Method and device for determining confidence coefficient of lane position

Abstract

The invention provides a method and device for determining the confidence coefficient of a lane position, and relates to the technical field of artificial intelligence, in particular to the technical fields of map navigation, automatic driving, intelligent traffic and the like. According to the specific implementation scheme, a road network lane group of a road where a vehicle is located and an initial lane position of the vehicle in the road network lane group are determined according to positioning information of the vehicle; identifying the front road image of the vehicle, and determining a visual lane group and a relative lane position of the vehicle in the visual lane group; determining a reference lane position based on the road network lane group, the visual lane group and the relative lane position; a confidence of the initial lane position is determined based on the reference lane position. According to the mode, effective evaluation of the lane-level positioning information of the vehicle is realized.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as map navigation, autonomous driving, and intelligent transportation, and more particularly to a method and device for determining the confidence level of a lane position. Background Art

[0002] The most important core technology of lane-level trajectory mining is lane-level trajectory matching. The existing methods for evaluating lane trajectory matching results mainly include evaluation based on positioning quality and evaluation based on matching offset and matching angle.

[0003] However, both methods strongly rely on the positioning effect of the original GPS (Global Positioning System) positioning points. Once the positioning is offset, the existing methods cannot effectively evaluate the matching quality. Summary of the invention

[0004] Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for determining the confidence level of a lane position.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for determining the confidence of a lane position, the method comprising: determining a road network lane group of a road on which a vehicle is located and an initial lane position of the vehicle in the road network lane group based on the positioning information of the vehicle; identifying an image of a road in front of the vehicle to determine a visual lane group and a relative lane position of the vehicle in the visual lane group; determining a reference lane position based on the road network lane group, the visual lane group and the relative lane position; and determining the confidence of the initial lane position based on the reference lane position.

[0006] In a second aspect, an embodiment of the present disclosure provides a device for determining the confidence of a lane position, the device comprising: a road network determination module, a visual determination module, a position determination module and a position evaluation module, wherein the road network determination module is configured to determine the road network lane group of the road on which the vehicle is located and the initial lane position of the vehicle in the road network lane group based on the positioning information of the vehicle; the visual determination module is configured to recognize the road image in front of the vehicle, determine the visual lane group and the relative lane position of the vehicle in the visual lane group; the position determination module is configured to determine the reference lane position based on the road network lane group, the visual lane group and the relative lane position; the position evaluation module is configured to determine the confidence of the initial lane position based on the reference lane position.

[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising one or more processors; a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a method for determining the confidence of a lane position as in any embodiment of the first aspect.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining the confidence of a lane position as in any embodiment of the first aspect.

[0009] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements a method for determining the confidence of a lane position as in any embodiment of the first aspect.

[0010] The present disclosure realizes effective evaluation of lane-level positioning information of a vehicle.

[0011] 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

[0012] Figure 1 is an exemplary system architecture diagram in which the present disclosure may be applied;

[0013] Figure 2 is a flow chart of an embodiment of a method for determining the confidence level of a lane position according to the present disclosure;

[0014] Figure 3 is a flow chart of another embodiment of a method for determining the confidence level of a lane position according to the present disclosure;

[0015] Figure 4 is a schematic diagram of an application scenario of the lane position confidence determination method disclosed in the present invention;

[0016] Figure 5 is a schematic diagram of an embodiment of a lane position confidence determination device according to the present disclosure;

[0017] Figure 6 It is a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] 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, the description of well-known functions and structures is omitted in the following description.

[0019] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the lane position confidence determination method of the present disclosure may be applied.

[0021] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0022] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc.

[0023] The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are software, they may be installed in the electronic devices listed above. They may be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0024] Server 105 can be a server that provides various services, for example, determining the road network lane group of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group based on the vehicle's positioning information; identifying the road image in front of the vehicle to determine the visual lane group and the relative lane position of the vehicle in the visual lane group; determining the reference lane position based on the road network lane group, the visual lane group and the relative lane position; and determining the confidence level of the initial lane position based on the reference lane position.

[0025] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, for providing lane position confidence determination services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0026] It should be noted that the lane position confidence determination method provided in the embodiment of the present disclosure may be executed by the server 105, or by the terminal devices 101, 102, 103, or by the server 105 and the terminal devices 101, 102, 103 in cooperation with each other. Accordingly, the various parts (such as various units, sub-units, modules, sub-modules) included in the lane position confidence determination device may be all arranged in the server 105, or all arranged in the terminal devices 101, 102, 103, or respectively arranged in the server 105 and the terminal devices 101, 102, 103.

