Method, device and equipment for determining lane line pressing amount, medium and product

Abstract

The invention relates to a method, device and equipment for determining a lane line pressing amount, a medium and a product. The method comprises the following steps: acquiring a current driving working condition of a vehicle; determining at least two actual line pressing quantities of the adjacent vehicle; the lane where the adjacent vehicle is located is adjacent to the lane where the vehicle is located; and determining a target actual line pressing amount of the adjacent vehicle based on the working condition and the at least two actual line pressing amounts. According to the scheme, the target actual line pressing amount is determined by combining actual working conditions, and the accuracy is higher.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method, device, equipment, medium and product for determining lane pressure. Background Art

[0002] With the continuous development of vehicle technology, the amount of pressure on the neighboring vehicle determines the planned path of the vehicle and whether to perform avoidance actions such as braking. Therefore, how to accurately determine the amount of pressure on the neighboring vehicle has become an urgent problem to be solved. Summary of the invention

[0003] One of the purposes of the present invention is to provide a method, device, equipment, medium and product for determining the lane line pressure amount, which combines the actual working conditions when determining the target actual line pressure amount and has higher accuracy.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for determining a lane line pressing amount, the method comprising: obtaining the current driving condition of a vehicle; determining at least two actual line pressing amounts of an adjacent vehicle; the lane where the adjacent vehicle is located is adjacent to the lane where the vehicle is located; based on the operating condition and at least two actual line pressing amounts, determining a target actual line pressing amount of the adjacent vehicle.

[0006] Based on the above means, the current driving condition of the vehicle and at least two actual line pressing values ​​are first obtained, and then the target actual line pressing value is determined by combining the condition information and at least two actual line pressing values. This solution combines the actual working conditions when determining the target actual line pressing value, and considers the influence of the actual working conditions on the line pressing value, so the determined target actual line pressing value is more accurate.

[0007] In some implementations, at least two actual line pressing amounts are determined based on image information acquired by an image collector of the vehicle.

[0008] Based on the above means, at least two actual line pressure amounts are determined based on image information, that is, the actual line pressure amounts are determined based on pure visual means. Compared with radar sensors and ranging sensors, the characteristics of vision can detect distances, so the applicable distance range is wider, and the calculation stability of pure line of sight is improved, and the calculation dependence is less.

[0009] In some implementations, determining at least two actual line-pressing amounts of a neighboring vehicle includes at least two of the following: determining a first actual line-pressing amount of the neighboring vehicle based on the first actual longitudinal distance; determining a second actual line-pressing amount of the neighboring vehicle based on the first actual lateral distance; and determining a third actual line-pressing amount of the neighboring vehicle based on the vehicle frame of the neighboring vehicle in the world coordinate system.

[0010] Based on the above means, a variety of purely visual methods for determining the actual amount of line pressing are configured, including: determining the actual amount of line pressing based on the first actual longitudinal distance, based on the first actual lateral distance, and based on the vehicle frame of the neighboring vehicle in the world coordinate system. Since the longitudinal distance, lateral distance, and vehicle frame rely on different image detection results, respectively, it is equivalent to determining the actual amount of line pressing through multiple dimensions. In this way, even under some special working conditions, which may affect the accurate determination of the actual amount of line pressing at a certain angle, the target amount of line pressing can be determined in combination with the actual amount of line pressing determined in other dimensions, with higher accuracy.

[0011] In some implementations, based on the first actual longitudinal distance, determining a first actual line pressing amount of the neighboring vehicle includes: determining the first actual longitudinal distance as the actual longitudinal distance between the neighboring vehicle and the vehicle; determining a first pixel line pressing amount of the neighboring vehicle based on image information acquired by an image collector; determining the first actual line pressing amount of the neighboring vehicle based on the first actual longitudinal distance, the first pixel line pressing amount of the neighboring vehicle and the focal length of the image collector.

[0012] Based on the above means, since the actual longitudinal distance between the neighboring vehicle and the vehicle can generally be determined, the actual longitudinal distance between the neighboring vehicle and the vehicle is taken as the first actual longitudinal distance, and then the first pixel pressure line amount of the neighboring vehicle is determined based on the image information collected by the image collector, that is, the pixel value of the first pressure line amount can be obtained. In this way, the first actual pressure line amount of the neighboring vehicle is determined based on the first actual longitudinal distance, the first pixel pressure line amount of the neighboring vehicle and the focal length of the image collector. It can be seen that the entire implementation principle relies on the longitudinal distance and the pixel distance, and has the characteristics of simple implementation.

[0013] In some implementations, determining a second actual line pressing amount of an adjacent vehicle based on the first actual lateral distance includes: determining the first actual lateral distance as the actual width of the lane where the adjacent vehicle is located; determining a second pixel line pressing amount of the adjacent vehicle based on image information acquired by an image collector; determining a lane pixel distance of the lane where the adjacent vehicle is located based on image information acquired by the image collector; determining a second actual line pressing amount of the adjacent vehicle based on the first actual lateral distance, the second pixel line pressing amount of the adjacent vehicle, and the lane pixel distance of the lane where the adjacent vehicle is located.

[0014] Based on the above means, since the actual width of the lane is generally known, the actual width of the lane can be determined as the first actual lateral distance, and then the second pixel line pressing amount of the adjacent vehicle can be determined based on the image information collected by the image collector, that is, the pixel value of the second line pressing amount can be obtained. In this way, the second actual line pressing amount is determined based on the first actual lateral distance, the second pixel line pressing amount of the adjacent vehicle and the lane pixel distance of the adjacent vehicle. It can be seen that the entire implementation principle relies on the lateral distance and pixel distance, and is simple to implement.

[0015] In some implementations, a third actual line-crossing amount of a neighboring vehicle is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system, including: determining the vehicle frame of the neighboring vehicle in the world coordinate system based on image information collected by an image collector; determining the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system based on the image information collected by the image collector; determining the third actual line-crossing amount of the neighboring vehicle based on the vehicle frame of the neighboring vehicle in the world coordinate system and the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system.

[0016] Based on the above means, when determining the third actual crossing amount of the neighboring vehicle, it is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system and the curve of the lane line between the neighboring vehicle and the vehicle in the world coordinate system. It can be seen that the entire implementation principle relies on the formulation of the curve and the determination of the vehicle frame, and has the characteristics of simple implementation.

[0017] In some implementations, a target actual line pressing amount of a neighboring vehicle is determined based on operating conditions and at least two actual line pressing amounts, including: inputting at least two actual line pressing amounts into a filter; configuring a filter coefficient corresponding to each of the at least two actual line pressing amounts in the filter based on the operating conditions to obtain a target filter; and filtering at least two actual line pressing amounts through the target filter to obtain a target actual line pressing amount.

[0018] Based on the above means, at least two actual wire pressing amounts are fused through a filter to obtain a target actual wire pressing amount. Compared with selecting one from at least two actual wire pressing amounts, this scheme can combine the respective advantages of each actual wire pressing amount and obtain a higher accuracy.

