A positioning data processing method, device, electronic device and storage medium

Abstract

The present disclosure provides a positioning data processing method, device, electronic device, readable storage medium and computer program product, which relate to the fields of autonomous driving and intelligent transportation. The specific implementation scheme is: using the lane lines in the first road image to determine the first positioning data for the vehicle, the first road image is a road image collected by the vehicle for the current driving road; performing lane line abnormality processing on the first road image to obtain a second road image; using the lane lines in the second road image to determine the second positioning data for the vehicle; determining the positioning deviation between the first positioning data and the second positioning data. This scheme can determine the impact of lane line abnormalities on the accuracy of vehicle positioning, and because the second road image is obtained by performing abnormal processing on the road image collected by the vehicle, it can construct road images with various lane line abnormalities, thereby achieving the accuracy of vehicle positioning in different lane line abnormality scenarios.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, specifically to autonomous driving and intelligent transportation technologies, and can be specifically used in scenarios such as autonomous driving and intelligent transportation. Background Art

[0002] It mainly recognizes information such as lane lines in road images, and determines the road position of the autonomous driving vehicle based on the recognized information to achieve the positioning of the autonomous driving vehicle.

[0003] However, in the process of visual positioning, the images collected by the on-board image acquisition equipment often have abnormal conditions such as dirty, missing and unclear lane lines, which will affect the accuracy of visual positioning and further affect the accuracy of vehicle positioning. Summary of the invention

[0004] The present disclosure provides a positioning data processing method, device, electronic device, readable storage medium and computer program product to achieve high accuracy in vehicle positioning in different lane line abnormal scenarios.

[0005] According to one aspect of the present disclosure, a positioning data processing method is provided, which may include the following steps:

[0006] Determine first positioning data for the vehicle using lane lines in a first road image, where the first road image is a road image collected by the vehicle for a current driving road;

[0007] Performing lane line abnormality processing on the first road image to obtain a second road image;

[0008] Determine second positioning data for the vehicle using lane lines in the second road image;

[0009] A positioning deviation between the first positioning data and the second positioning data is determined.

[0010] According to a second aspect of the present disclosure, a positioning data processing device is provided, which may include:

[0011] A first positioning data determining unit, configured to determine first positioning data for the vehicle using lane lines in a first road image, wherein the first road image is a road image collected by the vehicle for a current driving road;

[0012] A second image acquisition unit is used to perform lane line abnormality processing on the first road image to obtain a second road image;

[0013] A second positioning data determining unit, configured to determine second positioning data for the vehicle using lane lines in the second road image;

[0014] The positioning deviation determining unit is used to determine the positioning deviation between the first positioning data and the second positioning data.

[0015] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] 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.

[0019] 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.

[0020] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, wherein the computer program / instruction implements the method in any embodiment of the present disclosure when executed by a processor.

[0021] The technology disclosed in the present invention can perform lane line anomaly processing on a first road image to obtain a second road image, and will use the lane lines in the first road image and the lane lines in the second road image to determine the first positioning data and the second positioning data for the vehicle, and further determine the positioning deviation between the first positioning data and the second positioning data.

[0022] By determining the positioning deviation, the influence of lane line abnormality on the accuracy of vehicle positioning can be judged, and since the second road image is obtained by performing abnormality processing on the road image collected by the vehicle, road images with various lane line abnormalities can be constructed, thereby achieving the accuracy of vehicle positioning in different lane line abnormality scenarios.

[0023] 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

[0024] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0025] Figure 1 A flowchart of a positioning data processing method is provided for an embodiment of the present disclosure;

[0026] Figure 2A flowchart of a method for determining positioning data provided in an embodiment of the present disclosure;

[0027] Figure 3 A flowchart of a lane line removal method provided in an embodiment of the present disclosure;

[0028] Figure 4 A schematic diagram of a first road image provided in an embodiment of the present disclosure;

[0029] Figure 5 A schematic diagram of a mask image provided in an embodiment of the present disclosure;

[0030] Figure 6 A schematic diagram of a second road image provided in an embodiment of the present disclosure;

[0031] Figure 7 A schematic diagram of a positioning data processing device is provided for an embodiment of the present disclosure;

[0032] Figure 8 A schematic diagram of an electronic device provided according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] 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.

