Method and apparatus for determining a connected path of lanes

Abstract

The present disclosure provides a method, device, electronic equipment and readable storage medium for determining a connected path of a lane, which relates to the technical field of artificial intelligence such as automatic driving, cloud service, intelligent transportation, deep learning and the like. The method for determining a connected path of a lane comprises: determining a target lane, obtaining a number of candidate exit roads corresponding to the target lane, and a number of lanes having the same guide information as the target lane; in a case where the number of roads and the number of lanes are both multiple, obtaining a road scene image; in a case where a road scene in the road scene image is a valid road scene, extracting target text from the road scene image; and selecting a target exit road from the candidate exit roads according to the target text, and taking the target exit road as the connected path of the target lane. The present disclosure can improve the determination accuracy of the connected path, avoid incorrectly establishing the connected relationship between the lane and the exit road, and improve the accuracy of navigation reminders.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, specifically to artificial intelligence technologies such as autonomous driving, cloud services, intelligent transportation, and deep learning. It provides a method, apparatus, system, electronic device, and readable storage medium for determining the connectivity path of lanes. Background Technology

[0002] Current technology typically determines lane connectivity by calculating the angle between the lane's directional arrow and the exit road, and then using the exit road whose angle meets a preset range as the lane's connectivity path. However, with the increasing number of roads, determining connectivity solely based on angle calculations reduces the accuracy of the determined paths, thus affecting the accuracy of navigation alerts. Summary of the Invention

[0003] According to a first aspect of this disclosure, a method for determining the connectivity path of a lane is provided, comprising: determining a target lane; acquiring the number of candidate exit roads corresponding to the target lane and the number of lanes having the same guidance information as the target lane; when both the number of roads and the number of lanes are determined to be multiple, acquiring a road scene image; when the road scene in the road scene image is determined to be a valid road scene, extracting target text from the road scene image; selecting a target exit road from the candidate exit roads based on the target text, and using the target exit road as the connectivity path of the target lane.

[0004] According to a second aspect of this disclosure, an apparatus for determining the connectivity path of a lane is provided, comprising: a processing unit configured to determine a target lane, acquire the number of candidate exit roads corresponding to the target lane, and the number of lanes having the same guidance information as the target lane; a determining unit configured to acquire a road scene image when both the number of roads and the number of lanes are determined to be multiple; an extraction unit configured to extract target text from the road scene image when the road scene in the road scene image is determined to be a valid road scene; and a connectivity unit configured to select a target exit road from the candidate exit roads based on the target text, and use the target exit road as the connectivity path of the target lane.

[0005] According to a third aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.

[0006] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described above.

[0007] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described above.

[0008] As can be seen from the above technical solutions, this disclosure can improve the accuracy of the determined lane connection path, avoid incorrectly establishing the connection relationship between the lane and the exit road, and thus improve the accuracy of navigation reminders.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0012] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0013] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure;

[0014] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0015] Figure 5 This is a block diagram of an electronic device used to implement the method for determining the connectivity path of a lane in the embodiments of this disclosure. Detailed Implementation

[0016] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and mechanisms are omitted in the following description.

[0017] Figure 1 This is a schematic diagram based on the first embodiment of this disclosure. (See diagram below.) Figure 1 As shown, the method for determining the connectivity path of a lane in this embodiment specifically includes the following steps:

[0018] S101. Determine the target lane, and obtain the number of candidate exit roads corresponding to the target lane, as well as the number of lanes with the same guidance information as the target lane;

[0019] S102. When it is determined that both the number of roads and the number of lanes are multiple, obtain a road scene image;

[0020] S103. If the road scene in the road scene image is determined to be a valid road scene, extract the target text from the road scene image.

[0021] S104. Select a target exit road from the candidate exit roads according to the target text, and use the target exit road as the connecting path of the target lane.

