A tunnel lane line recognition method, device, equipment and storage medium

Abstract

A tunnel lane line identification method, device and equipment and storage medium, relating to the intelligent driving technical field, wherein the tunnel lane line identification method comprises: when the road side lane line is lost, fitting the road side lane line according to the coordinate information of the identified road side target object. The application can fit the lane line based on the road side target object, does not need to lay out the road sign in the tunnel, realizes low cost, and can effectively ensure the driving safety of the vehicle when the lane line is lost in vision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, in particular to a tunnel lane line identification method, device and equipment and a storage medium. BACKGROUND

[0002] Currently, lane lines often appear blurred after being worn out from a visual perspective, resulting in the inability to identify lane lines. For example, in a tunnel, the middle lane line is often clear, but the lane line on the side of the road edge is not clear. At this time, due to the inability to identify the lane line on the side of the road edge, the vehicle may deviate slightly in the tunnel, which is prone to cause a collision between the vehicle and the road edge.

[0003] In related technologies, one processing method is to calculate a fused lane line based on a front radar, an angle radar, a surround view camera, and a front camera; another processing method is to obtain lane line information corresponding to at least two sensors, and to preprocess the lane line information; to determine a confidence degree corresponding to the preprocessed lane line information; to determine a weight coefficient corresponding to the lane line information based on the confidence degree and the preprocessed lane line information; and to determine fused processed lane line data based on the weight coefficient and the preprocessed lane line information.

[0004] However, in the above method, tunnel positioning needs to be achieved by laser SLAM, and the lost lane line information needs to be obtained by a high-precision map, that is, a laser radar must be equipped and tunnel positioning must be achieved, which is high in cost and difficult in technology. Moreover, the multi-source fusion method needs to be output by multiple sources to ensure accuracy, and cannot deal with the situation of visual loss of lane lines in a tunnel. Therefore, the current solution cannot solve the problem of visual loss of lane lines in a tunnel by a low-cost method. SUMMARY

[0005] The present application provides a tunnel lane line identification method, device, equipment and storage medium, which can fit lane lines on the side of a road edge target based on the road edge target, without a laser radar and without road markers in a tunnel, thereby achieving low cost and effectively ensuring the driving safety of a vehicle when lane lines are visually lost.

[0006] In a first aspect, an embodiment of the present application provides a tunnel lane line identification method, which comprises:

[0007] When the lane line on the side of the road edge is lost, a lane line on the side of the road edge is fitted according to the coordinate information of the identified target on the side of the road edge.

[0008] In combination with the first aspect, in an implementation mode, the lane line on the side of the road edge is fitted according to the coordinate information of the target on the side of the road edge, which comprises:

[0009] A distance of the vehicle from the middle lane line is determined.

[0010] determine a distance of the ego vehicle from the road-side lane line according to the lane width and the distance of the ego vehicle from the middle lane line;

[0011] screen out road-side targets that meet the longitudinal relative distance and the lateral relative distance limit conditions simultaneously, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the lateral relative distance is determined based on the distance of the ego vehicle from the road-side lane line;

[0012] fit the road-side lane line based on coordinate information of all the screened-out road-side targets when the road-side lane line is lost.

[0013] In combination with the first aspect, in an implementation, the screening out of the road-side targets that meet the longitudinal relative distance and the lateral relative distance limit conditions simultaneously, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the lateral relative distance is determined based on the distance of the ego vehicle from the road-side lane line, comprises:

[0014] determine the longitudinal relative distance x according to the inequality 0 < x < N, wherein N is the maximum identifiable distance;

[0015] when the road-side target is located on the left side of the ego vehicle, determine the lateral relative distance y according to the inequality M + Δl < y < M + Δl + m;

[0016] when the road-side target is located on the right side of the ego vehicle, determine the lateral relative distance y according to the inequality -(M + Δl + m) < y < -(M + Δl);

[0017] wherein M is the distance of the ego vehicle from the road-side lane line: M = L - C0, L is the lane width, C0 is the distance of the ego vehicle from the middle lane line, Δl is the distance of the road-side lane line from the road-side, and m is an error fluctuation range.