[0034] The high-precision positioning of autonomous vehicles is mainly achieved based on at least one or more positioning methods such as visual positioning, Global Navigation Satellite System (GNSS) positioning, and Laser Radar (LIDAR) positioning. Among them, visual positioning is often used in combination with other positioning methods to provide high-precision positioning for autonomous vehicles due to its economical characteristics.

[0035] In the positioning process using visual positioning, the lane lines in the road image are mainly identified, and the road position of the autonomous driving vehicle is determined based on the identified information to achieve the positioning of the autonomous driving vehicle. It can be seen that the lane lines in the road image play a crucial role in the accuracy of visual positioning.

[0036] However, in the process of visual positioning, the images collected by the on-board image acquisition equipment often have abnormal conditions such as dirty, missing and unclear lane lines, which will affect the accuracy of visual positioning and further affect the accuracy of vehicle positioning.

[0037] Therefore, in order to determine the impact of different lane line abnormalities on the accuracy of vehicle positioning, it is necessary to evaluate the accuracy of vehicle positioning when lane line abnormalities exist. However, there are many scenarios of lane line abnormalities, and the collected road images are often difficult to cover all lane line abnormal scenarios only through the collection of road images. Therefore, how to evaluate the accuracy of vehicle positioning in different lane line abnormal scenarios has become a technical problem that needs to be solved urgently.

[0038] This disclosure provides a positioning data processing method. For details, please refer to Figure 1 , which is a flowchart of a positioning data processing method provided by an embodiment of the present disclosure. The method may include the following steps:

[0039] Step S101: using lane lines in a first road image, determining first positioning data for a vehicle, the first road image being a road image collected by the vehicle for a current driving road.

[0040] Step S102: performing lane line abnormality processing on the first road image to obtain a second road image.

[0041] Step S103: Determine second positioning data for the vehicle using lane lines in the second road image.

[0042] Step S104: determining a positioning deviation between the first positioning data and the second positioning data.

[0043] The positioning data processing method provided in the embodiments of the present disclosure can perform lane line anomaly processing on the first road image to obtain the second road image, and will use the lane lines in the first road image and the lane lines in the second road image to determine the first positioning data and the second positioning data for the vehicle, and further determine the positioning deviation between the first positioning data and the second positioning data.

[0044] By determining the positioning deviation, the influence of lane line abnormality on the accuracy of vehicle positioning can be judged. Since the second road image is obtained by performing abnormal processing on the road image collected by the vehicle, road images with various lane line abnormalities can be constructed, thereby achieving the accuracy of vehicle positioning in different lane line abnormality scenarios.

[0045] Vehicles generally collect road images in the following manner: during the driving process of the vehicle, an image acquisition device on the vehicle is used to collect images of the current driving road in real time to obtain a road image.

[0046] In the embodiments of the present disclosure, the specific implementation methods of determining the second positioning data for the vehicle using the lane lines in the second road image are: at least using the lane lines in the road image to visually locate the vehicle to obtain corresponding positioning data.

[0047] It should be noted that the accuracy of vehicle positioning is often low when the positioning data for the vehicle is obtained only through visual positioning. In order to make the obtained positioning data be used as the true value of the vehicle positioning under the current sensor data, and then more truly and accurately reflect the impact of lane line abnormality on the accuracy of vehicle positioning. In the embodiments of the present disclosure, when determining the positioning data, a combination of visual positioning and other positioning methods is often further used to determine the corresponding positioning data.

[0048] In order to reduce the error of positioning deviation, the same positioning method needs to be used when determining the first positioning data and the second positioning data. For example, if a combination of visual positioning and GNSS positioning is used when determining the first positioning data, a combination of visual positioning and GNSS positioning should also be used when determining the second positioning data.

[0049] Since the methods for determining the first positioning data and the second positioning data are the same, in the embodiment of the present disclosure, the step of determining the first positioning data is specifically taken as an example to explain the step of determining the positioning data in detail. Figure 2 , Figure 2 The present invention is a flowchart of a method for determining positioning data provided in an embodiment of the present invention.

[0050] Step S201: Based on the lane lines in the first road image, visual positioning of the vehicle is performed to obtain corresponding visual positioning data.

[0051] Step S202: Using other preset positioning methods to obtain other positioning data for the vehicle.

[0052] Step S203: Obtain first positioning data based on the visual positioning data and other positioning data.