[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0028] Figure 2 A process 200 of an embodiment of a method for determining the confidence level of a lane position is shown. The method for determining the confidence level of a lane position may specifically include the following steps:

[0029] Step 201, determining the road network lane group of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group according to the positioning information of the vehicle.

[0030] In this embodiment, the execution subject (for example, Figure 1 The server 105 or terminal devices 101, 102, 103) can obtain the vehicle's positioning information via the positioning component, and match the vehicle's positioning information with the high-precision map to determine the road network lane group of the vehicle and the vehicle's initial lane position in the road network lane group.

[0031] Among them, the positioning information may include longitude, latitude, heading angle, etc., and the positioning component may be a component used to determine the vehicle position in existing technology or future development technology, such as a GPS navigator, antenna, sensor, etc., which is not limited in this application.

[0032] Here, the road network lane group may include lane information of all lanes in the road where the vehicle is located. The lane information may include at least one of the following: lane line information, ground sign information, traffic sign information, sorting information of lanes in the road network lane group, etc. The lane line information may include at least one of the following: lane line type, lane line color, the distance between the current lane line and the adjacent lane line, the distance between the current lane line and the road boundary, etc.

[0033] Among them, the initial lane position of the vehicle in the road network lane group, that is, the lane-level position of the vehicle in the road network lane group, can be represented by the lane line position corresponding to the lane where the vehicle is located, and can also be represented by the order of the lane where the vehicle is located in the road network lane group from left to right or from right to left, for example, the first lane, the second lane, etc., and this application does not limit this.

[0034] Step 202 , recognize the road image ahead of the vehicle, and determine the visual lane group and the relative lane position of the vehicle in the visual lane group.

[0035] In this embodiment, the execution entity may collect the image of the road ahead of the vehicle via an image collection component installed in front of the vehicle (eg, inside the windshield, above the hood, etc.), and perform preprocessing operations on the image of the road ahead.

[0036] Among them, the image acquisition component can be a component that uses optical imaging principles in existing technologies or future development technologies to form images, such as a camera, a video camera, etc., and this application does not limit this.

[0037] Here, the preprocessing operation is used to indicate an operation for improving image quality, which may specifically include: noise reduction, enhancement, de-distortion and other operations.

[0038] Furthermore, the execution subject may use a lane detection algorithm to perform lane detection on the front road image after the preprocessing operation to determine the visual lane group and the relative lane position of the vehicle in the visual lane group. The lane detection algorithm may include a lane line detection algorithm, a road sign detection algorithm, etc.

[0039] Specifically, the execution entity may use a lane line detection algorithm to perform lane line detection on the front road image after the preprocessing operation, determine the lane lines on both sides of the lane where the vehicle is located and the lane lines of the adjacent lanes, and determine the visual lane group and the relative lane position of the vehicle in the visual lane group based on the lane lines on both sides of the lane where the vehicle is located and the lane lines of the adjacent lanes.

[0040] The visual lane group may include lane information of all lanes in the front road image.

[0041] Here, the relative lane position of the vehicle in the visual lane group, that is, the relative lane-level position of the vehicle in the visual lane group, can be characterized by the order of the lanes in which the vehicle is located in the visual lane group from left to right or from right to left. For example, the visual lane group includes two lanes, and the relative lane-level position of the vehicle in the visual lane group is the left lane of the two lanes.

[0042] Step 203, determining a reference lane position based on the road network lane group, the visual lane group and the relative lane position.

[0043] In this embodiment, after determining the road network lane group, the visual lane group and the relative lane position, the execution entity can determine the reference lane position, that is, the reference lane level position, based on the lane information included in the road network lane group, the lane information included in the visual lane group and the relative lane position.

[0044] Specifically, the road network lane group includes three lanes, which are the first lane, the second lane and the third lane from left to right, and the visual lane group includes two lanes, and the relative lane position is the left lane of the two lanes. If the lane information of the three lanes included in the road network lane group is matched with the lane information of the two lanes included in the visual lane group (for example, road signs, lane lines, etc.), it is determined that the two lanes included in the visual lane group are the second lane and the third lane, and the relative lane position is the left lane of the two lanes included in the visual lane group, then the reference lane position of the second lane can be determined.

[0045] Step 204 : determining the confidence level of the initial lane position based on the reference lane position.

[0046] In this embodiment, the execution entity can directly determine the confidence of the initial lane position based on whether the reference lane position matches the initial lane position; it can also determine the confidence of the initial lane position based on the distance between the reference lane position and the initial lane position, and this application does not limit this.

