Method for determining the position of a vehicle within a lane

Abstract

The invention relates to a method (100) for determining the position of a vehicle (1) within a lane (2), comprising the following steps: - Providing (101) image data, wherein the image data results from a recording by at least one camera (3) of the vehicle (1), - Analyzing (102) the image data to determine a lane width (2) and a distance of the vehicle (1) to the nearest lane boundary (2), - Determining (103) at least two partial lanes (4) in the lane (2) based on the determined width of the lane (2) and the nearest boundary of the lane (2), - Determining (104) the position of the vehicle (1) in relation to one of the at least two specified partial lanes (4) on the basis of the width of the lane (2) and the distance of the vehicle (1) to the nearest boundary (5) of the lane (2). Furthermore, the invention relates to a computer program, a device and a storage medium for this purpose.

Description

[0001] The invention relates to a method for determining the position of a vehicle within a lane. Furthermore, the invention relates to a computer program, a device, and a storage medium for this purpose. State of the art

[0002] When riding a motorcycle, it can be particularly important to take various preventative measures for safe riding. One of these measures, for example, is the choice of lane position so that the motorcycle rider can avoid potential hazards such as obstacles, sections of road with low grip, or vehicles ahead. Furthermore, the choice of position within the lane can also be important when riding in groups. When riding in groups, for example, there are various formations that ensure safe riding. Maintaining this formation can be achieved by knowing the position of the motorcycle in the lane. Furthermore, the choice of lane position can be relevant in the context of cornering in order to find a safe path for turning into the corner.

[0003] However, current lane detection solutions are mostly focused only on vehicle-based solutions and, in particular, do not take into account parts of a lane depending on the size of the vehicle. Disclosure of the invention

[0004] The subject matter of the invention is a method having the features of claim 1, a computer program having the features of claim 8, a device having the features of claim 9, and a computer-readable storage medium having the features of claim 10. Further features and details of the invention emerge from the respective subclaims, the description, and the drawings. Features and details described in connection with the method according to the invention naturally also apply in connection with the computer program according to the invention, the device according to the invention, and the computer-readable storage medium according to the invention, and vice versa, so that with regard to the disclosure of the individual aspects of the invention, reference is or can always be made to each other.

[0005] The invention particularly relates to a method for determining a position of a vehicle within a lane, comprising the following steps: - Providing image data, wherein the image data result from a recording by at least one camera of the vehicle, - Analyzing the image data to determine a lane width and a distance of the vehicle to a nearest lane boundary, - Determining at least two partial lanes in the lane based on the determined width of the lane and the nearest boundary of the lane, - Determining the position of the vehicle with respect to one of the at least two specific partial lanes based on the width of the lane and the distance of the vehicle to the nearest boundary of the lane.

[0006] The lane is, in particular, a lane in which the vehicle is currently traveling. The vehicle is preferably a two-wheeler, such as a motorcycle. It is also conceivable for the vehicle to be a bicycle. The nearest boundary is, in particular, the closest in relation to the vehicle. If there is more than one boundary, the distance of the vehicle to all boundaries can first be determined and then the nearest boundary can be determined among them. The boundary of the lane can be a marking and / or a road edge or carriageway edge and / or an obstacle, such as a wall or a guardrail. The analysis of the image data can be carried out using various image recognition methods known in the art, for example by applying a machine learning model such as a convolutional neural network.To determine the distance of the vehicle from the nearest boundary, it can be provided that 3D coordinates are provided for the image data in order to determine the distance to the nearest boundary based on depth information of the 3D coordinates. It is also conceivable that the distance to the nearest boundary is determined by a calculation based on the relative sizes of objects in the image data to one another, for example, based on the width of the lane and a known position of the camera in the vehicle. A width of the at least two partial lanes can be determined based on the width of the lane; for example, this is halved to provide the two partial lanes as half of the lane each, or divided into thirds if three partial lanes are provided. The method can be advantageous because it enables a differentiated determination of the position of the vehicle in the lane.It may be provided that the determination of the position of the vehicle is carried out at regular intervals in order to advantageously provide an update of the position and a tracking of the position along a route.

[0007] Furthermore, it is conceivable that at least three partial lanes are determined in the lane, wherein the at least three partial lanes preferably have the same width. The at least three partial lanes can, for example, be subdivided into a left, a middle, and a right partial lane, wherein the left, middle, and right partial lanes each make up, for example, one-third of the width of the lane. By determining at least three partial lanes, a more differentiated determination of the vehicle's position can be achieved. Furthermore, three partial lanes can be advantageous for analyzing various driving scenarios of the vehicle, especially in the case of a motorcycle. It is also conceivable that a subdivision into more than three lanes occurs.