[0019] In some implementations, when at least two actual line pressing amounts include a first actual line pressing amount, a second actual line pressing amount, and a third actual line pressing amount, a filter coefficient corresponding to each of the at least two actual line pressing amounts in the filter is configured based on the operating condition to obtain a target filter, including: based on the operating condition, configuring the coefficient of the first actual line pressing amount as a first filter coefficient; based on the operating condition, configuring the coefficient of the second actual line pressing amount as a second filter coefficient; based on the operating condition, configuring the coefficient of the third actual line pressing amount as a third filter coefficient; wherein the first actual line pressing amount is determined based on the first actual longitudinal distance, the second actual line pressing amount is determined based on the first actual lateral distance, and the third actual line pressing amount is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system.

[0020] Based on the above means, the first filter coefficient is configured for the filter coefficient corresponding to the first actual line-pressing amount determined based on the first actual longitudinal distance, the second filter coefficient is configured for the filter coefficient corresponding to the second actual line-pressing amount determined by the first actual lateral distance, and the third filter coefficient is configured for the filter coefficient corresponding to the third actual line-pressing amount determined based on the vehicle frame of the neighboring vehicle in the world coordinate system. The three actual line-pressing amounts are integrated through these three filter coefficients, which has the characteristics of simple, reliable and accurate implementation.

[0021] In some implementations, when the operating condition does not belong to a special operating condition, the first filter coefficient is a first value, the second filter coefficient is a second value, and the third filter coefficient is a third value; wherein, the special operating condition includes at least one of the following: the neighboring vehicle is blocked, the neighboring vehicle is a vehicle of the opposite sex, the road where the neighboring vehicle and the vehicle are located is on a curve or a slope, and the lane of the neighboring vehicle is blocked.

[0022] Based on the above means, for normal working conditions, the default first filter coefficient, the second filter coefficient and the third filter coefficient are configured to realize the fusion of the three actual line pressure quantities, which has the characteristics of simple, reliable and accurate implementation.

[0023] In some implementations, when the operating condition indicates that the neighboring vehicle is obscured, the first filter coefficient is greater than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value; when the operating condition indicates that the neighboring vehicle is a vehicle of the opposite sex, the first filter coefficient is greater than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value; when the operating condition indicates that the road on which the neighboring vehicle and the vehicle are located is on a curve or a slope, the first filter coefficient is less than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value; when the operating condition indicates that the lane of the neighboring vehicle is obscured, the first filter coefficient is less than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value.

[0024] Based on the above means, the value of the filter coefficient is adjusted for different special working conditions to reduce the impact of the special working conditions on the actual wire pressing amount and improve the accuracy of the target actual wire pressing amount.

[0025] In a second aspect, the present invention provides a device for determining a lane line pressing amount, the device comprising: an acquisition unit for acquiring the current driving condition of a vehicle; a first determination unit for determining at least two actual line pressing amounts of an adjacent vehicle; the lane where the adjacent vehicle is located is adjacent to the lane where the vehicle is located; and a second determination unit for determining a target actual line pressing amount of the adjacent vehicle based on the operating condition and at least two actual line pressing amounts.

[0026] In a third aspect, the present invention provides an electronic device, which is deployed in the vehicle. The electronic device includes a memory and a processor. The memory stores a computer program or instructions. When the computer program or instructions are executed by the processor, the method provided in the first aspect is implemented.

[0027] The electronic device may be a collection of electronic devices in the vehicle with related processing capabilities.

[0028] In a fourth aspect, the present invention provides a vehicle device, comprising a memory and a processor, wherein the memory stores a computer program or instructions, and when the computer program or instructions are executed by the processor, the method provided in the first aspect is implemented.

[0029] In a fifth aspect, the present invention further provides a storage medium storing a computer program or instructions, which, when executed by a processor, implements the method provided in the first aspect.

[0030] In a sixth aspect, the present invention further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the method provided in the first aspect is implemented.

[0031] It should be noted that the technical effects of the second to sixth aspects can refer to the detailed description of the first aspect above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a first optional structure of a vehicle control system provided by an embodiment of the present invention;

[0033] Figure 2 A second optional structural diagram of a vehicle control system provided by an embodiment of the present invention;

[0034] Figure 3 A third optional structural diagram of a vehicle control system provided by an embodiment of the present invention;

[0035] Figure 4 A fourth optional structural diagram of a vehicle control system provided by an embodiment of the present invention;

[0036] Figure 5 A fifth optional structural diagram of a vehicle control system provided by an embodiment of the present invention;

[0037] Figure 6 A sixth optional structural diagram of a vehicle control system provided by an embodiment of the present invention;

[0038] Figure 7A seventh optional structural diagram of a vehicle control system provided by an embodiment of the present invention;

[0039] Figure 8 A first optional schematic diagram of a semantic segmentation result provided by an embodiment of the present invention;

[0040] Fig. 9 A second optional schematic diagram of a semantic segmentation result provided by an embodiment of the present invention;

[0041] Fig.10 An optional schematic diagram of the wire pressing amount provided in an embodiment of the present invention;

[0042] Fig.11 An optional structural schematic diagram of the pinhole imaging principle provided by an embodiment of the present invention;

[0043] Fig.12 Another optional schematic diagram of the wire pressing amount provided in an embodiment of the present invention;

[0044] Fig.13 An optional schematic diagram of calculating the amount of line pressure of a vehicle frame provided in an embodiment of the present invention;

[0045] Fig.14 An optional flow chart of a process for determining a lane line pressure amount provided in an embodiment of the present invention;

[0046] Fig.15 An optional structural schematic diagram of a device for determining a lane line pressure amount provided in an embodiment of the present invention;

[0047] Fig.16 An optional structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] To make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the specific technical solution of the application will be further described in detail below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0049] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0050] In the following description, the terms "first\second\third" are used only as examples to distinguish different objects, and do not represent a specific order for the objects, nor do they have a limitation on the order of precedence. It is understood that "first\second\third" can be interchanged with a specific order or order of precedence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0052] Embodiments of the present invention provide a vehicle control system, method, storage medium, and program product.

[0053] To facilitate understanding, the scenario of lane line pressure provided in the embodiment of the present application is first described.

[0054] refer to Figure 1 The content shown includes the own vehicle 10 , the neighboring vehicle 20 and the neighboring vehicle 30 .

[0055] The vehicle 10 is currently located in lane 41 , the neighboring vehicle 20 is currently located in lane 42 , and the neighboring vehicle 30 is currently located in lane 43 .

[0056] For the lane crossing amount, if the neighboring vehicle has not crossed the line (the lane line of this vehicle), the minimum distance between the neighboring vehicle and the lane line of this vehicle is determined as the lane crossing amount of the neighboring vehicle; if the neighboring vehicle has crossed the line (the lane line of this vehicle), the maximum distance between the neighboring vehicle and the lane line of this vehicle in the part that exceeds the lane line of this vehicle is determined as the lane crossing amount of the neighboring vehicle.

[0057] refer to Figure 1 From the content shown by the medium thick solid line, it can be seen that the lane pressure amount of the neighboring vehicle 20 is 51, and the lane pressure amount of the neighboring vehicle 30 is 52.

[0058] The following describes various embodiments of the lane pressure determination method, device, equipment, storage medium, and program product provided by the embodiments of the present invention. The lane pressure determination method can be implemented by a lane pressure determination device, and the lane pressure determination device can be deployed in an electronic device including a memory and a processor. The electronic device can be the above Figure 1 The vehicle 10 or a combination of electronic devices in the vehicle 10 having relevant data processing capabilities.