[0022] The method for determining the connectivity path of a lane in this embodiment uses two judgment processes, combined with target text extracted from the road scene image, to select the target exit road as the connectivity path of the target lane from multiple candidate exit roads. This embodiment can improve the accuracy of the determined connectivity path of the lane, avoid incorrectly establishing the connectivity relationship between the lane and the exit road, and thus improve the accuracy when providing navigation reminders.

[0023] In this embodiment, when executing S101 to determine the target lane, the lane corresponding to the location information and / or name input by the input terminal can be used as the target lane, or the lane selected by the input terminal from the electronic map can be used as the target lane.

[0024] In this embodiment, when executing S101 to determine the target lane, the following method can also be used: determine the candidate lane, obtain the number of navigation reminder errors in the candidate lane. In this embodiment, the number of errors in the candidate lane can be obtained according to the pre-recorded correspondence between lanes and error counts, and the correspondence between lanes and error counts is obtained through feedback from the input terminal; if the number of errors exceeds a preset threshold, the candidate lane is used as the target lane.

[0025] In other words, the target lane determined in this embodiment can be a lane that frequently generates navigation warning errors. By determining the connection path of such a target lane, a more accurate connection relationship between the lane and the exit road can be established, thereby avoiding subsequent navigation warning errors and improving the accuracy of navigation warnings.

[0026] This embodiment does not limit the method of determining candidate lanes or the number of candidate lanes determined; there can be one or more candidate lanes. This embodiment also does not limit the number of target lanes determined; there can be one or more target lanes.

[0027] In this embodiment, after determining the target lane in S101, the steps are to obtain the number of candidate exit roads corresponding to the target lane and the number of lanes with the same guidance information as the target lane.

[0028] It is understandable that when there are multiple target lanes, this embodiment will obtain the number of roads and lanes corresponding to each target lane when executing S101, and then perform subsequent operations based on the number of roads and lanes corresponding to each target lane.

[0029] In this embodiment, the road where the target lane is located is an entry road, which is the road where the driving direction enters the intersection, and the exit road is the road where the driving direction moves away from the intersection. The guidance information is used to indicate the driving direction of the lane, which can be determined by the lane's guidance arrows (such as U-turn arrows, left turn arrows, straight arrows and right turn arrows, etc.), guidance text, etc. The driving direction of the lane includes at least one of U-turn, left turn, straight and right turn.

[0030] In this embodiment, when executing S101 to obtain the number of roads, the candidate exit roads corresponding to the target lane can be determined first, and then the number of roads can be obtained based on the determined candidate exit roads.

[0031] In this embodiment, when executing S101, the exit road corresponding to the target lane can be determined according to the road database, which stores the correspondence between lanes (lane location information and / or name) and exit roads; according to the determined candidate exit roads, this embodiment can further obtain the road name and / or road shape name of the candidate exit roads.

[0032] In addition, when performing S101 to determine the candidate exit road corresponding to the target lane, this embodiment can also adopt the following method: determine the entry road according to the target lane; obtain all exit roads corresponding to the entry road and obtain the road angle between the entry road and each exit road; determine the target angle range according to the guidance information of the target lane; and take the exit roads whose road angle is within the target angle range as the candidate exit roads corresponding to the target lane.

[0033] In this embodiment, when executing S101 to obtain the number of lanes, the lanes with the same guidance information as the target lane can be determined first, and then the number of lanes can be obtained based on the determined lanes.

[0034] In this embodiment, when executing S101, a lane with the same guidance information as the target lane can be determined according to the road database. The road database stores the entrance road where the lane (lane location information and / or name) is located and the guidance information of each lane in the entrance road. For example, it can determine the lane with the same guidance arrow as the target lane in the entrance road where the target lane is located.

[0035] In addition, when executing S101, this embodiment can also acquire a road scene image (such as a guide sign image, a road surface image, etc.) corresponding to the target lane, and determine the lane with the same guidance information as the target lane based on the road scene image.

[0036] In this embodiment, after executing S101 to obtain the number of roads and lanes corresponding to the target lane, S102 is executed to obtain a road scene image when it is determined that there are multiple roads and lanes.

