional representations of environmental information, which arise due to a temporal offset of the environmental information from the various sensors, for example, due to different clock rates or different acquisition times.

[0021] In the event that temporal synchronization of the first and second three-dimensional representations of environmental information is not possible, an interpolation of information between two time steps of the discrete-time information can be performed before comparing the first and second three-dimensional representations of environmental information or information derived therefrom. This allows intermediate values ​​of sensor information or three-dimensional representations of environmental information to be obtained between two consecutive time steps, which can be used to achieve improved coverage accuracy.

[0022] According to one embodiment, first and second three-dimensional representations of environmental information, which represent the vehicle environment at the same time, are compared with each other, and deviations between these first and second three-dimensional representations of environmental information are used to calculate the correction information. In particular, it is checked whether, among the multitude of deviations that exist between corresponding information in the first and second three-dimensional representations of environmental information, such deviations can be determined that are attributable to a calibration error of one or more sensors. If such deviations are detected, an attempt can be made to adapt the calibration of one or more sensors in such a way that the deviations are reduced, iethe coverage accuracy of the first and second three-dimensional representations of environmental information is increased.

[0023] According to one embodiment, the correction information for calibration parameters is calculated iteratively, specifically in such a way that, in several iterative steps, at least a first and a second three-dimensional representation of environmental information that reflect the vehicle environment at the same time are compared with each other, correction information is calculated, and after applying the correction information to the calibration parameters of at least one sensor, information about the congruence of the first and second three-dimensional representations of environmental information is determined. This allows the calibration of the sensors to be improved iteratively.

[0024] According to one embodiment, the correction information is iteratively modified in successive iteration steps such that the congruence error between the first and second three-dimensional representations of environmental information is reduced. For example, after determining the correction information in one iteration step, the correction information is applied, thereby changing the sensor calibration. This preferably results in a modified first and / or second three-dimensional representation of environmental information, which is checked for congruence. This cycle is repeated several times until a termination criterion is reached. This allows the sensor calibration to be improved iteratively.

[0025] According to one embodiment, a minimization method or an optimization method is used to reduce the congruence error. An example of this is the Iterative Closest Point Algorithm. When implementing the algorithm, an attempt is made, for example, to align the first and second three-dimensional representations of environmental information as closely as possible using rotation and translation. For example, corresponding points of the first and second three-dimensional representations of environmental information are determined and then, for example, the sum of the squares of the distances across all these point pairs is calculated. This provides a quality criterion regarding the correspondence between the three-dimensional representations of environmental information or the 3D point clouds. The goal of the algorithm is to achieve this quality criterion by changing the transformation parameters (i.e.Parameters for rotation and translation) can be minimized. This allows the congruence of the three-dimensional representations of environmental information determined by different sensors to be gradually improved.

[0026] According to one embodiment, correction information for calibration parameters is calculated using a plurality of first and second three-dimensional representations of environmental information determined at different points in time. This is done by comparing several pairs of first and second three-dimensional representations of environmental information, each of which represents the vehicle environment at the same point in time, and calculating correction information. By comparing first and second three-dimensional representations of environmental information across multiple points in time, the accuracy of the sensor calibration can be further increased.

[0027] According to one embodiment, the sensor of the first sensor type is a camera. The camera can be configured, in particular, to generate two-dimensional images. Multiple sensors of the first sensor type can also be provided in order to capture a larger area of ​​the vehicle's surroundings. In particular, a 360° representation of the surroundings, i.e., a panoramic view in a horizontal plane, can be generated using the sensors of the first sensor type.

[0028] According to one embodiment, the camera is a monocular camera and from the image information provided by the camera, three-dimensional representations of environmental information are calculated from individual images or a sequence of temporally successive two-dimensional images.

[0029] For example, a structure-from-motion method, a shape-from-focus method, or a shape-from-shading method can be used. Alternatively, depth estimation can be performed using neural networks. This allows depth information to be obtained from the two-dimensional image information of the camera, which is then used to generate three-dimensional representations of environmental information. Structure-from-motion methods generally assume a static environment.

[0030] Alternatively, one or more stereo cameras can be used to obtain depth information to the two-dimensional image information.

[0031] According to one embodiment, based on a sequence of temporally consecutive image information from at least one camera, in particular two-dimensional image information, a segmentation of moving objects contained in the image information and an estimation of the three-dimensional structure and relative movements of the segmented objects and the stationary environment are carried out, for example using the method from patent application DE 10 2019 208 216 A1. This allows segmentation and structural information to be determined with high accuracy even in dynamic environments. The determined information on the relative movements of the environment and the moving objects can advantageously be incorporated into the synchronization of the three-dimensional representations of all objects or the interpolation between two time steps, which leads to greater accuracy in determining the correction information for the calibration parameters.