[0059] In a first aspect, an embodiment of the present invention provides a method for determining a lane pressure value, referring to Figure 2The content shown takes the electronic device as the execution subject as an example, and the process may include but is not limited to the following S201 to S203.

[0060] S201. The electronic device obtains the current driving condition of the vehicle.

[0061] This vehicle refers to the vehicle to which the electronic equipment belongs.

[0062] The operating condition is used to characterize the current driving environment of the vehicle. The embodiment of the present application does not limit the type of the operating condition, and can be configured according to actual needs. For example, the operating condition may include special operating conditions and conventional operating conditions.

[0063] Special working conditions may include but are not limited to at least one of the following: the neighboring vehicle is blocked, the road is on a curve or a slope, the neighboring vehicle is a vehicle of the opposite sex, the lane of the neighboring vehicle is blocked, etc.

[0064] Normal working conditions are not special working conditions.

[0065] In a possible implementation, S201 may be implemented as follows: the electronic device acquires images around the vehicle through an image acquisition device, processes and analyzes the acquired images, and obtains the current driving condition of the vehicle. The processing and analysis here may include but are not limited to: vehicle and road line detection and recognition, recognition of whether the vehicle is blocked, recognition of whether there is a ramp, recognition of whether the lane is blocked, etc. The detection and recognition process may be implemented based on commonly used detection and recognition algorithms.

[0066] In another possible implementation, S201 may be implemented as follows: the electronic device receives the current driving condition of the vehicle (eg, driving on a slope, driving on a curve, etc.) sent by other devices (eg, the cloud).

[0067] S202: The electronic device determines at least two actual line-crossing amounts of an adjacent vehicle.

[0068] The lane where the neighboring vehicle is located is adjacent to the lane where this vehicle is located.

[0069] In simple terms, the lane where the vehicle is located can be called the vehicle lane, and the two lanes adjacent to the vehicle lane can be called adjacent vehicle lanes. The adjacent vehicles here refer to vehicles in the adjacent vehicle lanes.

[0070] The amount of the neighboring car pressing the line. If the neighboring car has not pressed the line (the lane line of your vehicle), the minimum distance between the neighboring car and the lane line of your vehicle is determined as the amount of the neighboring car pressing the line. If the neighboring car has pressed the line (the lane line of your vehicle), the maximum distance between the neighboring car and the lane line of your vehicle in the part that exceeds the lane line of your vehicle is determined as the amount of the neighboring car pressing the line.

[0071] In this application, the amount of line pressure can be divided into the actual line pressure and the pixel line pressure. The actual line pressure can also be called the physical line pressure, which is the line pressure of the neighboring car in the world coordinate system. The pixel line pressure is the line pressure of the neighboring car in the camera coordinate system.

[0072] The embodiments of the present application do not limit the specific method for the electronic device to determine at least two actual line pressing amounts, and can be configured according to actual needs. For example, at least two line pressing amounts can be determined based on pure vision, or at least two line pressing amounts can be determined based on vision and other methods (radar or laser).

[0073] The embodiment of the present application does not limit the number of the at least two pressure line amounts. For example, it can be two, three, four, etc., depending on the specific situation.

[0074] S203: The electronic device determines a target actual line pressing amount of the neighboring vehicle based on the working condition and at least two actual line pressing amounts.

[0075] In a possible implementation, the electronic device selects one actual line pressing amount from at least two actual line pressing amounts based on the working conditions as the target actual line pressing amount of the neighboring vehicle.

[0076] In another possible implementation, the electronic device fuses at least two actual line pressing amounts based on the working conditions to obtain a target actual line pressing amount of the neighboring vehicle.

[0077] The method for determining the lane line pressing amount provided in the embodiment of the present application is applied to the vehicle, and the method includes: obtaining the current driving condition of the vehicle; determining at least two actual line pressing amounts of the neighboring vehicle; the lane where the neighboring vehicle is located is adjacent to the lane where the vehicle is located; based on the operating condition and at least two actual line pressing amounts, determining the target actual line pressing amount of the neighboring vehicle.

[0078] In this embodiment, the current driving condition of the vehicle and at least two actual line pressing values ​​are first obtained, and then the target actual line pressing value is determined by combining the condition information and the at least two actual line pressing values. This solution combines the actual working condition when determining the target actual line pressing value, and considers the influence of the actual working condition on the line pressing value, so the determined target actual line pressing value is more accurate.

[0079] Next, a method for determining at least two actual wire pressing amounts of an electronic device is described.

[0080] In a possible implementation, at least two actual wire pressing amounts are determined based on image information acquired by an image collector of the vehicle.

[0081] In this embodiment, at least two actual line pressure amounts are determined based on image information, that is, the actual line pressure amounts are determined based on pure visual methods. Compared with radar sensors and ranging sensors, the characteristics of vision can detect distances, so the applicable distance range is wider, and the calculation stability of pure line of sight is improved, and the calculation dependence is less.

[0082] In another possible implementation, at least two actual wire pressing amounts are determined by image information acquired by an image collector of the vehicle and information acquired by other sensors.

[0083] Other sensors may include but are not limited to at least one of the following: a radar ranging sensor, a laser ranging sensor, an ultrasonic ranging sensor, and the like.

[0084] In this way, by determining at least two actual wire pressing amounts in a variety of ways, the advantages of the various ways can be combined to make the target actual wire pressing amount more accurate.

[0085] Next, the process of the electronic device determining at least two actual line-crossing amounts of the neighboring vehicle in S202 is described.

[0086] The process may include but is not limited to at least two of the following three methods.

[0087] Method 1: Based on the first actual longitudinal distance, determine the first actual line-crossing amount of the adjacent vehicle.

[0088] Method 2: Based on the first actual lateral distance, determine the second actual line-crossing amount of the adjacent vehicle.

[0089] Method 3: Determine the third actual line-crossing amount of the neighboring vehicle based on the vehicle frame of the neighboring vehicle in the world coordinate system.

[0090] The first actual longitudinal distance refers to a reference actual longitudinal distance. A longitudinal distance in a physical coordinate system (world coordinate system) is taken as the first actual longitudinal distance. For example, the actual distance between the vehicle and the neighboring vehicle can be determined as the first actual longitudinal distance.

[0091] The first actual lateral distance refers to a reference actual lateral distance. A lateral distance in a physical coordinate system (world coordinate system) is taken as the first actual lateral distance. For example, the lane width may be determined as the first actual lateral distance, or the lane line width may be determined as the first actual lateral distance.

[0092] In this way, a variety of purely visual methods for determining the actual amount of line pressing are configured, including: determining the actual amount of line pressing based on the first actual longitudinal distance, based on the first actual lateral distance, and based on the vehicle frame of the neighboring vehicle in the world coordinate system. Since the longitudinal distance, lateral distance, and vehicle frame rely on different image detection results, respectively, it is equivalent to determining the actual amount of line pressing through multiple dimensions. In this way, even in some special working conditions, which may affect the accurate determination of the actual amount of line pressing at a certain angle, the target amount of line pressing can be determined in combination with the actual amount of line pressing determined in other dimensions, with higher accuracy.