[0037] The road scene image obtained in S102 of this embodiment corresponds to the target lane and can be at least one of the following: a guide sign image located near the intersection into which the target lane is to enter, and a road surface image corresponding to the target lane.

[0038] In this embodiment, when executing S102, the image corresponding to the target lane in the road database can be used as the road scene image, or the image collected in real time according to the target lane can be used as the road scene image.

[0039] In other words, this embodiment determines whether to acquire road scene images based on whether the number of roads and lanes are both multiple. This avoids performing additional road scene image acquisition operations when the number of roads and lanes does not meet the requirements, reduces the waste of computing resources, and improves the accuracy of road scene image acquisition.

[0040] In this embodiment, after executing S102 to acquire a road scene image, S103 is executed to extract target text from the road scene image if the road scene in the road scene image is determined to be a valid road scene; wherein the extracted target text corresponds to the target lane.

[0041] In this embodiment, when executing S103 to determine that the road scene in the road scene image is a valid road scene, the optional implementation method can be: extracting road text features from the road scene image; and determining that the road scene in the road scene image is a valid road scene if the extracted road text features match the valid scene features.

[0042] In this embodiment, the road text features extracted from the road scene image in step S103 can be at least one of the following: road text such as road shape (ground, tunnel, viaduct, auxiliary road, ramp, etc.) name and / or road name, the relationship between road text and directional arrows, and the relationship between road text and lanes.

[0043] The effective scene features used when executing S103 in this embodiment are obtained in advance. The effective scene features are at least one of the following: the road text is a road shape name or road name, the road text is located below the directional arrow, and the road text corresponds to a part of the lane (the part of the lane includes the target lane and the lane with the same directional information as the target lane).

[0044] Therefore, in this embodiment, when executing S103, if the extracted road text features are determined to be road shape names or road names based on the road scene image, or if the extracted road text features are road shape names or road names located below the guide arrows, or if the extracted road text features are road shape names or road names corresponding to some lanes, then the road scene in the road scene image is determined to be a valid road scene.

[0045] In addition, when performing S103 to determine that the road scene in the road scene image is a valid road scene, this embodiment can also input the road scene image into a pre-trained scene recognition model. If the output result of the scene recognition model is determined to be a preset result, the road scene in the road scene image is determined to be a valid road scene; wherein, the preset result in this embodiment is 1.

[0046] It is understood that the scene recognition model used in S103 of this embodiment is pre-trained; by acquiring road scene images that are valid road scenes as training samples, the neural network model is trained to obtain the scene recognition model.

[0047] In this embodiment, after determining that the road scene in the road scene image is a valid road scene in step S103, the step of extracting target text from the road scene image is performed.

[0048] In this embodiment, when executing S103 to extract target text from a road scene image, the road text extracted from the road scene image can be obtained first, and then the road text corresponding to the target lane can be used as the target text. The target text is used to reflect the road name and / or road shape of the target exit road corresponding to the target lane.

[0049] In this embodiment, after executing S103 to extract the target text from the road scene image, S104 is executed to select the target exit road from the candidate exit roads based on the target text, and the target exit road is used as the connecting path of the target lane.

[0050] In this embodiment, when executing S104 to select the target exit road from the candidate exit roads based on the target text, the optional implementation method can be: obtaining the road shape name and / or road name of each candidate exit road; and taking the candidate exit road whose road shape name and / or road name matches the target text as the target exit road.

[0051] In this embodiment, the number of target exit roads selected in S104 can be one or more; if there are multiple target exit roads, this embodiment can use any one of the target exit roads as the connecting path of the target lane.

[0052] In this embodiment, after executing S104 to use the target exit road as the connecting path of the target lane, the connectivity between the target lane and the target exit road can be recorded. Then, the recorded connectivity can be used to update the electronic map, so as to achieve the purpose of using the updated connectivity for navigation reminders.