[0047] Among them, the confidence of the initial lane position is usually negatively correlated with the distance between the reference lane position and the initial lane position, that is, the greater the distance between the reference lane position and the initial lane position, the smaller the confidence of the initial lane position, and the smaller the distance between the reference lane position and the initial lane position, the greater the confidence of the initial lane position.

[0048] The method for determining the confidence of lane position provided by the embodiments of the present disclosure determines the road network lane group of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group according to the positioning information of the vehicle; recognizes the road image in front of the vehicle to determine the visual lane group and the relative lane position of the vehicle in the visual lane group; determines the reference lane position based on the road network lane group, the visual lane group and the relative lane position; determines the confidence of the initial lane position based on the reference lane position, that is, uses the road network lane group and the visual lane group to determine the reference lane position to evaluate the initial lane position, avoids direct evaluation based on GPS positioning information, reduces the impact of GPS positioning errors, and realizes effective evaluation of the lane-level positioning information of the vehicle.

[0049] In some optional embodiments, the method also includes: in response to determining that the confidence of the initial lane position is greater than or equal to a preset confidence threshold, based on the initial lane position, performing at least one of the following: determining road lane-level traffic information; determining lane-level candidate planning trajectories; determining vehicle lane-level control strategies.

[0050] In this implementation, the execution entity can determine whether the confidence of the initial lane position is greater than or equal to a preset confidence threshold. If so, the execution entity can determine the lane-level trajectory data based on the initial lane position, and determine the road lane-level traffic information based on the lane-level trajectory data.

[0051] Among them, road lane-level traffic information may include lane usage frequency, traffic density, lane usage, etc. Road lane-level traffic information can help optimize lane allocation and signal light control to alleviate traffic congestion and other problems.

[0052] Furthermore, the execution entity can determine lane-level candidate planning trajectories based on the lane-level trajectory data to avoid lanes with high-frequency lane changes or frequent accidents, thereby enhancing the reliability and safety of autonomous driving.

[0053] Furthermore, the execution entity can perform high-precision driving behavior modeling based on lane-level trajectory data and determine lane-level control strategies, so that the autonomous driving system can better learn the behavior patterns of human drivers, such as lane changing, overtaking, and avoidance.

[0054] Further references Figure 3 , which shows Figure 2 A process 300 of another embodiment of a method for determining the confidence level of a lane position is shown. In this embodiment, the process 300 of the method for determining the confidence level of a lane position may include the following steps:

[0055] Step 301, determining the road network lane group of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group according to the positioning information of the vehicle.

[0056] In this embodiment, the implementation details and technical effects of step 301 can refer to the description of step 201 and will not be repeated here.

[0057] Step 302 , identifying the road image ahead of the vehicle, and determining a visual lane group and a relative lane position of the vehicle in the visual lane group.

[0058] In this embodiment, the implementation details and technical effects of step 302 can refer to the description of step 202 and will not be repeated here.

[0059] Step 303, determining a reference lane position based on the road network lane group, the visual lane group and the relative lane position.

[0060] In this embodiment, the implementation details and technical effects of step 303 can refer to the description of step 203, which will not be repeated here.

[0061] Step 304: Match the reference lane position and the initial lane position to determine a first matching result.

[0062] In this embodiment, the execution entity can directly determine the first matching result based on whether the reference lane position matches the initial lane position; or determine the first matching result based on the distance between the reference lane position and the initial lane position, which is not limited in this application.

[0063] Step 305: Match the road network lane group with the visual lane group to determine a second matching result.

[0064] In this embodiment, the execution entity can directly determine the first matching result based on whether the road network lane group matches the visual lane group; it can also calculate the matching degree of the road network lane group and the visual lane group, and determine the second matching result based on the matching degree of the two. This application does not limit this.

[0065] Step 306 : Determine the confidence level of the initial lane position based on the first matching result and the second matching result.

[0066] In this embodiment, the execution entity may determine the confidence level of the initial lane position based on the first matching result, the first preset weight corresponding to the first matching result, the second matching result, and the second preset weight corresponding to the second matching result.

[0067] Among them, the first preset weight and the second preset weight can be set according to experience and actual needs.

[0068] The above embodiments of the present disclosure, Figure 2 Compared with the illustrated embodiment, it highlights matching the reference lane position with the initial lane position to determine a first matching result; matching the road network lane group with the visual lane group to determine a second matching result; and determining the confidence of the initial lane position based on the first matching result and the second matching result. That is, on the basis of the matching result of the reference lane position with the initial lane position, the influence of the matching results of the road network lane group and the visual lane group used to determine the reference lane position on the confidence of the initial lane position is further considered, thereby improving the accuracy of the confidence of the generated initial lane position.

