Method, device and storage medium for quickly searching for associations of non-equal length line segments

Abstract

This application discloses a method, device, and storage medium for quickly searching and associating line segments of unequal length. The method comprises: obtaining a target line segment and multiple line segments to be associated on the same side; determining a valid associated line segment set based on the target line segment and the multiple line segments to be associated; performing a horizontal distance sorting process on the valid line segment set to obtain a target associated line segment set; and performing a horizontal distance search on the target associated line segment set based on the target line segment to obtain a target association result; wherein the target association result is a set of coordinate points with the smallest horizontal distance to a coordinate point within the longitudinal range of the target line segment. This application enables rapid search of associated coordinate points, while ensuring the accuracy and completeness of the search results while achieving rapid search.

Description

Technical Field

[0001] The present application relates to the field of environmental cognition technology for autonomous driving vehicles, and in particular to a method, device, and storage medium for quickly searching for associations of non-equal-length line segments. Background Art

[0002] Crowdsourced maps rely on multiple acquisitions of lane boundaries, road boundaries, signs, and traffic lights by cameras on mass-produced vehicles. This information is automatically clustered to construct map elements such as lane boundaries, road boundaries, sign locations, and traffic light locations. This information is then integrated with onboard inertial navigation to infer vehicle trajectories and construct lane centerlines. Compared to high-precision maps, this process eliminates the need for manual verification, significantly reducing mapping costs. Furthermore, the maps are highly current, expanding the scope of autonomous driving applications.

[0003] During autonomous driving, it is necessary to select reference lines, avoid obstacles, and access ramps based on the surrounding environment, including the feasible centerline, lane boundary lines, and road boundaries. However, due to light obstruction and actual wear and tear, the perceived lane boundary lines and road boundaries may be missing, resulting in inconsistent lengths and a lack of correlation between lane boundary lines and road boundaries. Furthermore, the lane centerline is generated based on the actual vehicle's driving trajectory, and its length is inconsistent with the length of the lane boundary lines and road boundaries, and there is no correlation. This can lead to a one-to-many or many-to-one relationship in the horizontal and vertical directions.

[0004] Therefore, in the crowdsourcing map construction process in the existing technology, the perception of lane boundaries and road boundaries is incomplete due to the influence of environmental factors, resulting in the problem that the line segments in the crowdsourcing map are inconsistent in length and unrelated to each other. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, and storage medium for quickly searching for associations of non-equal-length line segments, so as to solve the problem in the crowdsourced map construction process in the prior art that, due to the influence of environmental factors, lane boundaries and road boundaries are not fully perceived, resulting in inconsistent line segment lengths and no correlation between them in the crowdsourced map.

[0006] To achieve the above-mentioned objectives, the present application provides, in a first aspect, a method for quickly searching for associations of line segments of unequal lengths, the method comprising:

[0007] Get the target line segment and multiple line segments to be associated on the same side;

[0008] Determine a valid associated line segment set according to the target line segment and multiple line segments to be associated;

[0009] Performing horizontal distance sorting on the valid associated line segment set to obtain the target associated line segment set;

[0010] Based on the target line segment, a horizontal distance search is performed on the target associated line segment set to obtain the target association result;

[0011] The target association result is a set of coordinate points with the smallest horizontal distance from the coordinate points within the vertical range of the target line segment.

[0012] In the embodiment of the present application, obtaining the target line segment and multiple line segments to be associated on the same side includes:

[0013] Acquire an initial target line segment and a plurality of initial line segments to be associated on the same side, wherein the initial target line segment and the plurality of initial line segments to be associated each include a plurality of two-dimensional coordinate data;

[0014] Convert the two-dimensional coordinate data into frenet coordinate data in a preset coordinate system to obtain the target line segment and multiple line segments to be associated;

[0015] The frenet coordinate data includes lateral displacement and longitudinal displacement, and the preset coordinate system is the frenet coordinate system established based on the target line segment.

[0016] In the embodiment of the present application, the valid associated line segment set satisfies formula (1):

[0017] ; (1)

[0018] in, is a set of valid associated line segments, represents the valid associated line segments in the valid associated line segment set, is the line segment association state, Indicates that the line segment is valid. 0 means the line segment is invalid. is the number of line segments to be associated in the valid associated line segment set.

[0019] In the embodiment of the present application, the line segment association state satisfies formula (2):

[0020] ; (2)

[0021] in, is the longitudinal displacement of the starting point of the line segment to be associated, is the longitudinal displacement of the end point of the line segment to be associated, is the lateral displacement of the starting point of the line segment to be associated, is the lateral displacement of the end point of the line segment to be associated, is the longitudinal displacement of the starting point of the target segment, is the longitudinal displacement of the end point of the target segment.