[0053] For example, if there are four lanes when entering intersection A, the directional information for the four lanes, from left to right, is left turn, straight, straight, and right turn, respectively. If the electronic map is updated according to the method provided in this embodiment, the target exit road corresponding to the first straight lane on the left is Road 1, and the target exit road corresponding to the second straight lane on the left is Road 2. If the navigation path is to enter Road 1, the directional arrow of the first straight lane on the left will be highlighted on the navigation interface to provide navigation reminders and prevent the driver from mistakenly entering Road 2 when the second straight lane is highlighted.

[0054] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure. Figure 2 The image shows two road scene images of type directional sign images; according to Figure 2 From the left image, the term "viaduct" representing the road type can be extracted, and since "viaduct" is located below the directional arrow, the road scene in the left image is a valid road scene; according to Figure 2 The image on the right can be used to extract the road name "Zhongshanmen Bridge", but "Zhongshanmen Bridge" corresponds to all the straight lanes below, so the road scene in the image on the right is not a valid road scene.

[0055] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure. Figure 3The diagram illustrates how the lane connection path is determined in this embodiment: If the road form of candidate exit road 1 corresponding to a right turn is an elevated bridge and the road form of candidate exit road 2 is ground level; following the order from left to right, if the target lane is the first right turn lane on the left, and the target text extracted from the road scene image in this embodiment is ground level, then candidate exit road 2, which has a ground level form, will be used as the connection path of the target lane; if the target lane is the second right turn lane on the left, and the target text extracted from the road scene image in this embodiment is an elevated bridge, then candidate exit road 1, which has an elevated bridge form, will be used as the connection path of the target lane.

[0056] Figure 4 This is a schematic diagram according to the fourth embodiment of this disclosure. (See diagram below.) Figure 4 As shown, the device 400 for determining the connectivity path of a lane in this embodiment includes:

[0057] Processing unit 401 is used to determine the target lane, obtain the number of candidate exit roads corresponding to the target lane, and the number of lanes with the same guidance information as the target lane;

[0058] Determining unit 402 is used to acquire a road scene image when both the number of roads and the number of lanes are determined to be multiple.

[0059] Extraction unit 403 is used to extract target text from the road scene image when the road scene in the road scene image is determined to be a valid road scene;

[0060] The connectivity unit 404 is used to select a target exit road from the candidate exit roads according to the target text, and use the target exit road as the connectivity path of the target lane.

[0061] When determining the target lane, the processing unit 401 may use the lane corresponding to the location information and / or name input by the input terminal as the target lane, or it may use the lane selected by the input terminal from the electronic map as the target lane.

[0062] When determining the target lane, the processing unit 401 may also use the following method: determine the candidate lane and obtain the number of times the candidate lane has a navigation reminder error; if the number of errors exceeds a preset threshold, the candidate lane is used as the target lane.

[0063] In other words, the target lane determined by the processing unit 401 can be a lane that has a high number of navigation warning errors. By determining the connection path of such a target lane, a more accurate connection relationship between the lane and the exit road can be established, thereby avoiding the recurrence of navigation warning errors and improving the accuracy of navigation warnings.

[0064] This embodiment does not limit the method of determining candidate lanes or the number of candidate lanes determined; there can be one or more candidate lanes. This embodiment also does not limit the number of target lanes determined; there can be one or more target lanes.

[0065] After determining the target lane, the processing unit 401 performs the steps of obtaining the number of candidate exit roads corresponding to the target lane and the number of lanes with the same guidance information as the target lane.

[0066] It is understandable that when there are multiple target lanes, the processing unit 401 will obtain the number of roads and lanes corresponding to each target lane, and then perform subsequent operations based on the number of roads and lanes corresponding to each target lane.

[0067] In this embodiment, the road where the target lane is located is an entry road, which is the road where the driving direction enters the intersection, and the exit road is the road where the driving direction moves away from the intersection. The guidance information is used to indicate the driving direction of the lane, which can be determined by the lane's guidance arrows (such as U-turn arrows, left turn arrows, straight arrows and right turn arrows, etc.), guidance text, etc. The driving direction of the lane includes at least one of U-turn, left turn, straight and right turn.