[0069] In some optional methods, the road network lane group is matched with the visual lane group to determine a second matching result, including: generating a visual lane line type sequence based on the lane line types of the lanes included in the visual lane group; generating a road network lane line type sequence based on the lane line types of the lanes included in the road network lane group; matching the visual lane line type sequence with the road network lane line type sequence to determine a second matching result.

[0070] In this implementation, the execution entity can generate a visual lane line type sequence according to the lane line types of the lanes included in the visual lane group and the arrangement order of the lane lines (from left to right or from right to left); and generate a road network lane line type sequence according to the lane line types of the lanes included in the road network lane group and the arrangement order of the lane lines (from left to right or from right to left).

[0071] Among them, there may be many ways to divide lane line types. For example, according to whether the lane lines are continuous, they can be divided into solid line type and dashed line type; according to the number of lane lines, they can be divided into single-line type and double-line type, etc.

[0072] In addition, the lane line type may also include an unknown type.

[0073] Here, the arrangement of lane line types in the visual lane line type sequence and the road network lane line type sequence can be the same as the arrangement of actual lane lines, or the lane line types can be grouped according to the corresponding lanes and arranged in the form of lane line type groups. This application does not limit this.

[0074] Specifically, the road network lane group / visual lane group may include a first lane and a second lane. The lane line types of the two lane lines of the first lane are solid line and dashed line respectively, and the lane line types of the two lane lines of the second lane are dashed line and solid line respectively. If the lane line types are arranged according to the arrangement method of the actual lane lines, the obtained road network lane line type sequence is solid line, dashed line, solid line; if the lane line types are grouped according to the corresponding lanes and arranged in the form of lane line type groups, the obtained road network lane line type sequence is (solid line, dashed line)|(dashed line, solid line).

[0075] This implementation method generates a visual lane line type sequence based on the lane line types of the lanes included in the visual lane group; generates a road network lane line type sequence based on the lane line types of the lanes included in the road network lane group; matches the visual lane line type sequence with the road network lane line type sequence to determine a second matching result, thereby achieving direct matching based on the lane line type sequence to determine the matching result, that is, determining the matching result only based on the lane line type, thereby improving the efficiency of generating the matching result.

[0076] In some optional methods, the visual lane line type sequence and the road network lane line type sequence are matched to determine a second matching result, including: respectively encoding the visual lane line type sequence and the road network lane line type sequence to generate a visual coding sequence and a road network coding sequence; matching the visual coding sequence and the road network coding sequence to determine a second matching result.

[0077] In this implementation, the execution entity can directly encode the lane line types in the visual lane line type sequence according to the preset type coding rules to generate a visual coding sequence, and encode the lane line types in the road network lane line type sequence to generate a road network coding sequence.

[0078] Among them, the preset type coding rules and the preset type coding rules can be set according to experience and actual needs.

[0079] Specifically, the road network lane line type sequence is (single solid line, double dashed line)|(double dashed line, single dashed line)|(single dashed line, solid line), and the visual lane line type sequence is (single solid line, double dashed line)|(double dashed line, single dashed line). If the preset type coding rule is that the single solid line corresponds to the number 1, the double dashed line corresponds to the number 2, and the single dashed line corresponds to the number 3, then the road network coding sequence is (1, 2)|(2, 3)|(3, 1), and the visual coding sequence is (1, 2)|(2, 3).

[0080] This implementation method generates a visual coding sequence and a road network coding sequence by respectively encoding the visual lane line type sequence and the road network lane line type sequence; the visual coding sequence and the road network coding sequence are matched to determine a second matching result, thereby achieving matching based on the coding sequence and further improving the efficiency of generating matching results.

[0081] In some optional embodiments, the lane line type may include a solid line type and a dashed line type.

[0082] In this implementation, the execution entity may encode the visual lane line type sequence and the road network lane line type sequence respectively according to a preset type encoding rule to generate a visual encoding sequence and a road network encoding sequence.

[0083] Among them, the lane line types may include solid line types and dashed line types. The lane line types corresponding to the solid line type may include: double solid line, single solid line, left dashed line and right solid line, left solid line and right dashed line, and road boundary solid line; the lane line types corresponding to the dashed line type may include: long dashed line, short dashed line, double dashed line, artificial virtual line, and fuzzy virtual line.