[0022] In the embodiment of the present application, the valid associated line segment set is sorted by horizontal distance to obtain a target associated line segment set including:

[0023] Determine the average lateral distance of each valid associated line segment in the set of valid associated line segments;

[0024] The valid associated line segment set is sorted according to the average horizontal distance to obtain the target associated line segment set.

[0025] In the embodiment of the present application, based on the target line segment, a lateral distance search is performed on the target associated line segment set to obtain a target association result including:

[0026] Searching the target associated line segments in the target associated line segment set in sequence based on the target line segment until all associated points in the longitudinal range of the target line segment are found to obtain a target association result;

[0027] Among them, the target association result satisfies formula (3):

[0028] ; (3)

[0029] in, is the target association result, is the associated coordinate point, It is Secondary associated point coordinate sequence, For the The longitudinal displacement of the starting point in the secondary associated point coordinate sequence, For the The longitudinal displacement of the end point in the secondary associated point coordinate sequence.

[0030] In an embodiment of the present application, the method further includes:

[0031] When the number of searches is greater than the preset number, the target search mode is determined based on the previous search result and the current line segment to be searched;

[0032] The current line segment to be searched is searched through the target search mode to obtain the coordinate sequence of the associated points after the search.

[0033] In the embodiment of the present application, the target search mode satisfies formula (4):

[0034] ; (4)

[0035] in, For target search mode, is the vertical displacement of the starting point in the previous search result, is the longitudinal displacement of the end point in the previous search result, is the longitudinal displacement of the starting point of the current segment to be searched, is the longitudinal displacement of the end point of the current line segment to be searched;

[0036] When the number of searches is greater than a preset number, determining the target search mode based on the previous search result and the current line segment to be searched includes:

[0037] exist =1, the target search mode is determined to be the first search mode;

[0038] exist =2, the target search mode is determined to be the second search mode;

[0039] exist =3, the target search mode is determined to be the third search mode;

[0040] exist =4, the target search mode is determined to be the fourth search mode;

[0041] exist =5, the target search mode is determined to be the fifth search mode;

[0042] exist =6, the target search mode is determined to be the sixth search mode.

[0043] A second aspect of the present application provides a device for quickly searching for associations of line segments of unequal lengths, comprising:

[0044] a memory configured to store instructions; and

[0045] The processor is configured to call instructions from a memory and implement the above-mentioned method for quickly searching for associations of unequal-length line segments when executing the instructions.

[0046] A third aspect of the present application provides a machine-readable storage medium having stored thereon instructions for enabling a machine to execute the above-mentioned method for quickly searching for associations of non-equal-length line segments.

[0047] Through the above technical solution, the target line segment and multiple line segments to be associated on the same side are first obtained; then, a valid associated line segment set is determined based on the target line segment and the multiple line segments to be associated; then, the valid associated line segment set is sorted by horizontal distance to obtain a target associated line segment set; finally, based on the target line segment, a horizontal distance search is performed on the target associated line segment set to obtain a target association result; wherein the target association result is the set of coordinate points with the smallest horizontal distance to the coordinate points within the longitudinal range of the target line segment. This application can realize a fast search for associated coordinate points, and can ensure the accuracy and completeness of the search results while realizing a fast search.

[0048] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0050] Figure 1 A flowchart of a method for quickly searching for associations of unequal-length line segments provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of a valid association line segment provided in a specific embodiment of the present application;

[0052] Figure 3 A schematic diagram illustrating the principle of sorting the left and right lateral distances according to a specific embodiment of the present application;

[0053] Figure 4 A schematic diagram showing the principle of a target search mode after a line segment is added to the left side according to a specific embodiment of the present application;

[0054] Figure 5 A schematic diagram illustrating the principle of search association when the second line segment on the left is newly added according to a specific embodiment of the present application;

[0055] Figure 6 A structural block diagram of a device for quickly searching for associations of unequal-length line segments provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0057] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), such directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0058] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0059] Figure 1 A flowchart of a method for quickly searching for associations of non-equal length line segments provided in an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for quickly searching for associations of unequal length line segments, which may include the following steps:

[0060] Step 101: Obtain a target line segment and multiple line segments to be associated on the same side;

[0061] Step 102: determining a valid associated line segment set based on the target line segment and the plurality of line segments to be associated;

[0062] Step 103: sort the valid associated line segment set by horizontal distance to obtain a target associated line segment set;

[0063] Step 104: Based on the target line segment, perform a horizontal distance search on the target associated line segment set to obtain a target associated result;

[0064] The target association result is a set of coordinate points with the smallest horizontal distance from the coordinate points within the vertical range of the target line segment.