[0008] In a further possibility, it can be provided that the method further comprises at least one of the following steps: - Detecting at least one lane boundary based on the analysis of the image data, - Defining the width of the lane based on a specification if only one boundary of the lane has been detected, - Calculate the lane width based on the analysis of the image data when two lane boundaries have been detected.

[0009] The specification can, for example, be a value for the width in a specific country, such as 3.5 meters. The specification can therefore be dependent on the country or region in which the vehicle is located. Advantageously, the method can also be implemented with only a single lane boundary. The detection of at least one lane boundary can occur continuously or at defined intervals.

[0010] It may be further advantageous for the method to further comprise the following steps: - Determining a recommended partial lane based on an analysis of the image data with regard to a current driving scenario, - Initiating an issuance of a warning to a driver of the vehicle when the vehicle is in a lane other than the recommended partial lane, the warning preferably indicating the recommended partial lane.

[0011] Multiple recommended partial lanes can also be identified. For example, both a right and a left partial lane could be the recommended partial lane, while a middle partial lane could pose a risk to the vehicle driver. The current driving scenario may, for example, involve the vehicle driving behind a passenger car, so the recommended partial lane could be the right or left of three partial lanes. Furthermore, the current driving scenario may also involve driving around a curve, in which case the recommended partial lane could be an outer partial lane. By issuing the warning to the vehicle driver, they can react advantageously and steer the vehicle into the recommended partial lane. This can help avoid hazards that could arise if the vehicle is in the wrong position within the lane.

[0012] Within the scope of the invention, it can be provided that the warning is output visually and / or acoustically in a human-machine user interface. For this purpose, the human-machine user interface can, for example, have a display to provide the visual output of the warning. It is also conceivable that the acoustic output is provided to the driver via a loudspeaker of the human-machine user interface or, for example, via a Bluetooth connection via headphones.

[0013] A further advantage within the scope of the invention can be achieved if the method further comprises the following step: - Determining a free space in front of the vehicle in the lane based on the analysis of the image data.

[0014] In this case, the recommended lane can be determined taking into account the determined free space in front of the vehicle. This can be advantageous because determining the free space can detect possible obstacles or objects in the lane. For example, there might be an oil stain or a vehicle part such as a tire in a left lane, so another lane, such as the middle and / or right lane, would be the recommended lane.

[0015] According to a further option, the determination of the recommended partial lane can also be carried out taking into account the current speed of the vehicle. By additionally taking the current speed into account, a more differentiated analysis can advantageously be performed with regard to the recommended partial lane. The current speed can be provided by sensor data from a sensor on the vehicle or determined based on the image data.

[0016] It is possible for the method according to the invention to be used in a vehicle. The vehicle can be designed, for example, as a motorcycle or a motor vehicle. The vehicle can have a vehicle device, for example, for providing an autonomous driving function and / or a driver assistance system. The vehicle device can be designed to control the vehicle at least partially automatically and / or to accelerate and / or decelerate and / or steer.

[0017] The image data can result from capture with a camera sensor. In this case, an environment and / or a traffic scene can be represented by the values ​​of image points, preferably pixels, of the image data. Objects in the environment and / or the traffic scene can be detected by classification and preferably image classification based on these values. The classification and image classification can also be provided in the form of semantic segmentation (i.e., pixel- or area-wise classification) and / or object detection. The image data can also be, for example, images from a radar sensor and / or an ultrasonic sensor and / or a LiDAR sensor and / or a thermal imaging camera. Accordingly, the images can also be implemented as radar images and / or ultrasonic images and / or thermal images and / or LiDAR images.

[0018] The invention also relates to a computer program, in particular a computer program product, comprising instructions that, when executed by a computer, cause the computer to carry out the method according to the invention. Thus, the computer program according to the invention provides the same advantages as those described in detail with reference to a method according to the invention.

[0019] The invention also relates to a data processing device configured to carry out the method according to the invention. The device can be, for example, a computer that executes the computer program according to the invention. The computer can have at least one processor for executing the computer program. A non-volatile data memory can also be provided, in which the computer program is stored and from which the computer program can be read by the processor for execution.

[0020] The invention may also provide a computer-readable storage medium that contains the computer program according to the invention and / or includes instructions that, when executed by a computer, cause the computer to carry out the method according to the invention. The storage medium is designed, for example, as a data storage device such as a hard disk and / or a non-volatile memory and / or a memory card. The storage medium can, for example, be integrated into the computer.