[0093] Next, the process of determining the first actual line-crossing amount of the neighboring vehicle based on the first actual longitudinal distance in method 1 is described.

[0094] refer to Figure 3 As shown in the content, the process may include but is not limited to S301 to S303.

[0095] S301. The electronic device determines that a first actual longitudinal distance is an actual longitudinal distance between an adjacent vehicle and the vehicle itself.

[0096] In a possible implementation, the electronic device determines the actual longitudinal distance between the neighboring vehicle and the vehicle through images of the neighboring vehicle captured by the vehicle at two different angles.

[0097] In another possible implementation, the electronic device directly measures the neighboring vehicle through a distance measuring sensor to obtain the actual longitudinal distance between the neighboring vehicle and the vehicle itself.

[0098] S302: The electronic device determines the first pixel line pressure amount of the neighboring vehicle based on the image information collected by the image collector.

[0099] The electronic device identifies the neighboring vehicle and the lane line from the image information collected by the image collector, and then directly determines the distance relationship between the neighboring vehicle and the lane line in the image information in the camera coordinate system to obtain the first pixel line pressure of the neighboring vehicle.

[0100] The image collector may be a camera.

[0101] S303: The electronic device determines a first actual line-crossing amount of the neighboring vehicle based on the first actual longitudinal distance, a first pixel line-crossing amount of the neighboring vehicle, and a focal length of the image collector.

[0102] The electronic device determines the first actual line pressing amount of the neighboring vehicle based on the first actual longitudinal distance, the first pixel line pressing amount of the neighboring vehicle and the focal length of the image collector through the principle of pinhole imaging (equal ratio). For example, the ratio of the first actual longitudinal distance to the focal length is determined as the first ratio, and the ratio of the first actual line pressing amount of the neighboring vehicle to the first pixel line pressing amount of the neighboring vehicle is determined as the second ratio. Through the pinhole imaging principle, it can be obtained that the first ratio is equal to the second ratio, so that the first actual line pressing amount of the neighboring vehicle can be obtained.

[0103] It can be seen that in method 1, since the actual longitudinal distance between the neighboring vehicle and the vehicle can generally be determined, the actual longitudinal distance between the neighboring vehicle and the vehicle is taken as the first actual longitudinal distance, and then the first pixel pressure line amount of the neighboring vehicle is determined based on the image information collected by the image collector, that is, the pixel value of the first pressure line amount can be obtained. In this way, the first actual pressure line amount of the neighboring vehicle is determined based on the first actual longitudinal distance, the first pixel pressure line amount of the neighboring vehicle and the focal length of the image collector. It can be seen that the entire implementation principle relies on the longitudinal distance and the pixel distance, and has the characteristics of simple implementation.

[0104] Next, the process of determining the second actual line-crossing amount of the neighboring vehicle based on the first actual lateral distance in method 2 is described.

[0105] refer to Figure 4 As shown in the content, the process may include but is not limited to S401 to S404.

[0106] S401. The electronic device determines that the first actual lateral distance is the actual width of the lane where the adjacent vehicle is located.

[0107] The actual width of the lane may be detected by the electronic device, or transmitted to the electronic device by other devices (such as a cloud device corresponding to a map application).

[0108] S402: The electronic device determines the second pixel line pressure amount of the neighboring vehicle based on the image information collected by the image collector.

[0109] The implementation of S402 may refer to the description in S302, which will not be described in detail here. The second pixel line pressing amount may be the same as or different from the first pixel line pressing amount.

[0110] S403: The electronic device determines the lane pixel distance of the lane where the adjacent vehicle is located based on the image information collected by the image collector.

[0111] The electronic device identifies the neighboring vehicle and lane lines from the image information collected by the image collector, and then directly determines the lane pixel distance of the lane where the neighboring vehicle is located in the camera coordinate system.

[0112] S404: The electronic device determines a second actual line-pressing amount of the neighboring vehicle based on the first actual lateral distance, the second pixel line-pressing amount of the neighboring vehicle, and the lane pixel distance of the lane where the neighboring vehicle is located.

[0113] The electronic device determines the second actual line pressure amount of the adjacent vehicle based on the first actual lateral distance, the second pixel line pressure amount of the adjacent vehicle and the lane pixel distance of the lane where the adjacent vehicle is located, by the principle that the ratio of the actual distance is the same as the ratio of the pixel distance.

[0114] In this embodiment, since the actual width of the lane is generally known, the actual width of the lane can be determined as the first actual lateral distance, and then the second pixel line pressing amount of the adjacent vehicle can be determined based on the image information collected by the image collector, that is, the pixel value of the second line pressing amount can be obtained. In this way, the second actual line pressing amount is determined based on the first actual lateral distance, the second pixel line pressing amount of the adjacent vehicle and the lane pixel distance of the adjacent vehicle. It can be seen that the entire implementation principle relies on the lateral distance and the pixel distance, and is simple to implement.

[0115] Next, the process of determining the third actual line-crossing amount of the neighboring vehicle based on the vehicle frame of the neighboring vehicle in the world coordinate system in method 3 is described.

[0116] refer to Figure 5 As shown in the content, the process may include but is not limited to S501 to S503.

[0117] S501. The electronic device determines a vehicle frame of a neighboring vehicle in a world coordinate system based on image information acquired by an image collector.

[0118] The calculation results of other modules of the electronic device know the distance of the neighboring vehicle from the vehicle, the length, width, height, and heading angle of the neighboring vehicle. The four vertices of the bottom projection surface of the neighboring vehicle in the physical coordinate system can be obtained, and the vehicle frame is determined based on the four vertices.

[0119] S502: The electronic device determines the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system based on the image information collected by the image collector.

[0120] The lane line curve equation is output by the lane line module of the electronic device.

[0121] S503, the electronic device determines a third actual line-crossing amount of the neighboring vehicle based on the vehicle frame of the neighboring vehicle in the world coordinate system and the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system.

[0122] The electronic device first determines the intersection point between the vehicle frame and the curve, and then determines a third actual line-pressing amount of the neighboring vehicle based on the definition of the line-pressing amount.

[0123] It can be seen that method 3, when determining the third actual crossing amount of the neighboring vehicle, is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system and the curve of the lane line between the neighboring vehicle and the vehicle in the world coordinate system. It can be seen that the entire implementation principle relies on the formulation of the curve and the determination of the vehicle frame, and is simple to implement.

[0124] Next, the process of determining the target actual line pressing amount of the neighboring vehicle by the electronic device based on the working condition and at least two actual line pressing amounts in S203 is described.

[0125] In one possible implementation, reference Figure 6 As shown in the content, the process may include but is not limited to the following S601 to S603.

[0126] S601. The electronic device inputs at least two actual line pressure values ​​into a filter.

[0127] The embodiment of the present application does not limit the type of filter, and can be configured according to actual needs. For example, a Kalman filter or an extended Kalman filter can be selected here.

[0128] The electronic device inputs at least two actual wire pressing quantities as filter inputs to the filter.

[0129] S602: The electronic device configures a filter coefficient corresponding to each of at least two actual wire pressing amounts in a filter based on the working condition to obtain a target filter.

[0130] In a possible implementation, a different filter coefficient is configured for each actual wire pressing amount, that is, one filter coefficient corresponds to one actual wire pressing amount.