[0065] During the autonomous driving process, when determining the left-right correlation relationship of the centerline, for the lane boundary lines and road boundary lines associated with the centerline, it is hoped to obtain the associated line segment with the smallest lateral distance within the longitudinal length of the centerline; for the left and right center lines associated with the centerline, it is hoped to obtain the centerline with the smallest lateral distance within the range of the vehicle's position. Since the search for the centerline near the centerline, the lane boundary lines near the centerline, and the road boundary lines near the centerline are essentially aimed at the rapid search problem when there are non-equal length line segments in the horizontal and vertical directions. In this regard, the present application proposes a method for rapid search of non-equal length line segments to achieve rapid search of the centerline near the centerline, the lane boundary lines near the centerline, and the road boundary lines near the centerline.

[0066] In the embodiments of the present application, the target line segment refers to the center line whose left-right association relationship needs to be determined through search, and the multiple line segments to be associated on the same side refer to the line segments around the center line to be associated. In one example, the same side can be the left side or the right side of the target line segment. Since the association relationship between the left and right sides of the target line segment ultimately needs to be determined, the line segments to be associated on both sides of the target line segment can be searched separately to determine the left-right association relationship of the target line segment.

[0067] In an embodiment of the present application, first, the target line segment collected in the crowdsourcing map and multiple line segments to be associated on the same side are obtained. Then, a valid associated line segment set is determined based on the target line segment and the multiple line segments to be associated. In one example, in order to avoid incorrect matching of the upper and lower layers at the overpass in the two-dimensional view, the line segments to be associated that intersect with the target line segment also need to be deleted; in addition, the line segments to be associated that have no association relationship with the target line segment within the longitudinal range also need to be deleted. After eliminating the invalid line segments that need to be deleted, the valid associated line segment set is obtained. In this way, by preliminarily screening the valid associated line segments within the longitudinal range of the target line segment and superimposing the lateral distances of the different scenes, a basis can be provided for quickly and accurately constructing a set of associated point coordinates with the minimum lateral distance within the longitudinal distance range.

[0068] In an embodiment of the present application, after obtaining a valid associated line segment set, a lateral distance sorting process can be performed based on the average lateral distance of each valid associated line segment in the valid associated line segment set to obtain a target associated line segment set. The elements in the target associated line segment set are sorted from small to large according to the lateral distance. After obtaining the target associated line segment set, a lateral distance search is performed on the target associated line segment set according to the size of the average lateral distance to obtain a target association result. Among them, the target association result is a set of coordinate points with the smallest lateral distance to the coordinate points within the longitudinal range of the target line segment. In one example, the left and right association results of the target line segment are a set of target association results obtained by searching on the left and a set of target association results obtained by searching on the right.

[0069] Through the above technical solution, the target line segment and multiple line segments to be associated on the same side are first obtained; then, a valid associated line segment set is determined based on the target line segment and the multiple line segments to be associated; then, the valid associated line segment set is sorted by horizontal distance to obtain a target associated line segment set; finally, based on the target line segment, a horizontal distance search is performed on the target associated line segment set to obtain a target association result; wherein the target association result is the set of coordinate points with the smallest horizontal distance to the coordinate points within the longitudinal range of the target line segment. This application can realize a fast search for associated coordinate points, and can ensure the accuracy and completeness of the search results while realizing a fast search.

[0070] In the embodiment of the present application, step 101 of obtaining the target line segment and multiple line segments to be associated on the same side may include:

[0071] Acquire an initial target line segment and a plurality of initial line segments to be associated on the same side, wherein the initial target line segment and the plurality of initial line segments to be associated each include a plurality of two-dimensional coordinate data;

[0072] Convert the two-dimensional coordinate data into frenet coordinate data in a preset coordinate system to obtain the target line segment and multiple line segments to be associated;

[0073] The frenet coordinate data includes lateral displacement and longitudinal displacement, and the preset coordinate system is the frenet coordinate system established based on the target line segment.

[0074] In an embodiment of the present application, the initial target line segment and the initial line segment to be associated collected in the crowdsourced map can be obtained. At this time, the data in the initial target line segment and the initial line segment to be associated are all two-dimensional coordinate data. For the convenience of calculation, the two-dimensional coordinate data can be converted into frenet coordinates in a preset coordinate system through a coordinate conversion function to obtain the target line segment and multiple line segments to be associated. At this time, the data in the target line segment and the multiple line segments to be associated are all frenet coordinate data. Among them, the preset coordinate system is a frenet coordinate system established based on the target line segment itself. In one example, the coordinate conversion function can satisfy formula (1):

[0075] ; (1)

[0076] in, is the coordinate transformation function, is the two-dimensional coordinate to be converted, is the transformed frenet coordinate, represents the longitudinal displacement, Indicates lateral displacement.