[0032] According to one embodiment, the sensor of the second sensor type is a radar sensor or a LIDAR sensor.

[0033] According to one embodiment, moving objects are filtered out from the first and second three-dimensional representations of environmental information, so that the correction information is calculated exclusively based on stationary objects. By filtering out moving objects, the accuracy of the sensor calibration can be increased, since, for stationary objects, the deviation between the first and second three-dimensional representations of environmental information can be used to directly determine the calibration inaccuracies between the sensors.

[0034] According to another embodiment, the correction information is calculated based on a comparison of first and second three-dimensional representations of environmental information that contain only stationary objects and based on a comparison of first and second three-dimensional representations of environmental information that contain only moving objects. This allows moving objects to be used in addition to stationary objects to calculate correction information for sensor calibration. However, motion information about the moving objects, such as their trajectory or speed, should preferably be known in order to compensate for the movement of the objects when calculating the correction information.

[0035] According to a further aspect, the invention relates to a driver assistance system for a vehicle. The driver assistance system comprises a sensor of a first sensor type and at least one sensor of a second sensor type that differs from the first sensor type. The driver assistance system is designed to perform the following steps: - detecting the environment while the vehicle is traveling by at least one sensor of the first sensor type and providing first sensor information by this sensor of the first sensor type; - detecting the environment while the vehicle is traveling by at least one sensor of the second sensor type and providing second sensor information by this sensor of the second sensor type; - Creating a first three-dimensional representation of environmental information from the first sensor information; - Creating a second three-dimensional representation of environmental information from the second sensor information; - comparing the first and second three-dimensional representation of environmental information or information derived therefrom; - determining deviations between the first and second three-dimensional representation of environmental information or information derived therefrom; - Calculating correction information for calibration parameters of at least one sensor based on the determined deviations; - Calibrating the vehicle's sensors relative to each other based on the calculated correction information.

[0036] “Three-dimensional representation of environmental information” means any representation of environmental information in a three-dimensional coordinate system, for example a discrete spatial representation of object areas in three-dimensional space.

[0037] The term “3D point cloud” in the sense of the present disclosure is understood to mean a set of points in three-dimensional space, wherein each point indicates that an object region is located at the location where the point is located in three-dimensional space.

[0038] The term "sensor type" within the meaning of this disclosure refers to a sensor type that determines environmental information using a predetermined detection principle. Sensor types can include, for example, cameras, radar sensors, LIDAR sensors, ultrasonic sensors, etc.

[0039] The terms “approximately”, “essentially” or “about” mean, in the sense of the invention, deviations from the exact value by + / - 10%, preferably by + / - 5% and / or deviations in the form of changes that are insignificant for the function.

[0040] Further developments, advantages, and possible applications of the invention will become apparent from the following description of exemplary embodiments and from the figures. All described and / or illustrated features, individually or in any combination, are fundamentally part of the invention, regardless of their summary in the claims or their reference back to them. The content of the claims is also incorporated into the description.

[0041] The invention is explained in more detail below with reference to exemplary embodiments and the figures. They show: Fig. 1 shows, by way of example, a schematic representation of a vehicle with a driver assistance system which has a plurality of sensors of different sensor types for detecting the surroundings of the vehicle; Fig. 2 shows an example of a flowchart illustrating method steps for calibrating sensor information from a camera and sensor information from a radar and / or LIDARS; and Fig. 3 shows an example schematic representation of the process steps for online calibration of sensor information of different sensor types.

[0042] Fig. Figure 1 shows, by way of example and schematically, a vehicle 1 with a driver assistance system that enables environmental detection using a plurality of sensors 2, 3, 4 of different sensor types. At least some of the sensors 2, 3, 4 enable all-round environmental detection (360° environmental detection).

[0043] The vehicle 1 comprises, in particular, at least one sensor 2 of a first sensor type, which is a radar sensor. The first sensor type is thus based on the radar principle. The sensor 2 can, for example, be provided in the front area of ​​the vehicle. It is understood that several sensors 2 of the first sensor type can be provided distributed around the vehicle 1, for example in the front area, the rear area and / or in the side areas of the vehicle 1. The at least one sensor 2 of the first sensor type generates first sensor information. This is, for example, the raw information provided by a radar sensor. A first three-dimensional representation of environmental information is generated from this first sensor information. This can, in particular, be a 3D point cloud.In the event that multiple sensors 2 of the first sensor type are used, the first three-dimensional representation of environmental information can be generated based on sensor information from several or all of these sensors 2.

