Vehicle information labeling method, device, equipment and storage medium

Abstract

The present disclosure provides a method, device, equipment and storage medium for vehicle signal annotation, which relates to the field of image processing technology, and in particular to the fields of computer vision, artificial intelligence, intelligent transportation, and autonomous driving. The specific implementation scheme is: determining a target area in a road image; determining the boundary of a diversion zone in the target area, and determining the boundary of a vehicle signal in the target area, the vehicle signal including a road sign line in the road image; annotating the vehicle signal using the positional relationship between the boundary of the vehicle signal and the boundary of the diversion zone in the target area; the positional relationship is determined based on the vehicle's driving trajectory. The above can overcome errors in manual annotation. Automatic annotation of the location of vehicle signals in the target area can provide data support for the subsequent continuous expansion of the map navigation database.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, in particular to the fields of computer vision, artificial intelligence, intelligent transportation, and autonomous driving, and specifically to a method, device, equipment, and storage medium for vehicle information labeling. Background Art

[0002] With the popularization of mobile Internet, navigation electronic products are widely used in driving. When planning the navigation route, if the user is not reminded of the lane turning information in time or is reminded incorrectly, the vehicle may mistakenly drive to the non-destination turning lane. For many novice drivers, if the navigation leads to the wrong lane, it will cause the driver to be nervous and greatly increase the driving risk.

[0003] In this regard, the relevant technology uses a target detection model to identify the type of ground vehicle signals in the image. Combined with the pictures taken on the spot by the dashcam, the positional relationship between the vehicle signal and the target area is manually determined. The navigation end plans the route for the user according to the prepared vehicle signal data. The above technology relies on manual labor, which is inefficient and costly. At the same time, there is a situation where only the vehicle signal can be produced before the target area, and there is an incomplete production defect for the situation where the vehicle signal is after the target area. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for vehicle information labeling.

[0005] According to one aspect of the present disclosure, a method for marking a vehicle signal is provided, and the method may include the following steps:

[0006] determining a target area in a road image;

[0007] Determine the boundaries of the diversion area of ​​the target area, and determine the boundaries of the vehicle signal in the target area;

[0008] The vehicle signal is marked by using the positional relationship between the boundary of the vehicle signal and the boundary of the diversion zone of the target area; the positional relationship is determined based on the driving trajectory of the vehicle.

[0009] According to another aspect of the present disclosure, a vehicle information labeling device is provided, and the device may include:

[0010] A target area determination module, used for determining a target area in a road image;

[0011] A boundary determination module, used to determine the boundary of the diversion area of ​​the target area, and to determine the boundary of the vehicle signal in the target area;

[0012] The marking module is used to mark the vehicle signal by using the positional relationship between the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area; the positional relationship is determined based on the driving trajectory of the vehicle.

[0013] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method in any embodiment of the present disclosure.

[0017] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to enable a computer to execute the method in any embodiment of the present disclosure.

[0018] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, which implements the method in any embodiment of the present disclosure when the computer program / instruction is executed by a processor.

[0019] The technology disclosed in the present invention can firstly realize automatic identification of the target area. Secondly, it can overcome the errors in manual labeling. Automatically labeling the location of vehicle information in the target area can provide data support for the subsequent expansion of the map navigation database, provide turning lane prompts during the user's navigation planning process, assist user decision-making, and optimize the navigation experience.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flow chart of a method for marking vehicle information according to the present disclosure;

[0023] Figure 2 is one of the road schematic diagrams according to the present disclosure;

[0024] Figure 3 is the second road schematic diagram according to the present disclosure;

[0025] Figure 4 is the third road schematic diagram according to the present disclosure;

[0026] Figure 5 is the fourth road schematic diagram according to the present disclosure;

[0027] Figure 6 is a flow chart for determining a target area according to the present disclosure;

[0028] Figure 7 is a schematic diagram of determining a vehicle signal according to the present disclosure;

[0029] Figure 8 is a schematic diagram of determining lane lines according to the present disclosure;

[0030] Fig. 9 is a schematic diagram of determining a target area according to the present disclosure;

[0031] Fig.10 It is one of the flow charts for marking vehicle information according to the present disclosure;

[0032] Fig.11 It is a schematic diagram of the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area according to the present disclosure;

[0033] Fig.12 This is the second flow chart for marking vehicle information according to the present disclosure;

[0034] Fig.13 is a schematic diagram of a device for marking vehicle information according to the present disclosure;

[0035] Fig.14 It is a block diagram of an electronic device used to implement the vehicle signal labeling method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0037] like Figure 1 As shown, the present disclosure relates to a method for marking a vehicle signal, which may include the following steps:

[0038] S101: determining a target area in a road image;

[0039] S102: Determine the boundary of the diversion area of ​​the target area, and determine the boundary of the vehicle signal in the target area;

[0040] S103: marking the vehicle signal by using the positional relationship between the boundary of the vehicle signal and the boundary of the diversion zone of the target area; the positional relationship is determined based on the driving trajectory of the vehicle.