[0077] Figure 2 This is a schematic diagram of a valid associated line segment provided in a specific embodiment of the present application. Figure 2 As shown, in the embodiment of the present application, the valid associated line segment set can satisfy formula (2):

[0078] ; (2)

[0079] in, is a set of valid associated line segments, represents the valid associated line segments in the valid associated line segment set, is the line segment association state, Indicates that the line segment is valid. 0 means the line segment is invalid. is the number of line segments to be associated in the valid associated line segment set.

[0080] In the embodiment of the present application, the line segment association state may satisfy formula (3):

[0081] ; (3)

[0082] in, is the longitudinal displacement of the starting point of the line segment to be associated, is the longitudinal displacement of the end point of the line segment to be associated, is the lateral displacement of the starting point of the line segment to be associated, is the lateral displacement of the end point of the line segment to be associated, is the longitudinal displacement of the starting point of the target segment, is the longitudinal displacement of the end point of the target segment.

[0083] In the embodiment of the present application, step 102 of determining a valid associated line segment set based on the target line segment and the plurality of line segments to be associated may include:

[0084] Determine whether each line segment to be associated meets the set conditions;

[0085] Determine the to-be-associated line segments that meet the set conditions as valid associated line segments to obtain a valid associated line segment set;

[0086] The setting conditions are as follows: the first longitudinal displacement is less than the first set longitudinal displacement, the second longitudinal displacement is greater than the second set longitudinal displacement, and the product of the first lateral displacement and the second lateral displacement is greater than or equal to zero;

[0087] The first set lateral displacement and the second set lateral displacement are the lateral displacement of the starting point and the longitudinal displacement of the end point of the target segment, respectively. The first lateral displacement, the first longitudinal displacement, the second lateral displacement, and the second longitudinal displacement are the lateral displacement of the starting point, the longitudinal displacement of the starting point, the lateral displacement of the end point, and the longitudinal displacement of the end point, respectively, for each direction to be associated. In this way, by initially screening valid associated line segments within the longitudinal range of the target line segment and superimposing the lateral distances of each scenario, a foundation is laid for quickly and accurately constructing a set of associated point coordinates with the minimum lateral distance within the longitudinal range.

[0088] In the embodiment of the present application, step 103, performing horizontal distance sorting on the valid associated line segment set to obtain the target associated line segment set, may include:

[0089] Determine the average lateral distance of each valid associated line segment in the set of valid associated line segments;

[0090] The valid associated line segment set is sorted according to the average horizontal distance to obtain the target associated line segment set.

[0091] In an embodiment of the present application, the average horizontal distance of each valid associated line segment in the valid associated line segment set can be determined first, and then the valid associated line segments in the valid associated line segment set can be sorted from small to large based on the average horizontal distance to obtain the target associated line segment set.

[0092] In one example, the target associated line segment set may include a left horizontal associated line segment set and a right horizontal associated line segment set. That is, for the valid associated line segment set on the left and the valid associated line segment set on the right of the target line segment, the above method can be used to determine the corresponding target line segment set.

[0093] In the embodiment of the present application, in the Frenet coordinate system established by the target segment itself, taking the left side of the target segment as the positive direction of the lateral displacement and the right side of the target segment as the negative direction of the lateral displacement as an example, the left associated segment set can satisfy formula (4):

[0094] ; (4)

[0095] Transforming the right associated segment set can satisfy formula (5):

[0096] ; (5)

[0097] in, To convert the left associated segment set, To convert the right associated segment set, is the line segment to be associated, is the average horizontal distance of the line segments to be associated, is the sorting function, They are the sorted left and right side line segment numbers respectively. Figure 3 This is a schematic diagram of the principle of sorting the left and right side lateral distances provided in a specific embodiment of the present application. Figure 3 As shown, the smaller the subscript of the line segment number, the smaller the horizontal distance. There are a total of There are a total of associated line segments on the right side. The specific number of line segments is related to the actual relationship between the line segments.

[0098] In one example, the average lateral distance of the line segments to be associated may satisfy formula (6):

[0099] ; (6)

[0100] in, is the average horizontal distance of the line segments to be associated, is the lateral displacement of the starting point of the line segment to be associated, is the lateral displacement of a coordinate point in the line segment to be associated, is the lateral displacement of the end point of the line segment to be associated, Calculate the value for the average horizontal distance of the selected points. Select the average interval according to the number of coordinate points of the line segment points determine the average lateral distance for, e.g., K The value can be 5, in which case, in addition to the first and last points, three points with equal spacing in the middle must also be selected.