[0068] When acquiring the number of roads, the processing unit 401 can first determine the candidate exit roads corresponding to the target lane, and then acquire the number of roads based on the determined candidate exit roads.

[0069] The processing unit 401 can determine the exit road corresponding to the target lane based on the road database, which stores the correspondence between lanes (lane location information and / or name) and exit roads; based on the determined candidate exit roads, this embodiment can further obtain the road name and / or road shape name of the candidate exit roads.

[0070] In addition, when determining the candidate exit road corresponding to the target lane, the processing unit 401 may also use the following method: determine the entry road according to the target lane; obtain all exit roads corresponding to the entry road and obtain the road angle between the entry road and each exit road; determine the target angle range according to the guidance information of the target lane; and take the exit roads whose road angle is within the target angle range as the candidate exit roads corresponding to the target lane.

[0071] When acquiring the number of lanes, the processing unit 401 can first determine the lanes that have the same guidance information as the target lane, and then acquire the number of lanes based on the determined lanes.

[0072] The processing unit 401 can determine lanes with the same guidance information as the target lane based on the road database. The road database stores the access road where the lane (lane location information and / or name) is located and the guidance information of each lane in the access road. For example, it can determine the lane with the same guidance arrow as the target lane in the access road where the target lane is located.

[0073] In addition, the processing unit 401 can also acquire road scene images (such as guide sign images, road surface images, etc.) corresponding to the target lane, and determine the lane with the same guidance information as the target lane based on the road scene images.

[0074] In this embodiment, after the processing unit 401 obtains the number of roads and lanes corresponding to the target lane, the determining unit 402 obtains a road scene image when it is determined that there are multiple roads and multiple lanes.

[0075] The road scene image acquired by the determining unit 402 corresponds to the target lane and can be at least one of the following: a guide sign image located near the intersection into which the target lane is to enter, and a road surface image corresponding to the target lane.

[0076] The determining unit 402 can use the image corresponding to the target lane in the road database as the road scene image, or it can use the image collected in real time according to the target lane as the road scene image.

[0077] In other words, the determining unit 402 determines whether to acquire a road scene image based on the judgment result that the number of roads and lanes are both multiple. This avoids performing additional road scene image acquisition operations when the number of roads and lanes does not meet the requirements, reduces the waste of computing resources, and improves the accuracy of road scene image acquisition.

[0078] In this embodiment, after the determining unit 402 acquires the road scene image, the extraction unit 403 extracts the target text from the road scene image if it determines that the road scene in the road scene image is a valid road scene; wherein, the extracted target text corresponds to the target lane.

[0079] When determining that a road scene in a road scene image is a valid road scene, the extraction unit 403 may adopt the following optional implementation methods: extract road text features from the road scene image; and determine that the road scene in the road scene image is a valid road scene if the extracted road text features match the valid scene features.

[0080] The road text features extracted by the extraction unit 403 from the road scene image can be at least one of the following: road text such as road form (ground, tunnel, viaduct, auxiliary road, ramp, etc.) name and / or road name, the relationship between road text and directional arrows, and the relationship between road text and lanes.

[0081] The effective scene features used by the extraction unit 403 are obtained in advance. The effective scene features are at least one of the following: the road text is a road shape name or road name, the road text is located below the directional arrow, and the road text corresponds to a part of the lane (the part of the lane includes the target lane and the lane with the same directional information as the target lane).

[0082] Therefore, if the extraction unit 403 determines that the road scene in the road scene image is a valid road scene based on at least one of the following: the road text feature is the road shape name or road name; the road text feature is the extracted road shape name or the road name is located below the guide arrow; or the road text feature is the extracted road shape name or the road name corresponds to a part of the lane.