[0053] The process of obtaining the first positioning data is generally: obtaining the first positioning data by offline solving the sensor data. Among them, the sensor data generally includes at least road image data, GNSS data and vehicle-mounted inertial sensor (IMU) data, and may further include radar data, etc. In other words, the preset other positioning methods include at least: GNSS positioning. In addition, it is difficult to achieve high-frequency output of positioning data by using visual positioning and GNSS positioning. Therefore, when obtaining positioning data, visual positioning, GNSS positioning and strapdown inertial navigation positioning can be used simultaneously to obtain positioning data. In addition, other positioning methods can further include positioning methods such as radar positioning.

[0054] The so-called visual positioning of the vehicle based on the lane lines in the first road image and obtaining the corresponding visual positioning data can be specifically implemented as follows: identifying the lane lines in the first road image, and matching the identified lane line information with the corresponding lane lines in the map, so as to determine the road position of the autonomous driving vehicle and realize the positioning of the autonomous driving vehicle.

[0055] It should be noted that, in the process of visual positioning, other road information of the road image, such as road sign information, etc., can also be combined to achieve visual positioning.

[0056] Common lane line anomalies generally include but are not limited to: blurred lane lines, contaminated lane lines, and missing lane lines. In real road environments, lane line anomalies often exist in various abnormal scenarios. Only by acquiring road images to obtain road images, it is often impossible to obtain a relatively comprehensive lane line anomaly scenario. Therefore, it is necessary to construct the required lane line anomaly scenario by performing lane line anomaly processing.

[0057] For the missing lane lines, the embodiments of the present disclosure adopt a method of partially removing the lane lines to achieve exception handling, that is, partially removing the lane lines in the first road image to obtain the second road image.

[0058] Regarding the blurring of lane lines, in the embodiments of the present disclosure, a method of blurring the lane lines is adopted to achieve exception handling.

[0059] For lane line contamination, the embodiments of the present disclosure implement exception handling by overlaying an image on the lane line.

[0060] In the process of lane line exception processing, the lane line that needs to be processed can be determined based on the pre-configured lane line exception reference. Then, the lane line that needs to be processed is processed. This lane line exception processing method can make the constructed second road image meet the lane line exception requirements of relevant personnel. For example: the lane line to be blurred in the first road image can be determined; the lane line to be blurred is blurred to obtain the second road image.

[0061] In addition, in the process of handling lane line anomalies, the lane line anomaly ratio corresponding to the first road image may be determined according to a preset lane line anomaly requirement, and then the lane line anomaly may be handled based on the lane line anomaly ratio.

[0062] For example, when determining the lane lines to be removed in the first road image, first determine the lane line removal ratio corresponding to the first road image according to the preset lane line removal requirement, and then determine the lane lines to be removed based on the lane line removal ratio.

[0063] For another example, when determining the lane line to be blurred in the first road image, first determine the lane line blurring ratio corresponding to the first road image according to the preset lane line blurring requirement, and then determine the lane line to be blurred based on the lane line blurring ratio.

[0064] The lane line abnormality processing method based on the lane line abnormality ratio can make the constructed second road image closer to the actual lane line abnormality, so that the second road image has higher authenticity.

[0065] In the embodiment of the present disclosure, the specific implementation method of partially removing the lane line in the first road image can refer to Figure 3 , Figure 3 The present invention is a flowchart of a lane line removal method provided in an embodiment of the present invention.

[0066] Step S301: Determine lane lines to be removed in a first road image.

[0067] Step S302: for the first road image, determine a mask image for removing lane lines to be removed.

[0068] Step S303: using the first road image and the mask image to obtain a second road image.

[0069] The mask image can make the pixel values ​​of some areas become zero while the pixel values ​​of other areas remain unchanged by performing AND operation on each pixel in the image to be processed and each corresponding pixel in the mask image. This can extract part of the image to be processed, or remove the uninteresting area in the image to be processed. In the embodiment of the present disclosure, please refer to the process of obtaining the second road image. Figure 4-6 .in, Figure 4 is a schematic diagram of a first road image provided in an embodiment of the present disclosure, Figure 5 is a schematic diagram of a mask image provided in an embodiment of the present disclosure, Figure 6 A schematic diagram of a second road image provided in an embodiment of the present disclosure.

[0070] Figure 4 The lane lines outlined by dashed lines are the lane lines to be removed. Figure 5 Specifically, the portion of the first road image corresponding to the region with a pixel value of 0 in the mask image will be removed, and the portion of the first road image corresponding to the region with a pixel value of 1 in the mask image will be retained.