[0101] In the embodiment of the present application, based on the target line segment, a lateral distance search is performed on the target associated line segment set to obtain a target association result including:

[0102] Searching the target associated line segments in the target associated line segment set in sequence based on the target line segment until all associated points in the longitudinal range of the target line segment are found to obtain a target association result;

[0103] Among them, the target association result satisfies formula (7):

[0104] ; (7)

[0105] in, is the target association result, is the associated coordinate point, It is Secondary associated point coordinate sequence, For the The longitudinal displacement of the starting point in the secondary associated point coordinate sequence, For the The longitudinal displacement of the end point in the secondary associated point coordinate sequence.

[0106] In the embodiment of the present application, after obtaining the target associated line segment set, the search and association can be performed based on the average horizontal distance of each line segment to be associated in the set. In one example, the calculation method for performing the association search on the left and right sides of the target line segment is the same, and the following example on the left is used to expand the description.

[0107] Specifically, first determine the relationship between the longitudinal displacement of the starting point and the longitudinal displacement of the end point of a line segment to be associated with the smallest average lateral distance in the target associated line segment set and the lateral displacement of the starting point and the lateral displacement of the end point of the target line segment. The lateral displacement is the S coordinate in the Frenet coordinate system. If the line segment to be associated contains the target line segment within the longitudinal range, then each point in the target line segment can find a corresponding associated point in the line segment to be associated. At this time, the search can be exited and the target association result can be determined. Otherwise, continue the search, and based on the previous search results, compare the relationship between the newly added line segment to be associated and the already associated associated point coordinate sequence, and add new associated points until all the coordinate points in the longitudinal range of the target line segment are found, or the search for all the line segments to be associated in the target associated line segment set is completed.

[0108] In the embodiment of the present application, it can be seen from formula (7) that if the starting point longitudinal displacement and the end point longitudinal displacement in the associated point coordinate sequence contain the starting point longitudinal displacement and the end point longitudinal displacement of the target segment, the search is exited; otherwise, the next search is entered until the entire search is completed or the target association result is obtained.

[0109] In an embodiment of the present application, the method may further include:

[0110] When the number of searches is greater than the preset number, the target search mode is determined based on the previous search result and the current line segment to be searched;

[0111] The current line segment to be searched is searched through the target search mode to obtain the coordinate sequence of the associated points after the search.

[0112] In this embodiment of the present application, the preset number of times is 1. That is, after searching the first line segment in the target-associated line segment set, if no target-associated result is obtained, the target search mode is determined based on the previous search result and the current line segment to be searched. The current line segment to be searched is then searched using the target search mode to obtain a sequence of associated point coordinates after the search. The current line segment to be searched is the newly added line segment.

[0113] In the embodiment of the present application, the current search is i search, the previous search is i- 1 search, the coordinate sequence of the associated points after the current search is Secondary associated point coordinate sequence , the previous search result is . The coordinate sequence of the secondary associated points can satisfy formula (8):

[0114] ; (8)

[0115] in, is the distance search function, which is based on and When searching for the first time, the historical associated point coordinate sequence can be regarded as 0 and relevant judgments can be made. The current line segment to be searched.

[0116] In the embodiment of the present application, the target search mode satisfies formula (9):

[0117] ; (9)

[0118] in, For target search mode, is the vertical displacement of the starting point in the previous search result, is the longitudinal displacement of the end point in the previous search result, is the longitudinal displacement of the starting point of the current segment to be searched, is the longitudinal displacement of the end point of the current line segment to be searched;

[0119] When the number of searches is greater than a preset number, determining the target search mode based on the previous search result and the current line segment to be searched includes:

[0120] exist =1, the target search mode is determined to be the first search mode;

[0121] exist =2, the target search mode is determined to be the second search mode;

[0122] exist =3, the target search mode is determined to be the third search mode;

[0123] exist =4, the target search mode is determined to be the fourth search mode;

[0124] exist =5, the target search mode is determined to be the fifth search mode;

[0125] exist =6, the target search mode is determined to be the sixth search mode.

[0126] Figure 4 This is a schematic diagram of the principle of the target search mode after the left side of the added line segment provided in a specific embodiment of the present application. Figure 4 As shown, in the embodiment of the present application, the first search mode corresponds to Figure 4 (1) When the target search mode is converted to the first search mode, the coordinate sequence of the associated points after the search satisfies formula (10):

[0127] ; (10)

[0128] in, is the coordinate sequence of the associated points after the search, For the previous search result, The starting point coordinates in the newly added associated point coordinate sequence, The coordinates of the end point in the newly added associated point coordinate sequence (the same below).