[0044] The vehicle 1 further comprises at least one sensor 3 of a second sensor type, which is a camera. The second sensor type is thus of the “camera” type, i.e., an image-recording sensor. The sensor 3 can, for example, be provided in the windshield area of ​​the vehicle 1. It is understood that a plurality of sensors 3 of the second sensor type can be provided distributed around the vehicle 1, for example, in the front area, the rear area and / or in the side areas of the vehicle 1. The at least one sensor 3 of the second sensor type generates second sensor information. This is, for example, the image information provided by a camera. The camera can provide two-dimensional image information of the surroundings, i.e., the image information does not contain any depth information.In this case, the second sensor information can be further processed in such a way that depth information about the image information is obtained from the change in the image information in successive images of an image sequence. For this purpose, methods known to those skilled in the art can be used which generate spatial relationships from two-dimensional image sequences. Examples of this are the structure-from-motion method, the shape-from-focus method or the shape-from-shading method. Depth estimation using neural networks is also conceivable in principle. If the camera is a stereo camera, the second sensor information can also be directly three-dimensional information, i.e. it can also contain depth information for some of the pixels or for each pixel of the image. A second three-dimensional representation of environmental information is generated from this second sensor information.This can, in particular, be a 3D point cloud. If multiple sensors 3 of the second sensor type are used, the second three-dimensional representation of environmental information can be generated based on sensor information from several or all of these sensors 3.

[0045] The vehicle 1 preferably also comprises at least one sensor 4 of a third sensor type, which is a LIDAR sensor. The third sensor type is thus based on the LIDAR principle. The sensor 4 can, for example, be provided in the roof area of ​​the vehicle 1. It is understood that multiple sensors 4 of the third sensor type can be provided distributed on the vehicle 1. The at least one sensor 4 of the third sensor type generates third sensor information. This is, for example, the raw information provided by a LIDAR sensor. From this third sensor information, a third three-dimensional representation of environmental information is generated, unless the third sensor information already provides such a representation. This can, in particular, be a 3D point cloud.In the event that multiple sensors 4 of the third sensor type are used, the third three-dimensional representation of environmental information can be generated based on sensor information from several or all of these sensors 4.

[0046] The vehicle further comprises a computing unit 5, which is designed to further process the data provided by the sensors 2, 3, 4. The computing unit can, as in Fig. 1, a central processing unit can be provided or several decentralized processing units can be provided so that subtasks of the method described below are carried out distributed over several computer units.

[0047] Fig. 2 shows a flow chart illustrating the method steps of the method for calibrating sensor information from different sensors 2, 3, 4 relative to each other.

[0048] In step S10, sensor information from at least one radar sensor and / or at least one LIDAR sensor is received.

[0049] If radar and LIDAR sensors are present, the sensor information is first provided separately for each sensor type.

[0050] If these sensors do not already provide a three-dimensional representation of environmental information, in particular a 3D point cloud, one is created from the sensor information. If radar and LIDAR sensors are present, a three-dimensional representation of environmental information, in particular a 3D point cloud, is provided separately for each sensor type. The 3D point clouds can be created using sensor information from a single sensor or by merging sensor information from multiple sensors of the same sensor type.

[0051] Preferably, in step S11, the 3D point cloud obtained from the radar sensor information and—if present—the 3D point cloud obtained from the LIDAR sensor information are separated according to static and dynamic content. This means, in particular, that for each sensor type, a first 3D point cloud containing only static objects and a second 3D point cloud containing only moving objects are created. This makes it possible to generate separate correction information for the calibration parameters from static objects and moving objects.

[0052] In addition, second sensor information is received from a camera in step S12. A 3D point cloud is generated from the second sensor information in step S13.

[0053] For example, a three-dimensional reconstruction of the surroundings of the vehicle 1 is carried out by evaluating the temporally successive images of an image sequence from one or more cameras, for example by means of a structure-from-motion reconstruction method.

[0054] Preferably, a method is used that is disclosed in German patent application DE 10 2019 208 216 A1. The disclosure of this patent application is incorporated in its entirety into the present disclosure. Preferably, according to the method, both a 3D reconstruction of the environment or output of a 3D point cloud and a segmentation of moving objects are carried out. This makes it possible to distinguish between moving and stationary objects in the image information provided by the at least one camera (S14). Furthermore, the method can be used to determine trajectories of the moving objects, as well as the trajectory of the camera system relative to the stationary environment. By knowing the movement of the objects, 3D point clouds of different sensor types that contain moving objects can be correlated with one another, and thus, correction information for calibration can be derived.This simplifies, among other things, the steps of synchronization and interpolation, which then also provide more accurate results.