[0018] In combination with the first aspect, in an implementation, the value of Δl is 20 cm, and the value of m is 10 cm.

[0019] In combination with the first aspect, in an implementation, the fitting of the road-side lane line based on the coordinate information of all the screened-out road-side targets comprises:

[0020] substitute the coordinates of the screened-out road-side targets into a polynomial fitting curve formula, and use the least square method to determine an expression of the polynomial fitting curve formula as a first fitting curve of the road-side lane line.

[0021] In combination with the first aspect, in an implementation, substitute the longitudinal relative distance x of the screened-out road-side targets into the first fitting curve to obtain a corresponding fitting value y';

[0022] The road edge side target corresponding to the difference between the transverse relative distance y and the fitting value y' exceeding the set threshold is removed;

[0023] The coordinates of the road edge side target remaining after the removal are substituted into the polynomial fitting curve formula, and the least square method is used to determine the expression of the polynomial fitting curve formula as the final fitting curve of the road edge side lane line.

[0024] In combination with the first aspect, in an implementation, the coordinates of the road edge side target are recognized by using the millimeter wave radar to fit the road edge side lane line.

[0025] In the second aspect, an embodiment of the present application provides a tunnel lane line recognition device, which comprises:

[0026] The fitting module is configured to fit the road edge side lane line according to the recognized coordinates of the road edge side target when the road edge side lane line is lost.

[0027] In the third aspect, an embodiment of the present application provides a tunnel lane line recognition device, which comprises a processor, a memory, and a tunnel lane line recognition program stored in the memory and executable by the processor, wherein when the tunnel lane line recognition program is executed by the processor, the steps of the tunnel lane line recognition method according to any one of the above embodiments are implemented.

[0028] In the fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a tunnel lane line recognition program, wherein when the tunnel lane line recognition program is executed by a processor, the steps of the tunnel lane line recognition method according to any one of the above embodiments are implemented.

[0029] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0030] When the road edge side lane line is lost in the tunnel, the low-confidence target recognized by the millimeter wave radar on the road edge in the tunnel is used to fit the lost lane line by multiple times in sections, so as to support the safe driving of the vehicle. The lane line is fitted by the road edge target of the millimeter wave radar, without the need of laser radar and the need of laying road markers in the tunnel, and the scheme has low cost and effectively ensures the driving safety of the vehicle when the lane line is lost in vision. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 The flowchart of an embodiment of the tunnel lane line recognition method of the present application is shown in the figure;

[0032] Figure 2 The phase diagram of the tunnel lane line recognition method of the present application is shown in the figure;

[0033] Figure 3 Fig. 1 is a schematic diagram of a hardware structure of a lane line recognition device in a tunnel according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] In the following well-known functions or components are not described in detail since they are commonly used in the art. The embodiments of the present application will be described herein below with reference to the drawings. In the description, well-known functions or components are not described in detail since they can obscure the understanding of the present application. The same or similar components are designated by the same or similar reference numerals, and a repeated description of the same or similar components is omitted. It should be noted that the following descriptions are examples for implementing the present application. Therefore, the present application should not be limited to the following examples.

[0035] The terms "comprise", "comprising", "include", "including", "have" and "having" and any variations thereof in the specification and in the claims are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a list of steps or units are not necessarily limited to those listed steps or units, but can optionally include additional steps or units not expressly listed or can also include steps or units inherent to such process, method, product, or apparatus. The terms "first", "second", and "third" and the like in the description and in the claims are used for distinguishing between similar objects and not necessarily for describing a sequential or chronological order. The terms "first", "second", and "third" and the like are used herein solely to distinguish one element from another, without necessarily implying examinations in that order.