[0021] Furthermore, the method according to the invention can also be implemented as a computer-implemented method.

[0022] Further advantages, features, and details of the invention will become apparent from the following description, which describes embodiments of the invention in detail with reference to the drawings. The features mentioned in the claims and in the description may be essential to the invention individually or in any combination. They show: Fig. 1 a schematic visualization of a method, a device, a storage medium and a computer program according to embodiments of the invention, Fig. 2 a schematic representation of a vehicle with a camera according to embodiments of the invention, Fig. 3 a possible application scenario of the method with a truck according to embodiments of the invention, Fig. 4 shows another possible application scenario of the method with a passenger car according to embodiments of the invention, Fig. 5 shows another possible application scenario of the method with an oil stain according to embodiments of the invention, Fig. 6 shows another possible application scenario of the method with cornering according to embodiments of the invention, Fig. 7 shows another possible application scenario of the method with a group trip according to embodiments of the invention,

[0023] In Fig. 1, a method 100, a device 10, a storage medium 15 and a computer program 20 according to embodiments of the invention are schematically shown.

[0024] Fig. 1 shows in particular a method 100 for determining a position of a vehicle 1 within a lane 2 according to exemplary embodiments of the invention. In a first step 101, image data is provided, wherein the image data results from a recording by at least one camera 3 of the vehicle 1. In a second step 102, the image data is analyzed to determine a width of the lane 2 and a distance of the vehicle 1 from a nearest boundary of the lane 2. In a third step 103, at least two partial lanes 4 in the lane 2 are determined based on the determined width of the lane 2 and the nearest boundary of the lane 2. In a fourth step 104, the position of the vehicle 1 with respect to one of the at least two determined partial lanes 4 is determined based on the width of the lane 2 and the distance of the vehicle 1 from the nearest boundary of the lane 2.

[0025] Fig. 2 schematically shows a vehicle 1 with a camera 3 according to embodiments of the invention.

[0026] The detection of lanes 2 and road edges can be performed using algorithms using appropriate video sensors. Based on this, the position in lane 2 can then be determined. This also enables, in particular, detection of the ego lane. The ego lane is preferably lane 2 in which the vehicle 1, in particular the motorcycle 1, is traveling.

[0027] When riding a motorcycle, the rider must be particularly able to avoid hazards on the road, and therefore the motorcycle 1 should preferably be in a safe position on the roadway. Given that the video sensor is capable of determining the boundaries 5 of lane 2, this information can be used to determine which partial lanes 4 (subsections of lane 2) can be selected. To achieve this, a method according to embodiments of the invention can determine the width of lane 2 and define two, in particular three, partial lanes 4, for example, left, center, and right.

[0028] Taking into account the smaller size of the motorcycle 1, it may be advantageous to identify sub-sections, or partial lanes 4, of the road in order to improve algorithms for accident prevention and comfortable driving and the associated functions.

[0029] Smaller, motorcycle-specific lanes 2 within the current lanes 2 enable new motorcycle-oriented comfort and safety functions, such as hazard avoidance, group riding, or cornering recommendations. Furthermore, existing comfort and safety functions for two-wheelers can be adapted to provide similar performance to the new functions.

[0030] A possible sequence of a method according to an exemplary embodiment is described below. In a first step, the width of the ego lane can be determined as a function of the detected boundaries 5 of the lane 2 and updated based on the following criteria. If only one boundary 5 is detected, the tracked width is preferably reduced to a standard lane width (for example 3.5 m). If both boundaries 5 are detected, the determined width is in particular updated accordingly. If no boundary 5 is detected, the determined width is preferably reduced to the standard lane width. In a further step, a distance to the nearest boundary 5 is preferably calculated. Subsequently, in a further step, a width of the at least two, in particular three, partial lanes 4 can be determined.In a further step, the position in lane 2 can be calculated based on the width and position of the lateral deviation of motorcycle 1 from the boundary 5. In a further step, a last position of motorcycle 1 in lane 2 can be updated to enable tracking of past positions.