[0083] In addition, when the extraction unit 403 determines that the road scene in the road scene image is a valid road scene, it can also input the road scene image into the pre-trained scene recognition model. If the output result of the scene recognition model is determined to be a preset result, the road scene in the road scene image is determined to be a valid road scene. In this embodiment, the preset result is 1.

[0084] It is understandable that the scene recognition model used by the extraction unit 403 is pre-trained; by acquiring road scene images that are valid road scenes as training samples, the neural network model is trained to obtain the scene recognition model.

[0085] After determining that the road scene in the road scene image is a valid road scene, the extraction unit 403 performs the step of extracting target text from the road scene image.

[0086] When extracting target text from a road scene image, the extraction unit 403 can first obtain the road text extracted from the road scene image, and then use the road text corresponding to the target lane as the target text. The target text is used to reflect the road name and / or road shape of the target exit road corresponding to the target lane.

[0087] In this embodiment, after the extraction unit 403 extracts the target text from the road scene image, the connection unit 404 selects the target exit road from the candidate exit roads according to the target text and uses the target exit road as the connection path of the target lane.

[0088] When the connectivity unit 404 selects the target exit road from the candidate exit roads based on the target text, the optional implementation method is as follows: obtain the road shape name and / or road name of each candidate exit road; and take the candidate exit road whose road shape name and / or road name matches the target text as the target exit road.

[0089] The number of target exit roads selected by the connecting unit 404 can be one or more; if there are multiple target exit roads, the connecting unit 404 can use any one of the target exit roads as the connecting path of the target lane.

[0090] After the connection unit 404 uses the target exit road as the connection path of the target lane, it can record the connection relationship between the target lane and the target exit road, and then use the recorded connection relationship to update the electronic map, so as to achieve the purpose of using the updated connection relationship for navigation reminders.

[0091] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0092] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0093] like Figure 5 The diagram shown is a block diagram of an electronic device for a method of determining a lane connectivity path according to an embodiment of the present disclosure. 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0094] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0095] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of displays, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0096] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as methods for determining the connectivity path of lanes. For example, in some embodiments, the method for determining the connectivity path of lanes may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508.

[0097] In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the method for determining the connectivity path of lanes described above may be performed. Alternatively, in other embodiments, computing unit 501 may be configured to perform the method for determining the connectivity path of lanes by any other suitable means (e.g., by means of firmware).

[0098] Various implementations of the systems and techniques described 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to the processor or controller of a general-purpose computer, special-purpose computer, or other programmable device for determining the connectivity path of lanes, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for showing information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0103] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the management difficulties and weak business scalability inherent in traditional physical hosts and VPS (Virtual Private Server) services. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0104] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining the connectivity path of lanes, comprising: Determine the target lane, and obtain the number of candidate exit routes corresponding to the target lane, as well as the number of lanes with the same guidance information as the target lane; When both the number of roads and the number of lanes are determined to be multiple, a road scene image is acquired; If the road scene in the road scene image is determined to be a valid road scene, target text is extracted from the road scene image, and the target text is the road text in the road scene image corresponding to the target lane; Select a target exit road from the candidate exit roads based on the target text, and use the target exit road as the connecting path of the target lane; The process of determining the candidate exit route corresponding to the target lane includes: Determine the entry road based on the target lane; Obtain all exit roads corresponding to the entry road, and obtain the road angle between the entry road and each exit road; The target angle range is determined based on the guidance information of the target lane; Exit roads whose road angle is within the target angle range are considered as candidate exit roads corresponding to the target lane. The step of selecting a target exit road from the candidate exit roads based on the target text includes: obtaining the road shape name and / or road name of each candidate exit road; Candidate exit roads whose road shape names and / or road names match the target text are selected as the target exit roads.

2. The method according to claim 1, wherein, The determination of the target lane includes: Determine candidate lanes and obtain the number of times navigation alerts for the candidate lanes are incorrect; If the number of errors exceeds a preset threshold, the candidate lane is selected as the target lane.