[0071] After performing AND operation on the pixels of the first road image and the mask image, the lane line to be removed can be removed. However, at this time, the pixel value of the first road image corresponding to the lane line to be removed is 0. In order to make the final second road image more realistic, it is necessary to further perform image restoration on the image area corresponding to the lane line to be removed, so as to obtain the following image: Figure 6 The second road image shown in . The image repairing method includes but is not limited to: using a pre-selected image repairing algorithm such as a convolutional neural network to implement image inference repair.

[0072] The mask image can more accurately and conveniently remove the lane lines to be removed in the first road image, thereby reducing the cost of obtaining the second road image.

[0073] In addition, in the embodiments of the present disclosure, there is no specific limitation on the specific implementation method of removing the lane line to be removed in the first road image, as long as the purpose of accurately removing the lane line to be removed can be achieved. For example, the lane line can also be removed by cropping.

[0074] In the embodiments of the present disclosure, the specific implementation method for blurring the lane lines may be: blurring the lane lines by reducing the pixel values ​​of the pixels corresponding to the lane lines to be blurred; or blurring the lane lines by using blur algorithms such as Gaussian Blur algorithm.

[0075] In the embodiments of the present disclosure, a deviation threshold may also be preset. The deviation threshold is used to determine whether the second positioning data meets the positioning requirements of the vehicle, so as to more intuitively reflect the impact of lane line abnormality scenarios on the accuracy of vehicle positioning. The implementation method is: according to the positioning deviation and the threshold corresponding to the positioning deviation, determine whether the second positioning data meets the positioning requirements of the vehicle.

[0076] Specifically, if the positioning deviation does not reach the threshold corresponding to the positioning deviation, it is determined that the second positioning data meets the positioning requirement of the vehicle; and if the positioning deviation reaches the threshold corresponding to the positioning deviation, it is determined that the second positioning data does not meet the positioning requirement of the vehicle.

[0077] like Figure 7 As shown, an embodiment of the present disclosure provides a positioning data processing device, the device comprising:

[0078] A first positioning data determining unit 701 is used to determine first positioning data for the vehicle using lane lines in a first road image, where the first road image is a road image collected by the vehicle for a current driving road;

[0079] The second image obtaining unit 702 is used to perform lane line abnormality processing on the first road image to obtain a second road image;

[0080] A second positioning data determining unit 703, configured to determine second positioning data for the vehicle using lane lines in the second road image;

[0081] The positioning deviation determining unit 704 is used to determine the positioning deviation between the first positioning data and the second positioning data.

[0082] In one implementation, the second image obtaining unit 702 may further include:

[0083] The first road image processing subunit is used to perform a partial removal process on the lane lines in the first road image to obtain a second road image.

[0084] In one implementation, the first road image processing subunit may further include:

[0085] A lane line to be removed determining subunit, used to determine the lane line to be removed in the first road image;

[0086] A mask image determination subunit, used to determine, with respect to the first road image, a mask image for removing a lane line to be removed;

[0087] The second road image obtaining subunit is used to obtain a second road image using the first road image and the mask image.

[0088] In one implementation, the lane line to be removed determining subunit may further include:

[0089] A removal ratio determination subunit, used to determine the lane line removal ratio corresponding to the first road image according to a preset lane line removal requirement;

[0090] The removal ratio obtaining subunit is used to determine the lane line to be removed based on the lane line removal ratio.

[0091] In one implementation, the second image obtaining unit 702 may further include:

[0092] A lane line to be blurred determining subunit, used to determine the lane line to be blurred in the first road image;

[0093] The fuzzification processing subunit is used to perform fuzzification processing on the lane line to be fuzzified to obtain a second road image.

[0094] In one implementation, the first positioning data determining unit 701 may further include:

[0095] A visual positioning data acquisition subunit, used to perform visual positioning on the vehicle based on the lane lines in the first road image to obtain corresponding visual positioning data;

[0096] Other positioning data acquisition subunit, used to obtain other positioning data for the vehicle by using other preset positioning methods;

[0097] The first positioning data obtaining subunit is used to obtain first positioning data based on the visual positioning data and other positioning data.

[0098] In one embodiment, the device may further include:

[0099] The positioning requirement determination unit is used to determine whether the second positioning data meets the positioning requirement of the vehicle according to the positioning deviation and a threshold value corresponding to the positioning deviation.

[0100] 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.

[0101] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0102] Figure 8A schematic block diagram of an example electronic device 700 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.