[0031] In the Fig. 3 to 7 show various advantageous applications of the method according to embodiments. Fig. 3 shows two lanes 2. On the lower lane 2, three possible sub-lanes 4 for the vehicle 1, preferably a motorcycle 1, are shown. On the upper lane 2, an obstacle 6, in this case a truck, is shown. Due to the presence of the obstacle 6 in the upper lane 2, the middle and lower sub-lanes 4 are preferably the recommended sub-lanes 4, since the left sub-lane 4 could pose a risk to the driver of the vehicle 1 due to the obstacle 6. On the lane 2, in which the vehicle 1 is located, center lane markings and an outer continuous lane marking are also shown, which can be a boundary 5 according to the method. For example, if the vehicle 1 is in the left sub-lane 4, the center lane markings are the nearest boundary.

[0032] Fig. Figure 4 shows another scenario with two lanes 2. In this case, an obstacle 6 in the form of a passenger car is present in the same lane 2 as vehicle 1. Due to the obstacle 6, the right and left partial lanes 4 may be the recommended partial lanes 4 in this case, since the middle partial lane 4 could pose a risk to the driver of vehicle 1 due to the obstacle 6.

[0033] Fig. Figure 5 shows another scenario with two lanes 2. In this case, an obstacle 6 in the form of an oil stain is present on the left lane 4. Accordingly, the middle and right lanes 4 can be the recommended lanes 4 for vehicle 1.

[0034] Fig. Figure 6 shows another scenario with two lanes 2. This scenario involves a left-hand bend, which is why the outer, i.e., the right, lane 4 can be the recommended lane 4 for vehicle 1. One boundary 5 is the outer edge of the road, and another possible boundary 5 is the center lane markings.

[0035] Fig. Figure 7 shows another scenario with two lanes 2. Here, several vehicles 1, in particular motorcycles 1, are in the lower lane 2. To ensure safe travel, it may be provided that vehicles 1 traveling one behind the other are located in an opposite partial lane 4. In simple terms, the partial lanes 4 recommended for the respective vehicles 1 can always alternate between the left and right partial lanes 4.

[0036] The above explanation of the embodiments describes the present invention exclusively by way of examples. Of course, individual features of the embodiments can be freely combined with one another, provided they are technically feasible, without departing from the scope of the present invention.

Claims

[1] Method (100) for determining a position of a vehicle (1) within a lane (2), comprising the following steps: - providing (101) image data, wherein the image data result from a recording by at least one camera (3) of the vehicle (1), - analyzing (102) the image data to determine a width of the lane (2) and a distance of the vehicle (1) to a nearest boundary of the lane (2), - determining (103) at least two partial lanes (4) in the lane (2) on the basis of the determined width of the lane (2) and the nearest boundary of the lane (2), - Determining (104) the position of the vehicle (1) with respect to one of the at least two specific partial lanes (4) on the basis of the width of the lane (2) and the distance of the vehicle (1) to the nearest boundary of the lane (2). [2] Method (100) according to claim 1, characterized bythat at least three partial lanes (4) are determined in the lane (2), wherein the at least three partial lanes (4) preferably have the same width. [3] Method (100) according to one of the preceding claims, characterized by that the method (100) further comprises at least one of the following steps: - detecting at least one boundary (5) of the lane (2) based on the analysis of the image data, - Defining the width of the lane (2) based on a specification if only one boundary (5) of the lane (2) has been detected, - Calculating the width of the lane (2) based on the analysis of the image data if two boundaries (5) of the lane (2) have been detected. [4] Method (100) according to one of the preceding claims, characterized by that the method (100) further comprises the following steps: - Determining a recommended partial lane (4) based on an analysis of the image data with regard to a current driving scenario, - initiating an output of a warning to a driver of the vehicle (1) when the vehicle (1) is in a lane other than the recommended partial lane (4), the warning preferably indicating the recommended partial lane (4). [5] Method (100) according to claim 4, characterized by that the warning is output visually and / or acoustically in a human-machine user interface. [6] Method (100) according to one of claims 4 or 5, characterized by , that the method (100) further comprises the following step: - Determining a free space in front of the vehicle (1) on the lane (2) based on the analysis of the image data, wherein the determination of the recommended partial lane (4) is carried out taking into account the determined free space in front of the vehicle (1). [7] Method (100) according to one of claims 4 to 6, characterized by that the determination of the recommended partial lane (4) is further carried out taking into account a current speed of the vehicle (1). [8] Computer program (20) comprising instructions which, when the computer program (20) is executed by a computer (10), cause the computer (10) to carry out the method (100) according to one of the preceding claims. [9] Device (10) for data processing, which is arranged to carry out the method (100) according to one of claims 1 to 7. [10] A computer-readable storage medium (15) comprising instructions which, when executed by a computer (10), cause the computer (10) to carry out the steps of the method (100) according to any one of claims 1 to 7.

Images