[0041] The execution subject of the above method disclosed in the present invention may be an electronic map server, or a navigation server, etc. The road image may be an image collected by the user's vehicle, an image collected by an electronic map or navigation information collection vehicle, etc.

[0042] The target area may be a designated road section, for example, a bus section, a diverging (exit, entrance) section of a highway or a ring road, etc. For example, an exit diverging intersection may correspond to a diverging intersection, and an entrance diverging intersection may correspond to a merging intersection.

[0043] By using image recognition technology, etc., the target area in the road image can be determined. The target area can include at least a first sub-area and a second sub-area. The first sub-area can be used as a diversion area of ​​the target area, and the second sub-area can be used as the main part of the target area. By using image recognition technology, etc., the first sub-area and the second sub-area can be identified and distinguished.

[0044] The vehicle information may include road marking lines in the road image, such as guide lines, straight line signs, left turn signs, right turn signs, and U-turn signs.

[0045] The boundary of the diversion area of ​​the target area and the boundary of the vehicle signal can be represented in the form of a rectangular frame. For example, the rectangular frame can include the coordinates of a corner point, as well as the length and width of the rectangular frame. After obtaining the road image, the upper left corner point in the road image can be directly determined as the coordinate origin. Through the above process, the time consumption and accuracy consumption of coordinate system conversion can be omitted, and the efficiency of subsequent work can be improved.

[0046] The positional relationship between the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area may include a front-to-back positional relationship or a left-to-right positional relationship. The above positional relationship may be determined based on the driving track of the vehicle.

[0047] like Figure 2 As shown, when the vehicle is traveling from the right side to the left side in the figure, the position relationship between the boundary of the diversion area of ​​the target area (divergence branch) and the vehicle signal can be a front-to-back position relationship, that is, the vehicle signal appears in front of the boundary of the diversion area of ​​the target area.

[0048] like Figure 3 As shown, when the vehicle is traveling from the right side to the left side in the figure, the position of the vehicle signal and the boundary relationship of the diversion area of ​​the target area (divergence branch) can be a front-to-back position relationship, that is, the vehicle signal appears behind the boundary of the diversion area of ​​the target area.

[0049] like Figure 4As shown, when the vehicle is traveling from the right side to the left side in the figure, the position of the vehicle signal and the boundary relationship of the diversion area of ​​the target area (merger and divergence) can be a front-to-back position relationship, that is, the vehicle signal appears in front of the boundary of the diversion area of ​​the target area.

[0050] like Figure 5 As shown, when the vehicle is traveling from the right side to the left side in the figure, the position of the vehicle signal and the boundary relationship of the diversion area of ​​the target area (merger and divergence) can be a front-to-back position relationship, that is, the vehicle signal appears behind the boundary of the diversion area of ​​the target area.

[0051] Since the relevant technology relies on manual verification, different operators have different observation angles and different judgments on the relative positions of vehicle information and target areas, which makes it difficult to unify the standards for vehicle information marking. Figure 2 The vehicle letter for the situation shown in is correctly labeled.

[0052] In the current implementation, based on the above positional relationship, the vehicle signal can be bound to the corresponding road in the road image to achieve vehicle signal binding.

[0053] Through the above process, firstly, the automatic identification of the target area can be realized. Secondly, the errors in manual labeling can be overcome. Automatically labeling the location of the vehicle signal in the target area can provide data support for the subsequent expansion of the map navigation database, provide turning lane prompts during the user's navigation planning process, assist user decision-making, and optimize the navigation experience.

[0054] like Figure 6 As shown, in one implementation, step S101 may include the following steps:

[0055] S601: performing object recognition on the road image to determine vehicle information in the road image;

[0056] S602: Performing semantic segmentation processing on the road image to determine lane lines in the road image;

[0057] S603: Determine the target area according to the vehicle information and lane lines.

[0058] Object recognition of road images can be implemented using a pre-trained object recognition model. The training process of the object recognition model may include: inputting road image samples with different shooting angles and different blurring degrees into the object recognition model to be trained. The road image samples contain different types of vehicle signals. The object recognition model to be trained may output a predicted value of the vehicle signal recognition result.