[0036] In the description of the present application, the terms "exemplary", "for example", or "e.g." are used to indicate one example out of many, or one instance out of many. Any embodiment or design scheme described as "exemplary", "for example", or "e.g." in the present application should not be construed as being more preferred or advantageous than other embodiments or design schemes. In fact, the terms "exemplary", "for example", or "e.g." are used herein to present concepts in a concrete manner.

[0037] In the description of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in the text is only a description of the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of the present application, "multiple" means two or more than two.

[0038] In some of the processes described in this application, there will be more, fewer or different operations than those described and the order in which the operations are described can be different from the order in which the operations are performed.

[0039] For the purpose of making the purpose, technical scheme and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0040] In a first aspect, the embodiments of the present application provide a tunnel lane line identification method, which comprises the following steps:

[0041] When the road edge side lane line is lost, the road edge side lane line is fitted according to the coordinate information of the identified road edge side target object.

[0042] It can be understood that in the tunnel, the middle lane line is often clear, while the road edge side lane line is not clear, at this time, the visual is difficult to identify the lane line, and at this time, since there is no signal in the high-precision map in the tunnel, the high-precision map cannot be combined to realize lane line fusion, at this time, due to the inability to identify the single side lane line, the vehicle may deviate slightly in the tunnel, which is easy to cause the danger of collision between the vehicle and the road edge.

[0043] To solve the above problems, the way adopted in the embodiment is to fit the road edge side lane line by identifying the coordinate information of the road edge side target object, thereby overcoming the problems of difficult visual identification and lane line fusion. The road edge side target object can be a step, a curb or other obstacles outside the road edge side lane line.

[0044] In a specific implementation, in an embodiment, reference is made to Figure 1 , Figure 1 FIG. 1 is a flowchart of a tunnel lane line identification method according to a first embodiment of the present application. As shown in FIG. 1, the tunnel lane line identification method according to the first embodiment of the present application comprises the following steps: Figure 1

[0045] S1, determining the distance of the ego vehicle from the middle lane line.

[0046] S2, determining the distance of the ego vehicle from the road edge side lane line according to the lane width and the distance of the ego vehicle from the middle lane line.

[0047] ​It is worth mentioning that since the middle lane line is usually clear and can be identified based on the front camera, the middle lane line can be taken as a reference to measure the distance of the ego vehicle from the middle lane line. Assuming that along the driving direction of the vehicle, the left side is positive and the right side is negative relative to the midpoint of the front axle of the vehicle; according to the middle lane line identified by the vision, the position C0 of the midpoint of the front axle of the ego vehicle from the middle lane line can be output in real time. Of course, the distance of the ego vehicle from the middle lane line can also be measured in other ways, such as taking the leftmost or rightmost side of the vehicle as a reference, which can be determined according to the actual situation, and the present application does not limit this.

[0048] In addition, the width of the lane can also be determined by the high-precision map. Before entering the tunnel, the high-precision map issues a tunnel entry flag, and outputs the lane width L from the high-precision map.

[0049] After determining the lane width L and the position C0 of the midpoint of the front axle of the ego vehicle from the middle lane line, it can be known that the distance of the midpoint of the front axle of the ego vehicle from the road edge lane line is M = L - C0.

[0050] S3, screening out road edge target objects that meet the longitudinal relative distance and transverse relative distance limit conditions relative to the ego vehicle, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the transverse relative distance is determined based on the distance of the ego vehicle from the road edge lane line.

[0051] Specifically, in the present embodiment, the road edge target objects are identified by a millimeter wave radar, and the road edge target object information mainly includes the coordinates of the road edge target object relative to the ego vehicle obj i (x, y), wherein x is the longitudinal relative distance and y is the transverse relative distance. If the maximum identifiable distance of the millimeter wave radar is N, it can be known that when the road edge target objects are screened based on the longitudinal relative distance, it should meet: 0 < x < N, that is, the road edge target objects beyond this range are not considered.