[0131] In another possible implementation, multiple filter coefficients are configured for at least two actual thread pressing amounts, and one filter coefficient may correspond to one or more actual thread pressing amounts. For example, when the determination of two actual thread pressing amounts is similar, one filter coefficient may be configured for the two actual thread pressing amounts.

[0132] Here, the filter with configured filter coefficients is determined as the target filter.

[0133] S603: The electronic device filters at least two actual wire pressing amounts through a target filter to obtain a target actual wire pressing amount.

[0134] The electronic device runs a target filter, filters and fuses at least two actual wire pressing amounts through a filter coefficient in the target filter, and obtains a target actual wire pressing amount.

[0135] In this embodiment, at least two actual wire pressing amounts are fused through a filter to obtain a target actual wire pressing amount. Compared with selecting one from at least two actual wire pressing amounts, this solution can combine the advantages of each actual wire pressing amount and obtain a higher accuracy.

[0136] Next, the process of obtaining a target filter by configuring a filter coefficient corresponding to each of at least two actual wire pressing amounts in a filter by the electronic device based on the working condition in S602 is described.

[0137] In a possible implementation manner, when the at least two actual thread pressing amounts include a first actual thread pressing amount, a second actual thread pressing amount, and a third actual thread pressing amount, reference Figure 7 As shown in the content, the process may include but is not limited to the following S701 to S703.

[0138] The first actual line pressing amount is determined based on the first actual longitudinal distance, the second actual line pressing amount is determined based on the first actual lateral distance, and the third actual line pressing amount is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system.

[0139] S701. The electronic device configures a coefficient of a first actual line pressure amount as a first filter coefficient based on working conditions.

[0140] Here, the first actual line pressure value corresponds to the first filter coefficient, and the value of the first filter coefficient is determined according to the actual working conditions.

[0141] S702: The electronic device configures a coefficient of a second actual line pressure amount as a second filter coefficient based on the working condition.

[0142] Here, the second actual line pressure value corresponds to the second filter coefficient, and the value of the second filter coefficient is determined according to the actual working conditions.

[0143] S703: The electronic device configures a coefficient of a third actual line pressure amount as a third filter coefficient based on the working condition.

[0144] Here, the third actual line pressure value corresponds to the third filter coefficient, and the value of the third filter coefficient is determined according to the actual working conditions.

[0145] In this embodiment, the first filter coefficient is configured according to the filter coefficient corresponding to the first actual line pressing amount determined based on the first actual longitudinal distance, the second filter coefficient is configured according to the filter coefficient corresponding to the second actual line pressing amount determined by the first actual lateral distance, and the third filter coefficient is configured according to the filter coefficient corresponding to the third actual line pressing amount determined based on the vehicle frame of the neighboring vehicle in the world coordinate system. The three actual line pressing amounts are integrated by these three filter coefficients, which has the characteristics of simple, reliable and accurate implementation.

[0146] Next, the configuration of filter coefficients under normal working conditions is described.

[0147] When the operating condition does not belong to a special operating condition, the first filter coefficient is a first value, the second filter coefficient is a second value, and the third filter coefficient is a third value; wherein, the special operating condition includes at least one of the following: the neighboring vehicle is blocked, the neighboring vehicle is a vehicle of the opposite sex, the road where the neighboring vehicle and the vehicle are located is on a curve or a slope, and the lane of the neighboring vehicle is blocked.

[0148] There is no limitation on the numerical values ​​of the first value, the second value and the third value, which can be configured according to actual needs.

[0149] For example, the first value, the second value, and the third value may all be determined as one third based on the principle of average.

[0150] For another example, the numerical values ​​of the first value, the second value, and the third value may be configured according to the importance or accuracy of the determination method of the first actual line pressing amount, the second actual line pressing amount, and the third actual line pressing amount. The higher the importance and the greater the accuracy, the greater the corresponding value.

[0151] In this embodiment, for normal working conditions, the default first filter coefficient, the second filter coefficient and the third filter coefficient are configured to realize the fusion of the three actual wire pressing quantities, which has the characteristics of simple, reliable and accurate implementation.

[0152] The following describes how to configure the filter coefficients under special working conditions.

[0153] When the working condition indicates that the neighboring vehicle is blocked, the first filter coefficient is greater than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value.

[0154] Since the neighboring car is blocked, the accuracy of the pixel distance is affected. Therefore, the first filter coefficient is increased, the second filter coefficient is increased, and the third filter coefficient is decreased to reduce the impact of the neighboring car on the accuracy of the target line pressure under the condition that the neighboring car is blocked.

[0155] When the working condition indicates that the neighboring vehicle is a vehicle of the opposite sex, the first filter coefficient is greater than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value.

[0156] Opposite-sex vehicles include: trucks, tractors, etc.

[0157] In this way, the heterogeneous vehicle will affect the accuracy of the vehicle frame, resulting in lower accuracy of the third actual line pressing amount. The heterogeneous vehicle also affects the accuracy of the longitudinal distance detection. Therefore, the first filter coefficient is increased, the second filter coefficient is decreased, and the third filter coefficient is increased to reduce the impact of the heterogeneous vehicle working condition on the accuracy of the target line pressing amount.

[0158] When the working condition indicates that the road where the neighboring vehicle and the vehicle are located is on a curve or a slope, the first filter coefficient is less than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value.

[0159] In this way, the curve or ramp affects the dotted line fitting, so the accuracy of the third actual pressure line amount is affected, so the third filter coefficient is increased, and the first filter coefficient and the second filter coefficient are increased.

[0160] For the case of a curve, the lane width may sometimes be affected. If the lane width is affected, the second filter coefficient may be increased accordingly. If the lane width is known, it will not be affected. If the lane width is detected and calculated by itself, it may be affected.

[0161] When the working condition indicates that the lane of the neighboring vehicle is blocked, the first filter coefficient is less than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value.

[0162] Since the lane line is blocked, the accuracy of the lane width is affected, so the accuracy of the second actual line pressure amount is reduced, so the second filter coefficient is correspondingly reduced, and the first filter coefficient and the third filter coefficient are increased.

[0163] In this embodiment, the value of the filter coefficient is adjusted for different special working conditions to reduce the impact of the special working conditions on the actual wire pressing amount and improve the accuracy of the target actual wire pressing amount.

[0164] Below, an embodiment is taken as an example to illustrate the process of determining the lane line pressure amount provided by this embodiment of the present invention.

[0165] This embodiment is used in the field of off-vehicle vision technology in autonomous driving, and is specifically applied to the calculation of the amount of line pressure in the relationship between the vehicle target and the lane line in the post-processing of off-vehicle vision in autonomous driving.

[0166] As autonomous driving technology continues to mature and its commercial applications advance, the technology is becoming more and more mature, the actual working conditions that need to be dealt with are becoming more and more complex, and the requirements for the calculation accuracy of the target vehicle's related attributes are also becoming higher and higher.

[0167] The two most important elements in autonomous driving are the vehicles on the road and the lane lines. The relationship between the target vehicle (equivalent to the neighboring vehicle mentioned above) and the lane lines, and the amount of line pressure, determine the path planned by the vehicle and whether to perform avoidance actions such as braking. When other vehicles change lanes or invade the lane, the relationship between the vehicle and the lane lines is comprehensively considered to formulate the optimal driving strategy and path planning to ensure that the autonomous driving vehicle can drive safely and stably according to the planned path and strategy.