[0084] Specifically, the lane line type may include a dashed line type and a solid line type, the solid line type is coded as 3, and the dashed line type is coded as 8. If the road network lane line type sequence is (single solid line, double dashed line)|(double dashed line, single dashed line)|(single dashed line, solid line), and the visual lane line type sequence is (single solid line, double dashed line)|(double dashed line, single dashed line), then the road network lane line type sequence is (solid line, dashed line)|(dash line, dashed line)|(dash line, solid line), and the visual lane line type sequence is (solid line, dashed line)|(dash line, dashed line); further, according to the preset type coding rule, the road network lane line type sequence is encoded to generate a road network coding sequence (3, 8)|(8, 8)|(8, 3), and the visual lane line type sequence is encoded to generate a visual coding sequence (3, 8)|(8, 8).

[0085] This method effectively reduces the types of codes in the matching coding sequence by setting the lane line type to include a solid line type and a dashed line type, thereby further improving the matching efficiency.

[0086] In some optional methods, the reference lane position is determined based on the road network lane group, the visual lane group and the relative lane position, including: determining the reference lane position based on the road network coding sequence, the visual coding sequence and the relative lane position.

[0087] In this implementation, the execution entity can determine the reference lane position according to the road network coding sequence corresponding to the road network lane group, the visual coding sequence corresponding to the visual lane group, and the relative lane position.

[0088] Specifically, the road network lane group includes three lanes, which are the first lane, the second lane and the third lane from left to right. The road network coding sequence corresponding to the road network lane group is (3, 8)|(8, 8)|(8, 3). The visual lane group includes two lanes, which are the left lane and the right lane from left to right. The visual coding sequence corresponding to the visual lane group is (3, 8)|(8, 8). If the relative lane position is that the vehicle is in the rightmost lane in the visual lane group, it can be determined that the reference lane position is the second lane.

[0089] This implementation method determines the reference lane position based on the road network coding sequence, the visual coding sequence and the relative lane position, thereby effectively improving the efficiency of determining the reference lane position.

[0090] In some optional embodiments, the confidence of the initial lane position is determined based on the first matching result and the second matching result, including: in response to determining that the first matching result and the second matching result are both mismatches, determining the confidence of the initial lane position to be a first value; in response to determining that the first matching result is a mismatch and the second matching result is a match, determining the confidence of the initial lane position to be a second value; in response to determining that the first matching result is a match and the second matching result is a mismatch, determining the confidence of the initial lane position to be a third value; in response to determining that the first matching result is a match and the second matching result is a mismatch, determining the confidence of the initial lane position to be a fourth value.

[0091] In this implementation, the execution entity can judge the first matching result and the second matching result. If the first matching result and the second matching result are both mismatches, the confidence of the initial lane position can be determined to be the first value; if the first matching result is mismatch and the second matching result is match, the confidence of the initial lane position can be determined to be the second value; if the first matching result is match and the second matching result is mismatch, the confidence of the initial lane position can be determined to be the third value; if the first matching result and the second matching result are both matches, the confidence of the initial lane position can be determined to be the fourth value.

[0092] Among them, the first value, the second value, the third value and the fourth value increase in sequence. For example, the first value is 0.1, the second value is 0.2, the third value is 0.8, and the fourth value is 1.

[0093] This implementation method determines whether the first matching result and the second matching result match, and determines the confidence level of the initial lane position.

[0094] In some optional embodiments, matching the reference lane position with the initial lane position to determine a first matching result includes: determining the first matching result based on a distance between the reference lane position and the initial lane position.

[0095] In this implementation, the execution entity may calculate the distance between the reference lane position and the initial lane position, and determine the first matching result according to the distance between the reference lane position and the initial lane position.

[0096] Among them, the value of the first matching result is usually negatively correlated with the distance between the reference lane position and the initial lane position, that is, the larger the distance, the smaller the value of the first matching result, and the smaller the distance, the larger the value of the first matching result.

[0097] This implementation method further improves the accuracy of the determined confidence by determining the first matching result based on the distance between the reference lane position and the initial lane position, and determining the confidence of the initial lane position based on the first matching result and the second matching result.

[0098] In some optional methods, matching the road network lane group with the visual lane group to determine a second matching result includes: determining the second matching result based on a similarity between the road network lane group and the visual lane group.

[0099] In this implementation, the execution entity may calculate the similarity between the lane information of the lanes included in the road network lane group and the lane information of the lanes included in the visual lane group, and determine the second matching result based on the calculated similarity.

[0100] The value of the second matching result is usually positively correlated with the calculated similarity, that is, the greater the similarity, the greater the value of the second matching result, and the smaller the similarity, the smaller the value of the second matching result.

[0101] This implementation method further improves the accuracy of the determined confidence by determining the second matching result according to the similarity between the road network lane group and the visual lane group, and determining the confidence of the initial lane position based on the first matching result and the second matching result.

[0102] Continue to see Figure 4 , Figure 4 It is a schematic diagram of an application scenario of the method for determining the confidence level of lane position according to this embodiment.