[0055] After a separation of static and dynamic content in the 3D point clouds generated from sensor information of a radar sensor and / or a LIDAR sensor as well as from sensor information of a camera has been performed, the further process steps can either be performed based solely on 3D point clouds containing static objects, or separate 3D point clouds are generated, each containing static or dynamic objects, and the further process steps are performed separately for static and dynamic objects, i.e., both 3D point clouds with static objects and 3D point clouds with dynamic objects are compared and used to generate the correction information for sensor calibration. Thus, the steps described below can be performed in parallel for 3D point clouds with dynamic objects and 3D point clouds with static objects.

[0056] The steps S10 / S11 and S12 / S13 / S14, i.e. the processing of the sensor information provided by the radar sensor or the LIDAR sensor and the sensor information provided by the camera, can be carried out at least partially in parallel.

[0057] In step S15, the 3D point clouds are preferably synchronized with each other in such a way that their congruence can be checked. This can be achieved, for example, by temporal synchronization. The 3D point clouds of the respective sensor types can be generated at different times, so that the environmental information in the 3D point clouds is spatially offset from each other due to the movement of the vehicle. This offset can be corrected by temporal synchronization of the 3D point clouds. Furthermore, it is possible to calculate intermediate information from several consecutive 3D point clouds, for example, by interpolation, in order to compensate for the temporal offset between the 3D point clouds of the respective sensor types.

[0058] Subsequently, in step S16, the 3D point clouds are compared, and the deviations between the 3D point clouds are determined. For example, the corresponding points in the point clouds to be compared—i.e., points that represent the same areas of an environmental scene—can be compared, and the distances between these points, or their spatial offsets, can be determined. This allows the determination in step S18 of the calibration inaccuracy between the sensors of the driver assistance system and which calibration parameters need to be changed (e.g., linear offset or deviation due to a rotated sensor).

[0059] Subsequently, in step S18, the correction information is applied, i.e., after modifying the calibration parameters based on the correction information, the 3D point clouds are again checked for congruence and this congruence is assessed.

[0060] A decision is then made in step S19 as to whether sufficient congruence has been achieved. If not, steps S16 to S19 are repeated. A minimization method with linear gradient descent, such as an iterative closest point method (ICP method), can be used.

[0061] After sufficient coverage between the 3D point clouds has been achieved, the correction information for the calibration parameters of the sensors is output in step S20 and / or the same is applied for sensor calibration.

[0062] Fig. 3 shows a flowchart illustrating the steps of a method for online calibration of sensor information from sensors of a vehicle.

[0063] First, the surroundings are detected while the vehicle is moving by at least one sensor of the first sensor type. Furthermore, initial sensor information is provided by this sensor of the first sensor type (S30).

[0064] In addition, the surroundings are detected by at least one sensor of the second sensor type while the vehicle is moving. Second sensor information is provided by this sensor of the second sensor type (S31). Steps S31 and S32 are executed simultaneously or at least temporarily overlapping.

[0065] Subsequently, a first three-dimensional representation of environmental information is created from the first sensor information (S32).

[0066] Simultaneously with step S32 or at least in temporal overlap, a second three-dimensional representation of environmental information is generated from the second sensor information (S33).

[0067] The first and second three-dimensional representations of environmental information or information derived therefrom are then compared (S34). "Derived information" refers to any information that can be obtained by modifying the first or second three-dimensional representation, for example, by filtering, restricting to stationary or non-stationary objects, etc.

[0068] Based on the comparison result, deviations between the first and second three-dimensional representation of environmental information or information derived therefrom are determined (S35).

[0069] Based on the determined deviations, correction information for the calibration parameters of at least one sensor is calculated (S36). Finally, the vehicle's sensors are calibrated relative to each other based on the calculated correction information (S37). This means, in particular, that the position or orientation of the sensors on the vehicle is not modified, but rather an indirect calibration is performed by modifying the 3D point clouds based on the correction information.