[0059] The predicted value of the vehicle signal recognition result can be expressed in the form of probability. For example, the probability that the vehicle signal recognition result is a left turn sign is a%, and the probability that the vehicle signal recognition result is a left U-turn sign is b%. The error between the marked vehicle signal recognition result (the true value of the vehicle signal recognition result) and the predicted value of the recognition result is used to adjust the parameters in the object recognition model to be trained. The above error can be reflected by the loss function, and the role of the loss function can be understood as follows: when the predicted value obtained by the forward propagation of the object recognition model to be trained is close to the true value, the loss function takes a smaller value; otherwise, the value of the loss function increases. In addition, the loss function is a function with the parameters in the object recognition model to be trained as independent variables.

[0060] The above error is used to adjust all parameters in the object recognition model to be trained. The above error will be back-propagated in each layer of the object recognition model to be trained, and the parameters of each layer of the object recognition model to be trained will be adjusted according to the above error until the output result of the object recognition model to be trained converges or reaches the expected effect.

[0061] like Figure 7 The schematic diagram of determining a vehicle signal in a road image is shown. The road image is input into a pre-trained object recognition model to obtain a vehicle signal recognition result. The vehicle signal recognition result may include the type of vehicle signal and the position of the vehicle signal in the image.

[0062] The purpose of semantic segmentation is to classify road images at the pixel level. Pixels belonging to the same category are classified into one category. For example, pixels belonging to vehicles can be classified into one category, and pixels belonging to lane lines can be classified into another category. Different categories can be determined based on the degree of refinement of the semantic segmentation model training. For example, a coarse-grained semantic segmentation model can classify pixels belonging to vehicles into one category, and a fine-grained semantic segmentation model can identify vehicles of various categories or brands. Similarly, combined with Figure 8 The schematic diagram of the semantic segmentation process shown in the figure shows that the lane lines in the road image can be determined through the semantic segmentation process. The lane lines may include bus lane lines, divergence guide lines, etc.

[0063] Combination Fig. 9 As shown, when the vehicle signal and lane line are determined in the road image, the target area can be determined. For example, the area where the end of the bifurcation guide line is located can be determined as the first sub-area (diversion area) of the target area. Alternatively, the area where the starting position of the bus lane line is located can be determined as the first sub-area (diversion area) of the target area. Secondly, the second sub-area (target area body) of the target area can be determined based on the connected domain.

[0064] Through the above process, the target area can be determined by using multi-dimensional image recognition technology.

[0065] like Fig.10 As shown, in one implementation, step S103 may include the following steps:

[0066] S1001: determining the corner point position and the border length of the vehicle signal boundary, and determining the corner point position and the border length of the diversion zone boundary of the target area;

[0067] S1002: Determine the front-to-back position relationship between the vehicle signal and the diversion area of ​​the target area by using the corner point position and boundary length of the vehicle signal and the corner point position and boundary length of the boundary of the diversion area of ​​the target area;

[0068] S1003: Marking the vehicle information according to the front and rear position relationship.

[0069] Combination Fig.11 As shown in FIG. 1 , the target area includes a confluence or divergence point. The boundary of the vehicle signal can be represented by w 1 and h 1 The border composed of the corner points of the border can be expressed as (x 1 ,y 1 ).

[0070] The boundary of the diversion zone in the target area can be expressed as 2 and h 2 The border composed of the corner points of the border can be expressed as (x 2 ,y 2 ).

[0071] The following formula (1) is used to determine the front-to-back position relationship between the vehicle signal and the diversion area of ​​the target area.

[0072]

[0073] In the above formula, q may be a preset empirical value, for example, q=0.8.

[0074] When the above formula (1) holds true, the positional relationship between the vehicle signal and the diversion area of ​​the target area can be expressed as the vehicle signal being located behind the confluence branch or the vehicle signal being located in front of the divergence branch.

[0075] On the contrary, when the above formula (1) is not valid, that is, when the calculation result is not less than q, the positional relationship between the vehicle signal and the diversion area of ​​the target area can be expressed as the vehicle signal being located in front of the confluence branch, or the vehicle signal being located in the rear of the divergence branch.

[0076] According to the front and rear position relationship, the directionality of the vehicle signal is marked to associate the directionality of the vehicle signal with the target area.

[0077] Through the above process, corresponding vehicle information annotation can be performed based on different positional relationships.