3. The method according to any one of claims 1-2, wherein, Determining that the road scene in the road scene image is a valid road scene includes: Extract road text features from the road scene image; If the road text features match the valid scene features, the road scene in the road scene image is determined to be a valid road scene.

4. The method according to claim 3, wherein, The step of determining whether the road text features match the effective scene features includes: If the road text feature is determined to be a road shape name or a road name, then the road text feature is determined to match the valid scene feature.

5. The method according to any one of claims 3-4, wherein, The step of determining whether the road text features match the effective scene features includes: If the road text feature is determined to be a road shape name or a road name located below a directional arrow, then the road text feature is determined to match a valid scene feature.

6. The method according to any one of claims 3-5, wherein, The step of determining whether the road text features match the effective scene features includes: If the road text feature is determined to be a road shape name or a road name that corresponds to a portion of the lanes, then the road text feature is determined to match the effective scene feature.

7. The method according to any one of claims 1-2, wherein, Determining that the road scene in the road scene image is a valid road scene includes: The road scene image is input into a pre-trained scene recognition model; If the output of the scene recognition model is determined to be a preset result, the road scene in the road scene image is determined to be a valid road scene.

8. An apparatus for determining the connectivity path of a lane, comprising: The processing unit is used to determine the target lane, obtain the number of candidate exit roads corresponding to the target lane, and the number of lanes with the same guidance information as the target lane; The determining unit is used to acquire a road scene image when both the number of roads and the number of lanes are determined to be multiple. An extraction unit is configured to extract target text from the road scene image when the road scene in the road scene image is determined to be a valid road scene, wherein the target text is the road text in the road scene image corresponding to the target lane; A connectivity unit is used to select a target exit road from the candidate exit roads based on the target text, and to use the target exit road as the connectivity path of the target lane; Specifically, when determining the candidate exit route corresponding to the target lane, the processing unit performs the following: Determine the entry road based on the target lane; Obtain all exit roads corresponding to the entry road, and obtain the road angle between the entry road and each exit road; The target angle range is determined based on the guidance information of the target lane; Exit roads whose road angle is within the target angle range are considered as candidate exit roads corresponding to the target lane. When the connectivity unit selects a target exit path from the candidate exit paths based on the target text, it specifically performs the following: Obtain the road morphology name and / or road name for each candidate exit road; Candidate exit roads whose road shape names and / or road names match the target text are selected as the target exit roads.

9. The apparatus according to claim 8, wherein, When determining the target lane, the processing unit specifically performs the following: Determine candidate lanes and obtain the number of times navigation alerts for the candidate lanes are incorrect; If the number of errors exceeds a preset threshold, the candidate lane is selected as the target lane.

10. The apparatus according to any one of claims 8-9, wherein, When the extraction unit determines that the road scene in the road scene image is a valid road scene, it specifically performs the following: Extract road text features from the road scene image; If the road text features match the valid scene features, the road scene in the road scene image is determined to be a valid road scene.

11. The apparatus according to claim 10, wherein, When the extraction unit determines that the road text features match the valid scene features, it specifically performs the following: If the road text feature is determined to be a road shape name or a road name, then the road text feature is determined to match the valid scene feature.

12. The apparatus according to any one of claims 10-11, wherein, When the extraction unit determines that the road text features match the valid scene features, it specifically performs the following: If the road text feature is determined to be a road shape name or a road name located below a directional arrow, then the road text feature is determined to match a valid scene feature.

13. The apparatus according to any one of claims 10-12, wherein, When the extraction unit determines that the road text features match the valid scene features, it specifically performs the following: If the road text feature is determined to be a road shape name or a road name that corresponds to a portion of the lanes, then the road text feature is determined to match the effective scene feature.

14. The apparatus according to any one of claims 8-9, wherein, When the extraction unit determines that the road scene in the road scene image is a valid road scene, it specifically performs the following: The road scene image is input into a pre-trained scene recognition model; If the output of the scene recognition model is determined to be a preset result, the road scene in the road scene image is determined to be a valid road scene.

15. 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 to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

17. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images