[0103] The execution subject 401 can obtain the positioning information of the vehicle through the positioning component installed on the vehicle, and determine the road network lane group 402 of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group according to the matching of the vehicle positioning information and the high-precision map. For example, the road network lane group 402 includes: the first lane: the solid road boundary line on the left and the solid yellow line on the right; the second lane: the solid yellow line on the left and the dotted line on the right; the third lane: the dotted line on the left and the solid line on the right; the fourth lane: the solid line on the left and the solid road boundary line on the right. The initial lane position is the second lane.

[0104] The execution subject may collect the road image in front of the vehicle through the image acquisition component installed in front of the vehicle, and perform preprocessing operation on the road image in front. Further, the execution subject may use the lane detection algorithm to perform lane detection on the road image in front after the preprocessing operation to determine the visual lane group 403 and the relative lane position of the vehicle in the visual lane group 403. Among them, the visual lane group includes: left lane: left solid line, right dashed line; right lane: left dashed line, right solid line. The relative lane position is the left lane.

[0105] Furthermore, the execution entity may encode the road network lane group and the visual lane group according to the lane line types of the lane lines included in the road network lane group 402 and the visual lane group 403 to obtain a road network coding sequence, such as (3, 3)|(3, 8)|(8, 3)|(3, 3) and a visual coding sequence, such as (3, 8)|(8, 3).

[0106] Furthermore, the execution entity can determine the reference lane position, i.e., the second lane, based on the road network coding sequence, the visual coding sequence and the relative lane position; match the reference lane position with the initial lane position to determine a first matching result; match the visual coding sequence with the road network coding sequence to determine a second matching result, and determine the confidence level of the initial lane position based on the first matching result and the second matching result.

[0107] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a lane position confidence determination device, which is similar to Figure 2 The method embodiments shown correspond.

[0108] like Figure 5 As shown, the lane position confidence determination device 500 of this embodiment includes: a road network determination module 501, a visual determination module 502, a position determination module 503 and a position evaluation module 504.

[0109] Among them, the road network determination module 501 can be configured to determine the road network lane group of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group according to the positioning information of the vehicle.

[0110] The visual determination module 502 may be configured to recognize the road image ahead of the vehicle, determine the visual lane group and the relative lane position of the vehicle in the visual lane group.

[0111] The position determination module is configured to determine a reference lane position based on a road network lane group, a visual lane group and a relative lane position.

[0112] The position evaluation module is configured to determine a confidence level of the initial lane position based on the reference lane position.

[0113] In some optional embodiments of this embodiment, the position evaluation module includes: a first matching unit, a second matching unit and a position evaluation unit, wherein the first matching unit is configured to match the reference lane position with the initial lane position to determine a first matching result; the second matching unit is configured to match the road network lane group with the visual lane group to determine a second matching result; and the position evaluation unit is configured to determine the confidence of the initial lane position based on the first matching result and the second matching result.

[0114] In some optional modes of this embodiment, the second matching unit is further configured to: generate a visual lane line type sequence based on the lane line types of the lanes included in the visual lane group; generate a road network lane line type sequence based on the lane line types of the lanes included in the road network lane group; match the visual lane line type sequence with the road network lane line type sequence to determine a second matching result.

[0115] In some optional methods of the present embodiment, the visual lane line type sequence and the road network lane line type sequence are matched to determine a second matching result, including: respectively encoding the visual lane line type sequence and the road network lane line type sequence to generate a visual coding sequence and a road network coding sequence; matching the visual coding sequence and the road network coding sequence to determine a second matching result.

[0116] In some optional methods of this embodiment, the lane line types include dashed line types and solid line types, wherein the lane line types corresponding to the solid line types include: double solid line, single solid line, left dashed line and right solid line, left solid line and right dashed line, and road boundary solid line; the lane line types corresponding to the dashed line types include: long dashed line, short dashed line, double dashed line, artificial virtual line, and fuzzy virtual line.

[0117] In some optional aspects of this embodiment, the road network determination module is further configured to: determine the reference lane position based on the road network coding sequence, the visual coding sequence and the relative lane position.

[0118] In some optional modes of this embodiment, the position evaluation unit is further configured to: in response to determining that the first matching result and the second matching result are both mismatches, determine that the confidence of the initial lane position is a first value; in response to determining that the first matching result is a mismatch and the second matching result is a match, determine that the confidence of the initial lane position is a second value; in response to determining that the first matching result is a match and the second matching result is a mismatch, determine that the confidence of the initial lane position is a third value; in response to determining that the first matching result is a match and the second matching result is a mismatch, determine that the confidence of the initial lane position is a fourth value.