[0052] In addition, for a tunnel, the lanes are usually two lanes of the same direction, that is, during driving, the road edge target objects of the left lane are on the left side, and the road edge target objects of the right lane are on the right side. That is, only the left side road edge target objects of the left lane need to be considered, and only the right side road edge target objects of the right lane need to be considered. The scheme in the present embodiment is related to both cases, and the overall idea is general, but there are slight differences in the specific implementation.

[0053] Specifically, according to the assumption in the above, assuming that along the driving direction of the vehicle, the left side is positive and the right side is negative relative to the midpoint of the front axle of the vehicle.

[0054] The left side of the road edge side target object screening: the road edge side target object meeting the longitudinal relative distance condition should meet the transverse relative distance condition: M+D1

[0055] The right side of the road edge side target object screening: the road edge side target object meeting the longitudinal distance condition should meet the transverse relative distance condition: -(M+D1+m)<y<-(M+D1).

[0056] Wherein, M is the distance from the vehicle to the road edge side lane line: M=L-C0, L is the lane width, C0 is the distance from the vehicle to the middle lane line, D1 is the distance from the road edge side lane line to the road edge, and m is the error fluctuation range.

[0057] In some preferred embodiments, D1 takes an empirical value of 20 cm, and m takes an empirical value of 10 cm. It can be understood that the values of D1 and m can be reasonably set according to different tunnel conditions, and the embodiments of the present application do not limit this.

[0058] S4, when the road edge side lane line is lost, fitting the road edge side lane line based on the coordinate information of all screened road edge side target objects.

[0059] After step S3, the road edge side target objects can be screened to select road edge side target objects meeting the requirements.

[0060] When the road edge side lane line is lost, the fitting method in step S4 is triggered for fitting.

[0061] Specifically, the coordinates of the screened road edge side target objects are substituted into the polynomial fitting curve formula, and the least squares method is used to determine the expression of the polynomial fitting curve formula as the first fitting curve of the road edge side lane line.

[0062] For example, based on all screened road edge side target objects, based on the fitting curve formula: y=a1+b1x+c1x 2 +d1x 3 , the coordinates of the road edge side target objects relative to the vehicle obj i (x, y) are substituted and the least squares method is used, the coefficients a1, b1, c1 and d1 in the fitting curve formula can be fitted, so that the expression of the fitting curve can be obtained, that is, the fitted lane line curve for subsequent driving reference is obtained.

[0063] In some preferred embodiments, after obtaining the first fitting curve, noise needs to be removed, and the parts that do not meet the requirements are deleted from the road edge side target objects preliminarily screened in the foregoing steps.

[0064] Specifically, first, the longitudinal relative distance x of the screened roadside target object is substituted into the first fitting curve to obtain the corresponding fitting value y'; then, the roadside target object corresponding to the difference between the transverse relative distance y and the fitting value y' exceeding the set threshold is removed; finally, the coordinates of the remaining roadside target objects after removal are substituted into the polynomial fitting curve formula, and the least square method is used to determine the expression of the polynomial fitting curve formula, which is used as the final fitting curve of the roadside lane line.

[0065] That is, after obtaining the first fitting curve y=a1+b1x+c1x 2 +d1x 3 , it is still necessary to verify and remove the roadside target object based on this curve expression. Specifically, the longitudinal relative distance x is substituted into the formula to obtain a fitting value y', and then the difference between the corresponding transverse relative distance y is compared. If the difference between the two is within the set threshold range, it indicates that it meets the requirements, and if it is outside the set threshold range, it indicates that it does not meet the requirements and should be removed. In this embodiment, if the absolute value of y-y' is greater than 20 cm, the point is removed from the roadside target object to form a new roadside target object, that is, the threshold is set to 20 cm. It can be understood that if higher precision is required, the threshold can be further reduced, which can be selected according to actual needs, and the present application does not limit it.