[0168] For determining the relationship between the target vehicle and the lane line, the related technical solutions include: using multiple sensors such as laser and radar to comprehensively calculate the amount of lane crossing. This embodiment can calculate the amount of lane crossing by a single visual sensor, that is, without other sensors or other sensors are not effective, and calculate the accurate amount of lane crossing by a single visual sensor.

[0169] At present, the calculation and application of the amount of wire pressing are based on the results of multi-sensor fusion. In this embodiment, a method for calculating the amount of wire pressing based on pure vision is proposed. Due to the characteristics of vision, the distance that can be applied is farther, the calculation stability is improved, and the calculation dependence is less.

[0170] According to the detection of the target input by the front end, these images and other modules are used to calculate the amount of the target line pressure. The calculation of the amount of pressure in this embodiment refers to the relationship between the target vehicle and the left and right lane lines of the vehicle. The calculation information input to this front end from the neural network and other modules includes: wheel detection frame, rear detection frame, segmentation result, lane line fitting curve, and target distance.

[0171] The specific implementation may include but is not limited to the following steps 1 to 5.

[0172] Step 1: Input verification.

[0173] The line-crossing amount in this embodiment refers to the relationship between the target vehicle and the corresponding left and right lane lines of the host vehicle, including: the relationship between the left lane target and the left lane line, and the relationship between the right lane target and the right lane line. If the target has crossed the line, the line-crossing amount is the maximum length of entering the host lane. If the target has not crossed the line, the line-crossing amount is the shortest distance between the target vehicle and the corresponding lane.

[0174] First, determine whether the target of the left / right lane to be calculated has a corresponding lane line. If so, execute step 2, otherwise, end.

[0175] Step 2: Calculate the amount of pressure in the image domain.

[0176] According to the semantic segmentation information of the input vehicle target and the semantic segmentation information of the lane line, the pixel distance between the target vehicle and the corresponding nearest left and right lane lines is calculated at the semantic segmentation level. And the longitudinal distance of the target vehicle calculated by the intrinsic reference distance measurement is known, and the line pressure is calculated according to the pinhole imaging principle.

[0177] The target vehicle's internal parameter distance measurement results calculated by other modules, the curve equation of the lane line, and the image information are used to preliminarily determine which lane the vehicle is in. Figure 8 The semantic segmentation result shown in FIG. 8 is based on the image semantic segmentation result, and the semantic segmentation result within the vehicle frame is traversed to find the side segmentation line 801 of the target vehicle. Fig. 9The semantic segmentation result shown is based on the semantic segmentation information of the lane line, and the segmentation point output of the lane line module, and the segmentation point 802 of the inner edge of the left and right lane lines of the vehicle is traversed. If the target vehicle is in the left lane, the segmentation point of the target vehicle is traversed and the segmentation point of the left lane line with the same horizontal coordinate is subtracted (the difference between the right lane target calculation and the right lane segmentation point) to confirm whether the segmentation point of the target vehicle enters the interior of the lane, that is, crosses the line.

[0178] At this time, calculate the maximum pixel distance (dis_img) of each segmentation point of the target vehicle entering the lane, and record this segmentation point as A(xa,ya). If it does not exist, calculate the minimum pixel distance of each segmentation point of the target vehicle from the corresponding (left or right) lane, and record this segmentation point as A(xa,ya). Given the target longitudinal distance (dis_obj) calculated by other modules, calculate the line pressure amount (dist_parsing) according to the characteristic pinhole imaging principle of the visual camera.

[0179] Among them, the pressure line amount can refer to Fig.10 The content shown includes lane line 1001 and line pressure amount 1002.

[0180] The principle of pinhole imaging can be referred to the following formula (1) and Fig.11 The content shown.

[0181] dist_parsing / dis_img=dis_obj / fu formula (1);

[0182] In formula (1), dist_parsing represents the amount of line crossing, dis_img represents the maximum pixel distance of each segmentation point of the target vehicle entering the lane, dis_obj represents the target longitudinal distance (equivalent to the first actual longitudinal distance mentioned above), and fu represents the focal length of the camera.

[0183] The principle of pinhole imaging can be referred to Fig.11 The contents shown include: the line crossing amount 1101, the maximum pixel distance 1102 of each segmentation point of the target vehicle entering the lane, the target longitudinal distance 1103 and the camera focal length 1104.

[0184] Step 3: Calculate lane width and pressure

[0185] Determine whether the lane line has a valid output. If it is a valid output, according to the lane line curve equation y=C0+C1x+C2x2+C3X3, the lane line width is C0. The pressure line pixel distance dis_img of the segmentation point of the target vehicle edge line has been calculated by step 1. Traverse the segmentation points of the lane line of the lane where dis_img is located, and obtain the segmentation points of the left and right lanes corresponding to the pressure line point A(xa,ya) and record them as L(xl,yl) and R(xr,yr) respectively. Calculate the lane line pixel width Wlane=R(xr,yr)-L(xl,yl) at the segmentation point. The default lane width is 3.6m, and the pressure line amount calculated according to the ratio is dist_Wlane / dis_pic=C0 / (R(xr,yr)-L(xl,yl)).

[0186] refer to Fig.12 The content shown includes the vehicle 1201 , the target vehicle 1202 , the lane width 1203 , and the line crossing amount 1204 .

[0187] Step 4: Calculate the amount of pressure line according to the target distance.

[0188] The physical distance, length, width, height, and heading angle of the target (equivalent to the neighboring vehicle) are known from the calculation results of other modules. The vehicle frame (box) of the target in the physical world and the four vertices of the bottom projection surface of the target (box_x1, box_y1), (box_x2, box_y2), (box_x3, box_y3), (box_x0, box_y0) can be obtained. The lane curve equation y=C0+C1x+C2x2+C3X3 output by the lane module.

[0189] The amount of crossing the lane is calculated based on the relationship between the four vertices of the target vehicle and the corresponding lane.

[0190] The vehicle frame can be calculated by referring to the pressure line Fig.13 The content shown includes the host vehicle 1301, the target vehicle 1302, and the four vertices of the target vehicle (13021, 13022, 13023, and 13024).

[0191] Step 5: Sequential filtering.

[0192] The above three calculation results of the wire pressing amount are used as observations, different observation noises are set, and they enter the extended Kalman filter in turn. The prediction process of the filter is set to the state value of this cycle equal to the state value of the previous cycle (the wire pressing amount result). According to the detection characteristics of the perception model and the influencing factors of pinhole imaging. The observation noise of the wire pressing amount obtained by the above three calculation methods under different working conditions is set, and the observation noise variance matrix required by the filter is set according to these noises.

[0193] 1) Set according to the occlusion status.

[0194] If the perception neural network model detects that the target is occluded, the semantic segmentation effect will be poor, and the noise of the parsing image domain line compression (equivalent to the first actual line compression) needs to be set to the maximum. The line compression calculated based on the target distance of the previous multi-frame filtering is more reliable, and the observation noise is set to the minimum.