[0119] In some optional aspects of this embodiment, the first matching unit is further configured to determine a first matching result based on a distance between the reference lane position and the initial lane position.

[0120] In some optional aspects of this embodiment, the second matching unit is further configured to: determine a second matching result based on a similarity between the road network lane group and the visual lane group.

[0121] In some optional embodiments of this embodiment, the device also includes a strategy execution module, which is configured to, in response to determining that the confidence of the initial lane position is greater than or equal to a preset confidence threshold, execute at least one of the following based on the initial lane position: determine road lane-level traffic information; determine lane-level candidate planning trajectories; determine vehicle lane-level control strategies.

[0122] 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.

[0123] 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.

[0124] like Figure 6 , is a block diagram of an electronic device according to a method for determining the confidence level of a lane position in accordance with an embodiment of the present disclosure.

[0125] 600 is a block diagram of an electronic device for a lane position confidence determination method 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 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 claimed herein.

[0126] like Figure 6 As shown, the electronic device includes: one or more processors 601, a memory 602, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 601 is taken as an example.

[0127] The memory 602 is a non-transitory computer-readable storage medium provided by the present disclosure. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the lane position confidence determination method provided by the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores computer instructions, which are used to enable a computer to perform the lane position confidence determination method provided by the present disclosure.

[0128] The memory 602 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the lane position confidence determination method in the embodiment of the present disclosure (for example, the attached Figure 5 The processor 601 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 602, that is, the lane position confidence determination method in the above method embodiment is implemented.

[0129] The memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created by the use of the electronic device for face tracking, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 602 may optionally include a memory remotely disposed relative to the processor 601, and these remote memories may be connected to the electronic device for lane line detection via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0130] The electronic device of the lane position confidence determination method may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0131] The input device 603 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device for lane line detection, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 604 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0132] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), 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.

[0133] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0134] 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).

[0135] 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.

[0136] A computer system may include clients and servers. Clients and servers 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 to each other.

[0137] According to the technical solution of the embodiment of the present disclosure, effective evaluation of the lane-level positioning information of the vehicle is achieved.

[0138] 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 application can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in this disclosure can be achieved, and this document is not limited here.

[0139] 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 determining the confidence of a lane position, comprising: Determine the road network lane group of the road where the vehicle is located and the initial lane position of the vehicle in the road network lane group according to the positioning information of the vehicle; Recognize the road image ahead of the vehicle, determine a visual lane group and a relative lane position of the vehicle in the visual lane group; Determining a reference lane position based on the road network lane group, the visual lane group and the relative lane position; A confidence level of the initial lane position is determined based on the reference lane position.

2. The method according to claim 1, wherein: The determining of the confidence of the initial lane position based on the reference lane position comprises: Matching the reference lane position with the initial lane position to determine a first matching result; Matching the road network lane group with the visual lane group to determine a second matching result; A confidence level of the initial lane position is determined based on the first matching result and the second matching result.

3. The method according to claim 2, wherein: The matching the road network lane group with the visual lane group to determine a second matching result includes: Generate a visual lane line type sequence based on the lane line types of the lanes included in the visual lane group; Generate a road network lane line type sequence based on the lane line types of the lanes included in the road network lane group; The visual lane line type sequence and the road network lane line type sequence are matched to determine a second matching result.

4. The method according to claim 3, wherein: The matching of the visual lane line type sequence with the road network lane line type sequence to determine a second matching result includes: Encoding the visual lane line type sequence and the road network lane line type sequence respectively to generate a visual coding sequence and a road network coding sequence; The visual coding sequence and the road network coding sequence are matched to determine a second matching result.

5. The method according to claim 4, wherein: The lane line types include dashed line types and solid line types, wherein the lane lines of the solid line type include: double solid line, single solid line, left dashed line and right solid line, left solid line and right dashed line, and road boundary solid line; the lane lines of the dashed line type include: long dashed line, short dashed line, double dashed line, artificial virtual line, and fuzzy virtual line.

6. The method according to claim 5, wherein: The determining of the reference lane position based on the road network lane group, the visual lane group and the relative lane position comprises: A reference lane position is determined based on the road network coding sequence, the visual coding sequence and the relative lane position.

7. The method according to claim 2, wherein: The determining of the confidence of the initial lane position based on the reference lane position comprises: In response to determining that both the first matching result and the second matching result are mismatches, determining the confidence level of the initial lane position to be a first value; In response to determining that the first matching result is a mismatch and the second matching result is a match, determining the confidence level of the initial lane position to be a second value; In response to determining that the first matching result is a match and the second matching result is a mismatch, determining the confidence level of the initial lane position to be a third value; In response to determining that the first matching result and the second matching result are both matches, the confidence of the initial lane position is determined to be a fourth value, wherein the first value, the second value, the third value, and the fourth value increase in sequence.