[0129] The starting point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (11):

[0130] ; (11)

[0131] The end point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (12):

[0132] ; (12)

[0133] in, is the longitudinal displacement of the end point in the previous search result, Indicates the corresponding longitudinal displacement, is the longitudinal displacement of the end point of the current segment to be searched, The longitudinal displacement of the endpoint of the target segment to be transformed (the same below).

[0134] like Figure 4 As shown, in the embodiment of the present application, the second search mode corresponds to Figure 4 (2) When the target search mode is the second search mode, the coordinate sequence of the associated points after the search satisfies formula (13):

[0135] ; (13)

[0136] The starting point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (14):

[0137] ; (14)

[0138] The end point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (15):

[0139] ; (15)

[0140] in, is the vertical displacement of the starting point in the previous search result, is the longitudinal displacement of the starting point of the current segment to be searched, It is the longitudinal displacement of the starting point of the target segment (the same below).

[0141] like Figure 4 As shown, in the embodiment of the present application, the third search mode corresponds to Figure 4 (3) When the target search mode is converted to the third search mode, the coordinate sequence of the associated points after the conversion search satisfies formula (16):

[0142] ; (16)

[0143] like Figure 4 As shown, in the embodiment of the present application, the fourth search mode corresponds to Figure 4 (4) When the target search mode is converted to the fourth search mode, the coordinate sequence of the associated points after the search satisfies formula (17):

[0144] ; (17)

[0145] in, To add the starting point coordinates in the first segment of the associated point coordinate sequence, To add the end point coordinates in the first segment of the associated point coordinate sequence, To add the starting point coordinates in the second segment of the associated point coordinate sequence, The end point coordinates of the newly added second segment of the associated point coordinate sequence (the same below).

[0146] The starting point coordinates in the newly added first segment of the associated point coordinate sequence are converted to satisfy formula (18):

[0147] ; (18)

[0148] The end point coordinates in the newly added first segment of the associated point coordinate sequence are converted to satisfy formula (19):

[0149] ; (19)

[0150] The starting point coordinates in the newly added second segment of the associated point coordinate sequence are converted to satisfy formula (20):

[0151] ; (20)

[0152] The end point coordinates in the newly added second segment of the associated point coordinate sequence satisfy formula (21):

[0153] ;(twenty one)

[0154] like Figure 4 As shown, in the embodiment of the present application, the fifth search mode corresponds to Figure 4 (5), when the target search mode is converted to the fifth search mode, the coordinate sequence of the associated points after the search satisfies formula (22):

[0155] ;(twenty two)

[0156] The starting point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (23):

[0157] ;(twenty three)

[0158] The end point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (24):

[0159] ;(twenty four)

[0160] like Figure 4As shown, in the embodiment of the present application, the sixth search mode corresponds to Figure 4 (6), when the target search mode is converted to the sixth search mode, the coordinate sequence of the associated points after the search satisfies formula (25):

[0161] ; (25)

[0162] The starting point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (26):

[0163] ; (26)

[0164] The end point coordinates in the newly added associated point coordinate sequence are converted to satisfy formula (27):

[0165] ; (27)

[0166] Figure 5 This is a schematic diagram of the search association principle when the second line segment on the left is newly added in a specific embodiment of the present application. Figure 5 As shown, taking the search for the second line segment on the left as an example, the corresponding target search mode is the third search mode. Therefore, the coordinate sequence of the associated points after the search can be calculated according to formula (22), formula (23) and formula (24).

[0167] In this way, by sorting and searching by lateral distance, the impact of coordinate point errors and calculation errors on the association results can be reduced. By initially screening valid associated line segments within the longitudinal distance and superimposing the lateral distances of each scene, the associated coordinate point with the minimum lateral distance within the longitudinal distance range can be quickly and accurately constructed, achieving the goal of constructing the vehicle's surrounding environment vector. The search association method proposed in this invention is universal, rapid, complete, and robust.

[0168] Figure 6 This is a structural block diagram of a device for quickly searching for associations of non-equal length line segments provided in an embodiment of the present application. Figure 6 As shown, an embodiment of the present application provides a device for quickly searching for associations of unequal length line segments, which may include:

[0169] Memory 610 configured to store instructions; and

[0170] The processor 620 is configured to call instructions from the memory 610 and implement the above-mentioned method for quickly searching for associations of unequal-length line segments when executing the instructions.