[0195] 2) Set according to the target type.

[0196] If the target is a truck or a special-shaped vehicle, based on past experience, the ranging error will be large. Therefore, when the target is detected as a truck or a large special-shaped vehicle, the observation noise of the line pressing amount calculated based on the box (equivalent to the third actual line pressing amount mentioned above) needs to be increased, and the other two observation noises should be set to smaller values.

[0197] 3) Set according to road conditions.

[0198] According to the characteristics of vision and past experience, when on a curve or up or down a ramp, the visual imaging is easily disturbed, resulting in deviations in the calculated distance of the target vehicle and the lane line coefficient in the VCS coordinate system. Therefore, if it is determined that the lane line curvature in the lane line coefficient calculated by the lane line module is very small, it means that it is a curve at this time. The method of step four (equivalent to the third actual line pressing amount) sets a large noise, which is equivalent to ignoring it. Since the lane width of the curve cannot be accurately calculated, the noise of step three (equivalent to the above-mentioned second actual line pressing amount) is also set to be large. Under this working condition, the main information comes from the calculation result of the first actual line pressing amount.

[0199] refer to Fig.14 As shown in the content, the process of determining the lane line pressure amount may include but is not limited to the following S1401 to S1408.

[0200] S1401, start;

[0201] S1402, determining whether there is a lane line;

[0202] If yes, execute the following S1403; if no, execute the following S1408;

[0203] S1403, calculating the amount of line pressure in the image domain;

[0204] S1404, lane width line pressure calculation;

[0205] S1405, calculating the line pressing amount according to the target distance;

[0206] S1406, setting noise;

[0207] S1407, Sequential Filtering

[0208] S1408, end.

[0209] This embodiment calculates the amount of line pressure based on a pure visual method, without relying on other sensors; it uses the information of images and world coordinates, and adopts multiple methods to calculate the fusion of line pressure, which improves the calculation accuracy, and due to the application of long-focus and short-focus cameras, the calculation distance is farther. Multiple observations are used to perform sequential filtering with an unscented Kalman filter, which improves the stability of calculating the amount of line pressure.

[0210] In a second aspect, an embodiment of the present application provides a device for determining a lane pressure amount, referring to Fig.15 As shown in the content, the lane pressure determination device 150 includes an acquisition unit 1501, a first determination unit 1502 and a second determination unit 1503.

[0211] The acquisition unit 1501 is used to acquire the current driving condition of the vehicle;

[0212] The first determining unit 1502 is used to determine at least two actual line crossing amounts of an adjacent vehicle; the lane where the adjacent vehicle is located is adjacent to the lane where the vehicle is located;

[0213] The second determining unit 1503 is used to determine a target actual line pressing amount of the neighboring vehicle based on the working condition and at least two actual line pressing amounts.

[0214] In some embodiments, at least two actual line pressing amounts are determined based on image information acquired by an image collector of the vehicle.

[0215] In some embodiments, the first determining unit 1502 is further configured to perform at least two of the following:

[0216] Based on the first actual longitudinal distance, determining a first actual line-crossing amount of the neighboring vehicle;

[0217] Based on the first actual lateral distance, determining a second actual line-crossing amount of the adjacent vehicle;

[0218] Based on the vehicle frame of the neighboring vehicle in the world coordinate system, the third actual line-crossing amount of the neighboring vehicle is determined.

[0219] In some embodiments, the first determination unit 1502 is also used to: determine the first actual longitudinal distance as the actual longitudinal distance between the neighboring vehicle and the vehicle; determine the first pixel pressure line amount of the neighboring vehicle based on the image information collected by the image collector; determine the first actual pressure line amount of the neighboring vehicle based on the first actual longitudinal distance, the first pixel pressure line amount of the neighboring vehicle and the focal length of the image collector.

[0220] In some embodiments, the first determination unit 1502 is further used to: determine the first actual lateral distance as the actual lane width of the lane where the adjacent vehicle is located; determine the second pixel line pressure amount of the adjacent vehicle based on the image information collected by the image collector; determine the lane pixel distance of the lane where the adjacent vehicle is located based on the image information collected by the image collector; determine the second actual line pressure amount of the adjacent vehicle based on the first actual lateral distance, the second pixel line pressure amount of the adjacent vehicle, and the lane pixel distance of the lane where the adjacent vehicle is located.

[0221] In some embodiments, the first determination unit 1502 is also used to: determine the vehicle frame of the neighboring vehicle in the world coordinate system based on the image information collected by the image collector; determine the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system based on the image information collected by the image collector; determine the third actual line pressing amount of the neighboring vehicle based on the vehicle frame of the neighboring vehicle in the world coordinate system and the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system.

[0222] In some embodiments, the second determination unit 1503 is also used to: input at least two actual wire pressing quantities into the filter; configure the filter coefficient corresponding to each of the at least two actual wire pressing quantities in the filter based on the working condition to obtain a target filter; filter at least two actual wire pressing quantities through the target filter to obtain a target actual wire pressing quantity.

[0223] In some embodiments, the second determination unit 1503 is also used to: based on the operating conditions, configure the coefficient of the first actual line pressing amount as the first filter coefficient; based on the operating conditions, configure the coefficient of the second actual line pressing amount as the second filter coefficient; based on the operating conditions, configure the coefficient of the third actual line pressing amount as the third filter coefficient; wherein the first actual line pressing amount is determined based on the first actual longitudinal distance, the second actual line pressing amount is determined based on the first actual lateral distance, and the third actual line pressing amount is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system.

[0224] In some embodiments, when the operating condition does not belong to a special operating condition, the first filter coefficient is a first value, the second filter coefficient is a second value, and the third filter coefficient is a third value; wherein, the special operating condition includes at least one of the following: the neighboring vehicle is blocked, the neighboring vehicle is a vehicle of the opposite sex, the road on which the neighboring vehicle and the vehicle are located is on a curve or a slope, and the lane of the neighboring vehicle is blocked.

[0225] In some embodiments, when the operating condition indicates that the neighboring vehicle is obscured, the first filter coefficient is greater than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value; when the operating condition indicates that the neighboring vehicle is a vehicle of the opposite sex, the first filter coefficient is greater than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value; when the operating condition indicates that the road where the neighboring vehicle and the vehicle are located is on a curve or a slope, the first filter coefficient is less than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value; when the operating condition indicates that the lane of the neighboring vehicle is obscured, the first filter coefficient is less than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value.

[0226] In a third aspect, an embodiment provides an electronic device, which is deployed in the vehicle. The electronic device includes a memory and a processor. The memory stores a computer program or instructions. When the computer program or instructions are executed by the processor, the method provided in the first aspect is implemented.

[0227] The electronic device may be a collection of electronic devices in the vehicle with related processing capabilities.

[0228] In one example, reference Fig.16 As shown in the content, the electronic device 160 includes: a processor 1601, at least one communication bus 1602, a user interface 1603, at least one external communication interface 1604 and a memory 1605. Among them, the communication bus 1602 is configured to realize the connection communication between these components. Among them, the user interface 1603 may include a device for receiving user input, and the external communication interface 1604 may include a standard wired interface and a wireless interface.