[0066] Then, based on the remaining roadside target objects after removal, curve fitting is performed again. The specific process is similar to the related steps of obtaining the first fitting curve, which is not described in detail herein. After this fitting, the final fitting curve y=a2+b2x+c2x 2 +d2x 3 is obtained. It can be understood that after this removal process, the remaining roadside target objects are more in line with the actual situation, that is, the final fitting curve is more restored, and its precision is higher, which can be used as a reference for intelligent driving.

[0067] It is worth noting that if the roadside lane line is restored during driving and can be visually identified, the curve fitting process is stopped, and driving is based on the actual roadside lane line. If needed in the future, it can be started again, which is relatively convenient to use.

[0068] Referring to Figure 2 , the entire process is described by a block diagram, in which a high-precision map, vision (front-view camera), millimeter-wave radar, and intelligent controller are required to participate in the process. Through these facilities, the related methods in the above process can be realized.

[0069] In summary, the tunnel lane line identification method in the application, when the road edge side lane line is lost in the tunnel, the low confidence target is identified by the millimeter wave radar on the road edge side in the tunnel, and the lost lane line is fitted by multiple segment fitting to support the safe driving of the vehicle. The lane line is fitted by the road edge target of the millimeter wave radar, without laser radar and without road marking in the tunnel, the scheme has low cost, and the driving safety of the vehicle is effectively ensured when the visual lane line is lost.

[0070] In a second aspect, the application also provides a tunnel lane line identification device.

[0071] In an embodiment, the tunnel lane line identification device comprises:

[0072] A fitting module configured to fit the road edge side lane line according to the coordinate information of the identified road edge side target when the road edge side lane line is lost.

[0073] Further, in an embodiment, the fitting module fits the road edge side lane line according to the coordinate information of the road edge side target, comprising:

[0074] determining the distance of the vehicle from the middle lane line;

[0075] determining the distance of the vehicle from the road edge side lane line according to the lane width and the distance of the vehicle from the middle lane line;

[0076] screening the road edge side target that meets the longitudinal relative distance and the transverse relative distance limit conditions at the same time, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the transverse relative distance is determined based on the distance of the vehicle from the road edge side lane line;

[0077] fitting the road edge side lane line based on the coordinate information of all the screened road edge side targets when the road edge side lane line is lost.

[0078] Further, in an embodiment, the fitting module screens the road edge side target that meets the longitudinal relative distance and the transverse relative distance limit conditions at the same time, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the transverse relative distance is determined based on the distance of the vehicle from the road edge side lane line, comprising:

[0079] determining the longitudinal relative distance x according to the inequality 0 < x < N, wherein N is the maximum identifiable distance;

[0080] when the road edge side target is located on the left side of the vehicle, determining the transverse relative distance y according to the inequality M + Δl < y < M + Δl + m;

[0081] When the road-side target object is located at the right side of the ego vehicle, the lateral relative distance y is determined according to the inequality -(M+Δl+m)<y<-(M+Δl);

[0082] wherein M is the distance of the ego vehicle from the road-side lane line: M=L-C0, L is the lane width, C0 is the distance of the ego vehicle from the middle lane line, Δl is the distance of the road-side lane line from the road edge, and m is the error fluctuation range.

[0083] Further, in an embodiment, the value of Δl is 20 cm, and the value of m is 10 cm.

[0084] Further, in an embodiment, the fitting module is configured to fit the road-side lane line based on the coordinate information of all the screened road-side target objects, including:

[0085] substituting the coordinates of the screened road-side target objects into the polynomial fitting curve formula, and using the least square method to determine the expression of the polynomial fitting curve formula as the first fitting curve of the road-side lane line.

[0086] Further, in an embodiment, the fitting module is further configured to:

[0087] substituting the longitudinal relative distance x of the screened road-side target objects into the first fitting curve to obtain the corresponding fitting value y';

[0088] removing the road-side target object corresponding to the difference between the lateral relative distance y and the fitting value y' exceeding the set threshold value;

[0089] substituting the coordinates of the remaining road-side target objects after the removal into the polynomial fitting curve formula, and using the least square method to determine the expression of the polynomial fitting curve formula as the final fitting curve of the road-side lane line.