[0070] The invention has been described above using exemplary embodiments. It is understood that numerous changes and modifications are possible without departing from the scope of protection defined by the patent claims. List of reference symbols 1 vehicle 2 sensors 3 Sensor 4 Sensor 5 Computing unit

Claims

[1] Method for calibrating sensor information of a vehicle (1), wherein the vehicle (1) has at least one sensor (2) of a first sensor type and at least one sensor (3) of a second sensor type different from the first sensor type, the method comprising the following steps: - detecting the environment while the vehicle (1) is traveling by at least one sensor (2) of the first sensor type and providing first sensor information by this sensor (2) of the first sensor type (S10); - detecting the surroundings while the vehicle (1) is traveling by at least one sensor (3) of the second sensor type and providing second sensor information by this sensor (3) of the second sensor type (S11); - Creating a first three-dimensional representation of environmental information from the first sensor information (S 12); - Creating a second three-dimensional representation of environmental information from the second sensor information (S13); - comparing the first and second three-dimensional representation of environmental information or information derived therefrom (S14); - determining deviations between the first and second three-dimensional representation of environmental information or information derived therefrom (S15); - Calculating correction information for calibration parameters of at least one sensor based on the determined deviations (S16); - Calibrating the sensors (2, 3) of the vehicle (1) relative to each other based on the calculated correction information (S17). [2] Method according to claim 1, characterized bythat the first and second three-dimensional representations of environmental information are time-discrete information and that before comparing the first and second three-dimensional representations of environmental information or information derived therefrom, the information is temporally synchronized with one another. [3] Method according to claim 1 or 2, characterized by that the first and second three-dimensional representations of environmental information are time-discrete information and that before comparing the first and second three-dimensional representations of environmental information or information derived therefrom, an interpolation of information between two time steps of the time-discrete information takes place. [4] Method according to one of the preceding claims, characterized bythat first and second three-dimensional representations of environmental information, which represent the vehicle environment at the same time, are compared with each other and deviations between these first and second three-dimensional representations of environmental information are used to calculate the correction information. [5] Method according to one of the preceding claims, characterized bythat the calculation of correction information for calibration parameters is carried out iteratively, in such a way that in a plurality of iteration steps at least a first and a second three-dimensional representation of environmental information which represent the vehicle environment at the same time are compared with one another, correction information is calculated and, after application of the correction information to the calibration parameters of at least one sensor, information about the congruence of the first and second three-dimensional representations of environmental information is determined. [6] Method according to claim 5, characterized by that in the successive iteration steps the correction information is iteratively changed in such a way that the congruence error between the first and second three-dimensional representation of environmental information is reduced. [7] Method according to claim 6, characterized bythat a minimization method or an optimization method is used to reduce the congruence error. [8] Method according to one of the preceding claims, characterized by that the calculation of the correction information for calibration parameters is carried out by means of a plurality of first and second three-dimensional representations of environmental information which were determined at different times, in such a way that a plurality of pairs of first and second three-dimensional representations of environmental information, wherein the environmental information of a pair each represents the vehicle environment at the same time, are compared with one another and correction information is calculated. [9] Method according to one of the preceding claims, characterized by that the sensor (2) of the first sensor type is a camera. [10] Method according to claim 9, characterized bythat the camera is a monocular camera and that three-dimensional representations of environmental information from individual images or a sequence of temporally successive two-dimensional images are calculated from the image information provided by the camera. [11] Method according to claim 9 or 10, characterized by that based on a sequence of temporally successive image information from at least one camera, a segmentation of moving objects contained in the image information and an estimation of three-dimensional structure and relative movements of the segmented objects and the stationary environment are carried out. [12] Method according to one of the preceding claims, characterized by that the sensor (3) of the second sensor type is a radar sensor or a LIDAR sensor. [13] Method according to one of the preceding claims, characterized bythat moving objects are filtered out from the first and second three-dimensional representations of environmental information, so that the calculation of the correction information is based exclusively on stationary objects. [14] Method according to one of claims 1 to 12, characterized by that the correction information is calculated based on a comparison of first and second three-dimensional representations of environmental information containing only stationary objects and based on a comparison of first and second three-dimensional representations of environmental information containing only moving objects. [15] Driver assistance system for a vehicle (1) with a sensor (2) of a first sensor type and at least one sensor (3) of a second sensor type different from the first sensor type, wherein the driver assistance system is designed to carry out the following steps: - detecting the environment while the vehicle (1) is traveling by at least one sensor (2) of the first sensor type and providing first sensor information by this sensor (2) of the first sensor type; - detecting the environment while the vehicle (1) is traveling by at least one sensor (3) of the second sensor type and providing second sensor information by this sensor (3) of the second sensor type; - Creating a first three-dimensional representation of environmental information from the first sensor information; - Creating a second three-dimensional representation of environmental information from the second sensor information; - comparing the first and second three-dimensional representation of environmental information or information derived therefrom; - determining deviations between the first and second three-dimensional representation of environmental information or information derived therefrom; - Calculating correction information for calibration parameters of at least one sensor (2, 3) based on the determined deviations; - Calibrating the sensors (2, 3) of the vehicle (1) relative to each other based on the calculated correction information.

Images