[0229] The memory 1605 is configured to store instructions and applications executable by the processor 1601, and can also cache data to be processed or processed by the processor 1601 and various modules in the electronic device (for example, image data, audio data, voice communication data, and video communication data), which can be implemented through flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0230] In a fourth aspect, this embodiment provides a vehicle device, the vehicle device includes a memory and a processor, the memory stores a computer program or instructions, and when the computer program or instructions are executed by the processor, the method provided in the first aspect is implemented.

[0231] In a fifth aspect, an embodiment provides a storage medium, that is, a computer-readable storage medium, on which a computer program or instructions are stored. When the computer program or instructions are executed by a processor, the method provided in the first aspect is implemented.

[0232] In a sixth aspect, an embodiment provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the method provided in the first aspect is implemented.

[0233] It should be noted here that the description of the above storage medium, device, apparatus and program product embodiments is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the storage medium, device, apparatus and program product embodiments, please refer to the description of the method embodiment for understanding.

[0234] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments, the size of the sequence number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment. The above-mentioned embodiment sequence numbers are for description only and do not represent the advantages and disadvantages of the embodiments.

[0235] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0236] In the several embodiments provided in this embodiment, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0237] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0238] In addition, all functional units in each embodiment may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0239] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0240] Alternatively, if the above-mentioned integrated unit is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0241] The above are only embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the disclosed technical scope, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for determining lane line pressure, characterized in that: The method comprises: Get the current driving condition of the vehicle; Determine at least two actual line-crossing values ​​of an adjacent vehicle; the lane where the adjacent vehicle is located is adjacent to the lane where the own vehicle is located; Based on the working condition and the at least two actual line pressing amounts, a target actual line pressing amount of the neighboring vehicle is determined.

2. The method according to claim 1, characterized in that The at least two actual line pressing amounts are determined based on image information acquired by the image collector of the vehicle.

3. The method according to claim 1, characterized in that Determining at least two actual line crossing amounts of the neighboring vehicle includes at least two of the following: Based on the first actual longitudinal distance, determining a first actual line-crossing amount of the neighboring vehicle; Determining a second actual line-crossing amount of the neighboring vehicle based on the first actual lateral distance; Based on the vehicle frame of the neighboring vehicle in the world coordinate system, a third actual line-crossing amount of the neighboring vehicle is determined.

4. The method according to claim 3, characterized in that: The determining, based on the first actual longitudinal distance, a first actual line-crossing amount of the neighboring vehicle includes: Determining the first actual longitudinal distance as the actual longitudinal distance between the neighboring vehicle and the own vehicle; Determine the first pixel line pressure amount of the neighboring vehicle based on the image information collected by the image collector; A first actual line pressing amount of the neighboring vehicle is determined based on the first actual longitudinal distance, the first pixel line pressing amount of the neighboring vehicle, and the focal length of the image collector.

5. The method according to claim 3, characterized in that: The determining, based on the first actual lateral distance, a second actual line-crossing amount of the adjacent vehicle includes: Determining the first actual lateral distance as the actual width of the lane where the adjacent vehicle is located; Determine the second pixel line pressure amount of the neighboring vehicle based on the image information collected by the image collector; Determining the lane pixel distance of the lane where the adjacent vehicle is located based on the image information collected by the image collector; The second actual line pressing amount of the neighboring vehicle is determined based on the first actual lateral distance, the second pixel line pressing amount of the neighboring vehicle, and the lane pixel distance of the lane where the neighboring vehicle is located.

6. The method according to claim 3, characterized in that The determining, based on the vehicle frame of the neighboring vehicle in the world coordinate system, a third actual line-crossing amount of the neighboring vehicle includes: Based on the image information collected by the image collector, determining the vehicle frame of the neighboring vehicle in the world coordinate system; Based on the image information collected by the image collector, determine the curve of the lane line between the neighboring vehicle and the own vehicle in the world coordinate system; A third actual lane-crossing amount of the neighboring vehicle is determined based on a vehicle frame of the neighboring vehicle in the world coordinate system and a curve of a lane line between the neighboring vehicle and the host vehicle in the world coordinate system.

7. The method according to any one of claims 1 to 6, characterized in that: The determining, based on the working condition and the at least two actual line pressing amounts, a target actual line pressing amount of the neighboring vehicle includes: Inputting the at least two actual wire pressing quantities into a filter; Based on the working condition, configure the filter coefficient corresponding to each of the at least two actual wire pressing amounts in the filter to obtain a target filter; The at least two actual wire pressing amounts are filtered by the target filter to obtain the target actual wire pressing amount.

8. The method according to claim 7, characterized in that In a case where the at least two actual wire pressing amounts include a first actual wire pressing amount, a second actual wire pressing amount, and a third actual wire pressing amount, configuring a filter coefficient corresponding to each of the at least two actual wire pressing amounts in the filter based on the working condition to obtain a target filter includes: Based on the working condition, configuring a coefficient of the first actual wire pressing amount as a first filtering coefficient; Based on the working condition, configuring a coefficient of the second actual wire pressing amount as a second filtering coefficient; Based on the working condition, configuring the coefficient of the third actual wire pressing amount as a third filtering coefficient; Among them, the first actual line pressing amount is determined based on the first actual longitudinal distance, the second actual line pressing amount is determined based on the first actual lateral distance, and the third actual line pressing amount is determined based on the vehicle frame of the neighboring vehicle in the world coordinate system.

9. The method according to claim 8, characterized in that When the operating condition does not belong to a special operating condition, the first filter coefficient is a first value, the second filter coefficient is a second value, and the third filter coefficient is a third value; Among them, the special working conditions include at least one of the following: the neighboring vehicle is blocked, the neighboring vehicle is a vehicle of the opposite sex, the road where the neighboring vehicle and the vehicle are located is on a curve or a slope, and the lane of the neighboring vehicle is blocked.

10. The method according to claim 9, characterized in that When the working condition indicates that the neighboring vehicle is blocked, the first filter coefficient is greater than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value; When the working condition indicates that the neighboring vehicle is a vehicle of the opposite sex, the first filter coefficient is greater than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value; When the working condition indicates that the road where the neighboring vehicle and the own vehicle are located is on a curve or a slope, the first filter coefficient is less than the first value, the second filter coefficient is less than the second value, and the third filter coefficient is greater than the third value; When the operating condition indicates that the lane of the neighboring vehicle is blocked, the first filter coefficient is less than the first value, the second filter coefficient is greater than the second value, and the third filter coefficient is less than the third value.

11. A device for determining lane line pressure, characterized in that: The device comprises: An acquisition unit, used to acquire the current driving condition of the vehicle; The first determining unit is used to determine at least two actual line-crossing values ​​of an adjacent vehicle; the lane where the adjacent vehicle is located is adjacent to the lane where the own vehicle is located; The second determination unit is used to determine the target actual line pressing amount of the neighboring vehicle based on the working condition and the at least two actual line pressing amounts.

12. An electronic device, characterized in that: The electronic device is deployed in the vehicle, and includes a memory and a processor. The memory stores a computer program or instruction. When the computer program or instruction is executed by the processor, the method described in any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium, characterized in that: The storage medium stores a computer program or an instruction, and when the computer program or the instruction is executed by the processor, the method according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that The computer program product comprises a computer program or instructions, and when the computer program or instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images