[0090] Further, in an embodiment, the fitting module is configured to fit the road-side lane line based on the coordinate information of the road-side target objects recognized by the millimeter wave radar.

[0091] The functions of each component of the tunnel lane line recognition device correspond to each step in the tunnel lane line recognition method embodiment, and the functions and implementation processes will not be repeated here.

[0092] In summary, the lane line recognition device in the tunnel in the application, when the road edge side lane line loss occurs in the tunnel, the low confidence target in the tunnel is recognized by the millimeter wave radar on the road edge side, and the lost lane line is fitted by multiple segmentation to support the safe driving of the vehicle. The lane line is fitted by the road edge target of the millimeter wave radar, without laser radar and without laying road marks in the tunnel, the scheme cost is low, and the driving safety of the vehicle is effectively ensured when the visual lane line is lost.

[0093] In a third aspect, the embodiments of the present application provide a tunnel lane line recognition device. The tunnel lane line recognition device can be a personal computer (PC), a notebook computer, a server, or other devices with data processing functions.

[0094] Reference Figure 3 , Figure 3 The figure is a schematic diagram of the hardware structure of the tunnel lane line recognition device involved in the embodiments of the present application. In the embodiments of the present application, the tunnel lane line recognition device can include a processor, a memory, a communication interface, and a communication bus.

[0095] The communication bus can be of any type, used to realize the interconnection of the processor, the memory, and the communication interface.

[0096] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, and other interfaces used to realize the interconnection of the devices inside the tunnel lane line recognition device, and interfaces used to realize the interconnection of the tunnel lane line recognition device and other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0097] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0098] The processor can be a general-purpose processor, which can invoke a tunnel lane line identification program stored in the memory and execute the tunnel lane line identification method provided in the embodiments of the present application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the tunnel lane line identification program is invoked can refer to various embodiments of the tunnel lane line identification method of the present application, which will not be described here.

[0099] Those skilled in the art can understand that the hardware structure shown in the above-mentioned embodiments is not a limitation of the present application, and can include more or fewer components than those shown, or combine certain components, or different component arrangements. Figure 3

[0100] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium.

[0101] The computer readable storage medium of the present application stores a tunnel lane line identification program therein, wherein the tunnel lane line identification program, when executed by a processor, implements the steps of the tunnel lane line identification method as described above.

[0102] The method implemented when the tunnel lane line identification program is executed can refer to various embodiments of the tunnel lane line identification method of the present application, which will not be described here.

[0103] It should be noted that the above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0104] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software and necessary general hardware platforms, and of course can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk) as described above, and includes a plurality of instructions for causing a terminal device to execute the methods described in various embodiments of the present application.

[0105] The above is only the preferred embodiments of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the contents of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.​

Claims

1. A lane line recognition method in a tunnel, characterized by, The tunnel lane line recognition method comprises: When the roadside lane line is lost, fitting the roadside lane line according to the coordinate information of the recognized roadside target object; The fitting of the roadside lane line according to the coordinate information of the recognized roadside target object comprises: determining the distance of the ego vehicle from the middle lane line; determining the distance of the ego vehicle from the roadside lane line according to the lane width and the distance of the ego vehicle from the middle lane line; screening out roadside target objects that simultaneously satisfy the longitudinal relative distance and the lateral relative distance limit conditions, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the lateral relative distance is determined based on the distance of the ego vehicle from the roadside lane line; When the roadside lane line is lost, fitting the roadside lane line based on the coordinate information of all the screened roadside target objects; The screening out of roadside target objects that simultaneously satisfy the longitudinal relative distance and the lateral relative distance limit conditions, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the lateral relative distance is determined based on the distance of the ego vehicle from the roadside lane line, comprises: determining the longitudinal relative distance x according to the inequality 0 < x < N, wherein N is the maximum identifiable distance; When the roadside target object is located on the left side of the ego vehicle, determining the lateral relative distance y according to the inequality M + Δl < y < M + Δl + m; When the roadside target object is located on the right side of the ego vehicle, determining the lateral relative distance y according to the inequality - (M + Δl + m) < y < - (M + Δl); wherein M is the distance of the ego vehicle from the roadside lane line: M = L - C0, L is the lane width, C0 is the distance of the ego vehicle from the middle lane line, Δl is the distance of the roadside lane line from the road edge, and m is the error fluctuation range.