[0171] Specifically, in the embodiment of the present application, the processor 620 may be configured to:

[0172] Get the target line segment and multiple line segments to be associated on the same side;

[0173] Determine a valid associated line segment set according to the target line segment and multiple line segments to be associated;

[0174] Performing horizontal distance sorting on the valid associated line segment set to obtain the target associated line segment set;

[0175] Based on the target line segment, a horizontal distance search is performed on the target associated line segment set to obtain the target association result;

[0176] The target association result is a set of coordinate points with the smallest horizontal distance from the coordinate points within the vertical range of the target line segment.

[0177] Furthermore, the processor 620 may be further configured to:

[0178] Acquire an initial target line segment and a plurality of initial line segments to be associated on the same side, wherein the initial target line segment and the plurality of initial line segments to be associated each include a plurality of two-dimensional coordinate data;

[0179] Convert the two-dimensional coordinate data into frenet coordinate data in a preset coordinate system to obtain the target line segment and multiple line segments to be associated;

[0180] The frenet coordinate data includes lateral displacement and longitudinal displacement, and the preset coordinate system is the frenet coordinate system established based on the target line segment.

[0181] In the embodiment of the present application, the set of valid associated line segments satisfies formula (2):

[0182] ; (2)

[0183] in, is a set of valid associated line segments, represents the valid associated line segments in the valid associated line segment set, is the line segment association state, Indicates that the line segment is valid. 0 means the line segment is invalid. is the number of line segments to be associated in the valid associated line segment set.

[0184] In the embodiment of the present application, the line segment association state satisfies formula (3):

[0185] ; (3)

[0186] in, is the longitudinal displacement of the starting point of the line segment to be associated, is the longitudinal displacement of the end point of the line segment to be associated, is the lateral displacement of the starting point of the line segment to be associated, is the lateral displacement of the end point of the line segment to be associated, is the longitudinal displacement of the starting point of the target segment, is the longitudinal displacement of the end point of the target segment.

[0187] Furthermore, the processor 620 may be further configured to:

[0188] Determine the average lateral distance of each valid associated line segment in the set of valid associated line segments;

[0189] The valid associated line segment set is sorted according to the average horizontal distance to obtain the target associated line segment set.

[0190] Furthermore, the processor 620 may be further configured to:

[0191] Searching the target associated line segments in the target associated line segment set in sequence based on the target line segment until all associated points in the longitudinal range of the target line segment are found to obtain a target association result;

[0192] Among them, the target association result satisfies formula (7):

[0193] ; (7)

[0194] in, is the target association result, is the associated coordinate point, It is Secondary associated point coordinate sequence, For the The longitudinal displacement of the starting point in the secondary associated point coordinate sequence, For the The longitudinal displacement of the end point in the secondary associated point coordinate sequence.

[0195] Furthermore, the processor 620 may be further configured to:

[0196] When the number of searches is greater than the preset number, the target search mode is determined based on the previous search result and the current line segment to be searched;

[0197] The current line segment to be searched is searched through the target search mode to obtain the coordinate sequence of the associated points after the search.

[0198] In the embodiment of the present application, the target search mode satisfies formula (9):

[0199] ; (9)

[0200] in, For target search mode, is the vertical displacement of the starting point in the previous search result, is the longitudinal displacement of the end point in the previous search result, is the longitudinal displacement of the starting point of the current segment to be searched, is the longitudinal displacement of the end point of the current line segment to be searched;

[0201] Furthermore, the processor 620 may be further configured to:

[0202] exist =1, the target search mode is determined to be the first search mode;

[0203] exist =2, the target search mode is determined to be the second search mode;

[0204] exist =3, the target search mode is determined to be the third search mode;

[0205] exist =4, the target search mode is determined to be the fourth search mode;

[0206] exist =5, the target search mode is determined to be the fifth search mode;

[0207] exist =6, the target search mode is determined to be the sixth search mode.

[0208] Through the above technical solution, the target line segment and multiple line segments to be associated on the same side are first obtained; then, a valid associated line segment set is determined based on the target line segment and the multiple line segments to be associated; then, the valid associated line segment set is sorted by horizontal distance to obtain a target associated line segment set; finally, based on the target line segment, a horizontal distance search is performed on the target associated line segment set to obtain a target association result; wherein the target association result is the set of coordinate points with the smallest horizontal distance to the coordinate points within the longitudinal range of the target line segment. This application can realize a fast search for associated coordinate points, and can ensure the accuracy and completeness of the search results while realizing a fast search.

[0209] An embodiment of the present application further provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for quickly searching for associations of non-equal-length line segments.