[0078] like Fig.12 As shown, in one implementation, step S1003 may include the following steps:

[0079] S1201: when the vehicle signal and the diversion area of ​​the target area are in a specified position relationship, the vehicle signal is divided into two groups;

[0080] S1202: According to the left-right position relationship between each group of vehicle signals and the diversion area of ​​the target area, each group of vehicle signals is marked to a corresponding lane; the lane is a lane within the target area.

[0081] The specified position relationship may be a position relationship in which the borders corresponding to the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area overlap to a certain extent. Alternatively, the specified position relationship may also be a position relationship in which the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area do not overlap, but the distance between the two is less than the corresponding threshold. That is, by using the overlap or distance as a constraint condition, it can be indicated that the content guided by the vehicle signal corresponds to the diversion area of ​​the target area, thereby improving the guidance accuracy.

[0082] The vehicle signals are divided into two groups, and the left and right position relationship between the vehicle signals and the boundary of the diversion zone of the target area can be used as the basis for grouping.

[0083] The following formula (2) is used to determine the left-right position relationship between the vehicle signal and the diversion area of ​​the target area.

[0084]

[0085] If the above formula (2) holds true, it can be said that the vehicle signal is located on the left side of the diversion area of ​​the target area. On the contrary, if the above formula (2) does not hold true, that is, the calculation result is not greater than y 2 In this case, it can mean that the vehicle is located on the right side of the diversion area of ​​the target area.

[0086] According to the above left and right position relationship, the vehicle signal can be assigned to the corresponding lane. Fig. 9 As shown, Fig. 9 The vehicle information at the top layer can be classified as the lane above the diversion area of ​​the target area, which is named the first lane. When the vehicle is driving in the first lane, the vehicle's path planning can be prompted with reference to the guidance content of the vehicle information. For example, the guidance content can be "There is a merging intersection ahead, pay attention to merging in advance."

[0087] in addition, Fig. 9The three vehicle signals in the middle and lower part can be assigned to the lanes below the diversion area of ​​the target area. Here, the three lanes are uniformly named the second lane. When the vehicle is driving in the first lane, the vehicle's path planning can be prompted by referring to the guidance content of the vehicle signal. For example, the guidance content can be "There is a merging intersection ahead, please pay attention to the merging vehicles."

[0088] Through the above process, different vehicle signals can be accurately assigned to corresponding lanes, thereby providing navigation references for vehicles traveling in the corresponding lanes.

[0089] In one embodiment, the target area diversion zone includes: a confluent branch or a divergent branch.

[0090] like Fig.13 As shown, the present disclosure provides a vehicle signal marking device, which may include:

[0091] A target area determination module 1301 is used to determine a target area in a road image;

[0092] A boundary determination module 1302 is used to determine the boundary of the diversion area of ​​the target area and the boundary of the vehicle signal in the target area;

[0093] The marking module 1303 is used to mark the vehicle signal by using the positional relationship between the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area; the positional relationship is determined based on the driving trajectory of the vehicle.

[0094] In one implementation, the target area determination module 1301 may include:

[0095] A vehicle signal determination submodule is used to perform object recognition on the road image and determine the vehicle signal in the road image;

[0096] The lane line determination submodule is used to perform semantic segmentation processing on the road image and determine the lane lines in the road image;

[0097] The target area determination execution submodule is used to determine the target area according to the vehicle information and lane lines.

[0098] In one implementation, the annotation module 1303 may include:

[0099] The boundary position determination submodule is used to determine the corner point position and boundary length of the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area respectively;

[0100] A front-to-back position relationship determination submodule is used to determine the front-to-back position relationship between the vehicle signal and the diversion area of ​​the target area by using the corner point position and boundary length of the vehicle signal and the corner point position and boundary length of the boundary of the diversion area of ​​the target area;

[0101] The labeling execution submodule is used to label the vehicle information according to the front and rear position relationship.

[0102] In one implementation, the annotation execution submodule may include:

[0103] a grouping unit, for dividing the vehicle signal into two groups when the vehicle signal and the diversion area of ​​the target area are in a specified position relationship;

[0104] The marking unit is used to mark each group of vehicle signals to the corresponding lane according to the left-right position relationship between the corner point position of each group of vehicle signals and the corner point position of the boundary of the diversion area of ​​the target area; the lane is the lane in the target area.

[0105] In one embodiment, the target area may include: a confluent branch or a divergent branch.

[0106] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0107] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0108] Fig.14 A schematic block diagram of an example electronic device 1400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0109] like Fig.14 As shown, the device 1400 includes a computing unit 1410, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1420 or a computer program loaded from a storage unit 1480 into a random access memory (RAM) 1430. In the RAM 1430, various programs and data required for the operation of the device 1400 can also be stored. The computing unit 1410, the ROM 1420, and the RAM 1430 are connected to each other via a bus 1440. An input / output (I / O) interface 1450 is also connected to the bus 1440.