[0103] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0104] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0105] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 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 801 performs the various methods and processes described above, such as the positioning data processing method. For example, in some embodiments, the positioning data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the positioning data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the positioning data processing method in any other appropriate manner (e.g., by means of firmware).

[0106] 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.

[0107] 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 positioning data processing device, so that the program code, when executed by the processor or controller, causes 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 positioning data processing method, comprising: Determine first positioning data for the vehicle using lane lines in a first road image, where the first road image is a road image collected by the vehicle for a current driving road; Performing lane line abnormality processing on the first road image to obtain a second road image; Determine second positioning data for the vehicle using lane lines in the second road image; determining a positioning deviation between the first positioning data and the second positioning data; The performing lane line abnormality processing on the first road image to obtain a second road image includes: Partially remove the lane lines in the first road image to obtain the second road image.

2. The method according to claim 1, wherein: The partially removing the lane lines in the first road image to obtain the second road image includes: Determining a lane line to be removed in the first road image; For the first road image, determining a mask image for removing the lane line to be removed; The second road image is obtained by using the first road image and the mask image.

3. The method according to claim 2, wherein: The determining the lane line to be removed in the first road image includes: Determining a lane line removal ratio corresponding to the first road image according to a preset lane line removal requirement; Based on the lane line removal ratio, the lane line to be removed is determined.

4. The method according to any one of claims 1 to 3, wherein: The performing lane line abnormality processing on the first road image to obtain a second road image includes: Determining a lane line to be blurred in the first road image; The lane line to be blurred is blurred to obtain the second road image.

5. The method according to claim 1, wherein: The method of determining first positioning data for the vehicle by using lane lines in the first road image includes: Based on the lane lines in the first road image, visually locate the vehicle to obtain corresponding visual positioning data; Using other preset positioning methods to obtain other positioning data for the vehicle; The first positioning data is obtained based on the visual positioning data and the other positioning data.

6. The method according to claim 1, wherein: The method further comprises: According to the positioning deviation and a threshold value corresponding to the positioning deviation, it is determined whether the second positioning data meets the positioning requirement of the vehicle.

7. A model pruning device, comprising: A first positioning data determining unit, configured to determine first positioning data for a vehicle using lane lines in a first road image, wherein the first road image is a road image collected by the vehicle for a current driving road; A second image acquisition unit is used to perform lane line abnormality processing on the first road image to obtain a second road image; A second positioning data determining unit, configured to determine second positioning data for the vehicle using lane lines in the second road image; a positioning deviation determining unit, configured to determine a positioning deviation between the first positioning data and the second positioning data; Wherein, the second image acquisition unit includes: The first road image processing subunit is used to perform a partial removal process on the lane lines in the first road image to obtain the second road image.

8. The device according to claim 7, wherein: The first road image processing subunit includes: A lane line to be removed determining subunit, used to determine the lane line to be removed in the first road image; A mask image determination subunit, configured to determine, with respect to the first road image, a mask image for removing the lane line to be removed; The second road image obtaining subunit is used to obtain the second road image by using the first road image and the mask image.

9. The device according to claim 8, wherein: The lane line to be removed determining subunit includes: a removal ratio determination subunit, configured to determine a lane line removal ratio corresponding to the first road image according to a preset lane line removal requirement; The removal ratio obtaining subunit is used to determine the lane line to be removed based on the lane line removal ratio.

10. The device according to any one of claims 7 to 9, wherein: The second image acquisition unit comprises: A lane line to be blurred determining subunit, used to determine the lane line to be blurred in the first road image; The fuzzification processing subunit is used to perform fuzzification processing on the lane line to be fuzzified to obtain the second road image.

11. The device according to claim 7, wherein: The first positioning data determining unit includes: a visual positioning data acquisition subunit, configured to perform visual positioning on the vehicle based on the lane lines in the first road image to obtain corresponding visual positioning data; Other positioning data obtaining subunit, used to obtain other positioning data for the vehicle by using other preset positioning methods; The first positioning data obtaining subunit is used to obtain the first positioning data based on the visual positioning data and the other positioning data.

12. The device according to claim 7, wherein: The device also includes: A positioning requirement determination unit is used to determine whether the second positioning data meets the positioning requirement of the vehicle according to the positioning deviation and a threshold value corresponding to the positioning deviation.

13. 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 executable 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 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

15. 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 claims 1 to 6 are implemented.

Images