[0210] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0211] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0212] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0213] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0214] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0215] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0216] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitor4 media), such as modulated data signals and carrier waves.

[0217] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0218] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for quickly searching for associations of segments of unequal lengths, characterized in that: include: Obtain the target line segment collected from the crowdsourced map and multiple line segments to be associated on the same side; Determining a valid associated line segment set based on the target line segment and the plurality of line segments to be associated, the valid associated line segment set including the plurality of valid associated line segments, the valid associated line segments being line segments to be associated that intersect with the target line segment in a longitudinal range and do not intersect with the target line segment in a transverse range among the plurality of line segments to be associated; performing horizontal distance sorting processing on the valid associated line segment set to obtain a target associated line segment set; Based on the target line segment, performing a lateral distance search on the target associated line segment set to obtain a target association result; The target association result is a set of coordinate points having the smallest horizontal distance from the coordinate points within the longitudinal range of the target line segment.

2. The method according to claim 1, characterized in that The acquiring of the target line segment and the plurality of line segments to be associated on the same side includes: Acquire an initial target line segment and a plurality of initial line segments to be associated on the same side, wherein the initial target line segment and the plurality of initial line segments to be associated each include a plurality of two-dimensional coordinate data; Converting the two-dimensional coordinate data into frenet coordinate data in a preset coordinate system to obtain the target line segment and the plurality of line segments to be associated; The frenet coordinate data includes lateral displacement and longitudinal displacement, and the preset coordinate system is a frenet coordinate system established based on the target line segment.

3. The method according to claim 1, characterized in that The set of valid associated line segments satisfies formula (1): ； （1） in, is the set of valid associated line segments, represents a valid associated line segment in the valid associated line segment set, is the line segment association state, Indicates that the line segment is valid. 0 means the line segment is invalid. is the number of line segments to be associated in the valid associated line segment set.

4. The method according to claim 3, characterized in that The segment association state satisfies formula (2): ；（2） in, is the longitudinal displacement of the starting point of the line segment to be associated, is the longitudinal displacement of the end point of the line segment to be associated, is the lateral displacement of the starting point of the line segment to be associated, is the lateral displacement of the end point of the line segment to be associated, is the longitudinal displacement of the starting point of the target segment, is the longitudinal displacement of the endpoint of the target segment.

5. The method according to claim 1, characterized in that The performing horizontal distance sorting on the valid associated line segment set to obtain a target associated line segment set includes: Determining an average lateral distance of each valid associated line segment in the set of valid associated line segments; The valid associated line segment set is sorted according to the average horizontal distance to obtain the target associated line segment set.

6. The method according to claim 2, characterized in that The step of performing a lateral distance search on the target-associated line segment set based on the target line segment to obtain a target association result includes: Searching the line segments to be associated in the target associated line segment set in sequence based on the target line segment until all associated points within the longitudinal range of the target line segment are searched, so as to obtain the target association result; The target association result satisfies formula (3): ；（3） in, is the target association result, is the associated coordinate point, It is Secondary associated point coordinate sequence, For the The longitudinal displacement of the starting point in the secondary associated point coordinate sequence, For the The longitudinal displacement of the end point in the secondary associated point coordinate sequence.

7. The method according to claim 6, characterized in that The method further comprises: When the number of searches is greater than the preset number, the target search mode is determined based on the previous search result and the current line segment to be searched; The current line segment to be searched is searched using the target search mode to obtain a coordinate sequence of associated points after the search.

8. The method according to claim 7, characterized in that The target search mode satisfies formula (4): ；（4） in, is the target search mode, is the vertical displacement of the starting point in the previous search result, is the longitudinal displacement of the endpoint in the previous search result, is the longitudinal displacement of the starting point of the current line segment to be searched, is the longitudinal displacement of the end point of the current line segment to be searched; When the number of searches is greater than a preset number, determining the target search mode according to the previous search result and the current line segment to be searched includes: exist =1, the target search mode is determined to be the first search mode; exist =2, the target search mode is determined to be the second search mode; exist =3, it is determined that the target search mode is the third search mode; exist =4, the target search mode is determined to be the fourth search mode; exist =5, the target search mode is determined to be the fifth search mode; exist =6, the target search mode is determined to be the sixth search mode.

9. A device for quickly searching for associations of line segments of unequal lengths, characterized in that: include: a memory configured to store instructions; as well as The processor is configured to call the instructions from the memory and implement the method for quickly searching for associations of unequal-length line segments according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for enabling a machine to execute the method for quickly searching for associations of unequal-length line segments according to any one of claims 1 to 8.

Images