8. The method according to claim 2, wherein: The matching the reference lane position with the initial lane position to determine a first matching result includes: A first matching result is determined based on a distance between the reference lane position and the initial lane position, wherein a value of the first matching result is negatively correlated with the distance.

9. The method according to claim 2, wherein: The matching the road network lane group with the visual lane group to determine a second matching result includes: A second matching result is determined based on the similarity between the road network lane group and the visual lane group, wherein a value of the second matching result is positively correlated with the similarity.

10. The method according to any one of claims 1 to 9, further comprising: In response to determining that the confidence level of the initial lane position is greater than or equal to a preset confidence threshold, based on the initial lane position, performing at least one of the following: Determine road lane-level traffic information; Determine lane-level candidate planning trajectories; Determine the vehicle lane-level control strategy.

11. A lane position confidence determination device, comprising: A road network determination module is configured to determine a road network lane group of a road where the vehicle is located and an initial lane position of the vehicle in the road network lane group according to the positioning information of the vehicle; A visual determination module is configured to recognize a road image ahead of the vehicle, determine a visual lane group and a relative lane position of the vehicle in the visual lane group; a position determination module configured to determine a reference lane position based on the road network lane group, the visual lane group and the relative lane position; A position evaluation module is configured to determine a confidence level of the initial lane position based on the reference lane position.

12. The device according to claim 11, wherein The position evaluation module includes: a first matching unit, a second matching unit and a position evaluation unit, wherein: The first matching unit is configured to match the reference lane position with the initial lane position to determine a first matching result; The second matching unit is configured to match the road network lane group with the visual lane group to determine a second matching result; The position evaluation unit is configured to determine a confidence level of the initial lane position based on the first matching result and the second matching result.

13. The device according to claim 12, wherein: The second matching unit is further configured to: Generate a visual lane line type sequence based on the lane line types of the lanes included in the visual lane group; Generate a road network lane line type sequence based on the lane line types of the lanes included in the road network lane group; The visual lane line type sequence and the road network lane line type sequence are matched to determine a second matching result.

14. The device according to claim 13, wherein: The matching of the visual lane line type sequence with the road network lane line type sequence to determine a second matching result includes: Encoding the visual lane line type sequence and the road network lane line type sequence respectively to generate a visual coding sequence and a road network coding sequence; The visual coding sequence and the road network coding sequence are matched to determine a second matching result.

15. The device according to claim 14, wherein: The lane line types include dashed line types and solid line types, wherein the lane line types corresponding to the solid line types include: double solid line, single solid line, left dashed line and right solid line, left solid line and right dashed line, and road boundary solid line; the lane line types corresponding to the dashed line types include: long dashed line, short dashed line, double dashed line, artificial virtual line, and fuzzy virtual line.

16. The device according to claim 15, wherein: The road network determination module is further configured to: A reference lane position is determined based on the road network coding sequence, the visual coding sequence and the relative lane position.

17. The device according to claim 12, wherein: The position evaluation unit is further configured to: In response to determining that both the first matching result and the second matching result are mismatches, determining the confidence level of the initial lane position to be a first value; In response to determining that the first matching result is a mismatch and the second matching result is a match, determining the confidence level of the initial lane position to be a second value; In response to determining that the first matching result is a match and the second matching result is a mismatch, determining the confidence level of the initial lane position to be a third value; In response to determining that the first matching result and the second matching result are both matches, the confidence of the initial lane position is determined to be a fourth value, wherein the first value, the second value, the third value, and the fourth value increase in sequence.

18. The device according to claim 12, wherein: The first matching unit is further configured to: A first matching result is determined based on a distance between the reference lane position and the initial lane position, wherein a value of the first matching result is negatively correlated with the distance.

19. The device according to claim 12, wherein: The second matching unit is further configured to: A second matching result is determined based on the similarity between the road network lane group and the visual lane group, wherein a value of the second matching result is positively correlated with the similarity.

20. The device according to any one of claims 11 to 19, further comprising: A policy execution module, wherein the policy execution module is configured to: In response to determining that the confidence level of the initial lane position is greater than or equal to a preset confidence threshold, based on the initial lane position, performing at least one of the following: Determine road lane-level traffic information; Determine lane-level candidate planning trajectories; Determine the vehicle lane-level control strategy.

21. An electronic device, characterized in that: include: 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 10.

22. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images