2. The in-tunnel lane line recognition method of claim 1, wherein, The value of Δl is 20 cm, and the value of m is 10 cm.

3. The in-tunnel lane line recognition method of claim 1, wherein, The fitting of the roadside lane line based on the coordinate information of all the screened roadside target objects comprises: substituting the coordinates of the screened roadside target objects into the polynomial fitting curve formula, and using the least square method to determine the expression of the polynomial fitting curve formula as the first fitting curve of the roadside lane line.

4. The in-tunnel lane line recognition method of claim 3, wherein, Further comprising: substituting the longitudinal relative distance x of the screened roadside target objects into the first fitting curve to obtain the corresponding fitting value y'; eliminating the roadside target objects whose difference between the lateral relative distance y and the fitting value y' exceeds the set threshold value; substituting the coordinates of the roadside target objects remaining after the elimination into the polynomial fitting curve formula, and using the least square method to determine the expression of the polynomial fitting curve formula as the final fitting curve of the roadside lane line.

5. The in-tunnel lane line recognition method of claim 1, wherein, The tunnel lane line recognition device comprises:

6. A lane line recognition device in a tunnel, characterized by comprising: a fitting module configured to fit the roadside lane line according to the coordinate information of the recognized roadside target object when the roadside lane line is lost; The fitting of the roadside lane line according to the coordinate information of the recognized roadside target object comprises: determining the distance of the ego vehicle from the middle lane line; determining the distance of the ego vehicle from the roadside lane line according to the lane width and the distance of the ego vehicle from the middle lane line; ​ Screening out the road side target objects which meet the conditions of longitudinal relative distance and lateral relative distance, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the lateral relative distance is determined based on the distance between the ego vehicle and the road side lane line; When the road side lane line is lost, fitting the road side lane line based on the coordinate information of all the screened road side target objects; The screening out the road side target objects which meet the conditions of longitudinal relative distance and lateral relative distance, wherein the longitudinal relative distance is determined based on the maximum identifiable distance, and the lateral relative distance is determined based on the distance between the ego vehicle and the road side lane line, comprises: Determining the longitudinal relative distance x according to the inequality 0 < x < N, wherein N is the maximum identifiable distance; When the road side target object is located on the left side of the ego vehicle, determining the lateral relative distance y according to the inequality M + Δl < y < M + Δl + m; When the road side target object is located on the right side of the ego vehicle, determining the lateral relative distance y according to the inequality - (M + Δl + m) < y < - (M + Δl) ; Wherein, M is the distance between the ego vehicle and the road side lane line: M = L - C0, L is the lane width, C0 is the distance between the ego vehicle and the middle lane line, Δl is the distance between the road side lane line and the road, and m is the error fluctuation range.

7. A lane line recognition device for tunnels, characterized in that, The tunnel lane line recognition device comprises a processor, a memory, and a tunnel lane line recognition program stored in the memory and executable by the processor, wherein when the tunnel lane line recognition program is executed by the processor, the steps of the tunnel lane line recognition method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a tunnel lane line recognition program, wherein when the tunnel lane line recognition program is executed by the processor, the steps of the tunnel lane line recognition method according to any one of claims 1 to 5 are implemented.

Images