[0110] A number of components in the device 1400 are connected to the I / O interface 1450, including: an input unit 1460, such as a keyboard, a mouse, etc.; an output unit 1470, such as various types of displays, speakers, etc.; a storage unit 1480, such as a disk, an optical disk, etc.; and a communication unit 1490, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1490 allows the device 1400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0111] The computing unit 1410 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1410 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1410 performs the various methods and processes described above, such as the method of car letter labeling. For example, in some embodiments, the method of car letter labeling may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1480. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1400 via the ROM 1420 and / or the communication unit 1490. When the computer program is loaded into the RAM 1430 and executed by the computing unit 1410, one or more steps of the method of car letter labeling described above may be performed. Alternatively, in other embodiments, the computing unit 1410 may be configured to execute the vehicle signal labeling method in any other appropriate manner (eg, by means of firmware).

[0112] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0114] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0117] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0118] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0119] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for marking a vehicle signal, comprising: determining a target area in a road image; Determine the boundary of the diversion area of ​​the target area, and determine the boundary of the vehicle signal in the target area, the vehicle signal includes the road marking line in the road image; Determine the corner point position and the border length of the vehicle signal, and determine the corner point position and the border length of the diversion area of ​​the target area; Determine the front-to-back position relationship between the vehicle signal and the diversion area of ​​the target area by using the corner point position and boundary length of the vehicle signal and the corner point position and boundary length of the boundary of the diversion area of ​​the target area; In the case where the vehicle signal and the diversion area of ​​the target area are in a specified position relationship, the vehicle signal is divided into two groups; According to the left-right position relationship between each group of vehicle signals and the diversion area of ​​the target area, each group of vehicle signals is marked to a corresponding lane; The lane is a lane within the target area; the position relationship is determined based on the driving trajectory of the vehicle; Among them, the specified position relationship is a position relationship in which the borders corresponding to the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area overlap to a certain extent; or, the specified position relationship is a position relationship in which the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area do not overlap, but the distance between the two is less than the corresponding threshold.

2. The method according to claim 1, wherein: Determining the target area in the road image includes: Performing object recognition on the road image to determine vehicle information in the road image; Performing semantic segmentation processing on the road image to determine lane lines in the road image; The target area is determined according to the vehicle information and the lane line.

3. The method according to claim 1 or 2, wherein: The target area includes: a confluence branch or a divergence branch.

4. A vehicle information marking device, comprising: A target area determination module, used for determining a target area in a road image; A boundary determination module, used to determine the boundary of the diversion area of ​​the target area, and determine the boundary of the vehicle signal in the target area, wherein the vehicle signal includes a road marking line in the road image; A marking module, used for marking the vehicle signal by using the positional relationship between the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area; The positional relationship is determined based on the driving trajectory of the vehicle; The marking module comprises: A boundary position determination submodule, used to respectively determine the corner point positions and boundary lengths of the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area; A front-to-back position relationship determination submodule, for determining a front-to-back position relationship between the vehicle signal and the flow diversion area of ​​the target area by using the corner point position and the boundary length of the vehicle signal and the corner point position and the boundary length of the boundary of the flow diversion area of ​​the target area; A marking execution submodule, used for marking the vehicle signal according to the front and rear position relationship; The annotation execution submodule includes: A grouping unit, configured to divide the vehicle signal into two groups when the vehicle signal and the diversion area of ​​the target area are in a specified position relationship; a marking unit, configured to mark each group of vehicle signals to a corresponding lane according to a left-right position relationship between a corner point position of each group of vehicle signals and a corner point position of a boundary of a diversion zone of the target area; the lane being a lane within the target area; Among them, the specified position relationship is a position relationship in which the borders corresponding to the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area overlap to a certain extent; or, the specified position relationship is a position relationship in which the boundary of the vehicle signal and the boundary of the diversion area of ​​the target area do not overlap, but the distance between the two is less than the corresponding threshold.

5. The device according to claim 4, wherein: The target area determination module includes: A vehicle signal determination submodule, configured to perform object recognition on the road image and determine a vehicle signal in the road image; A lane line determination submodule, used to perform semantic segmentation processing on the road image to determine the lane lines in the road image; The target area determination execution submodule is used to determine the target area according to the vehicle information and the lane line.

6. The device according to claim 4 or 5, wherein: The target area includes: a confluence branch or a divergence branch.

7. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 3.

9. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images