Roadside noise detection method, device and equipment and storage medium

Abstract

The present application relates to the field of automatic driving, and particularly relates to a road edge line noise detection method, device, equipment and storage medium. The method comprises the following steps: acquiring a vehicle trajectory line set and a road edge line set collected in advance, wherein the road edge line set comprises a first road edge line and a second road edge line, and the second road edge line is a road edge line in the road edge line set except the first road edge line; generating a detection range corresponding to a road edge point on the first road edge line according to the road edge point and a nearest vehicle trajectory point in the vehicle trajectory line set; detecting whether the second road edge line that meets a preset detection condition exists in the detection range; if yes, it is determined that noise exists in the detection range. The present application determines the range of noise by using the geometric relationship between the vehicle trajectory line and the road edge line, more conveniently optimizes the noise data in the electronic map, and perfects the map optimization process.

Description

Technical Field

[0001] This invention relates to the field of electronic maps, and more particularly to a method, apparatus, device, and storage medium for detecting roadside noise. Background Technology

[0002] Currently, in the field of electronic mapping, data is collected from vehicles and analyzed to obtain a set containing several roadside lines and vehicle trajectory lines. In practical applications, this set often contains noise, which affects the formation and accuracy of the electronic map. Noise removal is necessary before the data can be used to generate a usable electronic map. However, current roadside noise removal processes often require significant computing power and considerable time to identify and denoise the collected data. Summary of the Invention

[0003] The main objective of this invention is to solve the technical problem of low identification efficiency in existing roadside noise detection methods.

[0004] The first aspect of the present invention provides a method for detecting roadside noise, the method comprising: acquiring a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, the second roadside line being the roadside lines in the set other than the first roadside line; generating a detection range corresponding to a roadside point based on a roadside point on the first roadside line and the nearest vehicle trajectory point in the set of vehicle trajectory lines; detecting whether a second roadside line satisfying a preset detection condition exists within the detection range; and if so, determining that noise exists within the detection range.

[0005] Optionally, in a first implementation of the first aspect of the present invention, generating the detection range corresponding to the curb point based on the curb point on the first roadside line and the nearest vehicle trajectory point in the vehicle trajectory line set includes: selecting a curb point in the first roadside line, and connecting the curb point to the vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set to obtain the connection distance between the curb point and each vehicle trajectory point; identifying the vehicle trajectory point closest to the curb point based on the connection distance to obtain the nearest vehicle trajectory point of the curb point; connecting the curb point to the corresponding nearest vehicle trajectory point to obtain a first line segment; generating a circular region with the first line segment as the radius and the curb point as the center, and using the circular region as the detection range of the curb point.

[0006] Optionally, in a second implementation of the first aspect of the present invention, detecting whether there is a second roadside line satisfying a preset detection condition within the detection range includes: determining whether the detection range intersects with the second roadside line; if so, extending the first line segment in the reverse direction to a preset length based on the roadside point in the first line segment to obtain a second line segment; and determining whether there is a second roadside line satisfying the preset detection condition based on the intersection state of the second line segment with any vehicle trajectory line or roadside line.

[0007] Optionally, in a third implementation of the first aspect of the present invention, determining whether the detection range intersects with the second path includes: determining whether there are path edges of the second path in the detection range, wherein the second path is composed of a plurality of second path edges; if so, determining whether the second path to which the second path edge belongs intersects with the first line segment to obtain a determination result; and determining whether the detection range intersects with the second path based on the determination result.

[0008] Optionally, in a fourth implementation of the first aspect of the present invention, after determining that noise exists within the detection range, the method further includes: comparing the lengths of a first roadside line and a second roadside line to obtain a comparison result; identifying the shorter roadside line among the first roadside line and the second roadside line as noise based on the comparison result; and removing the roadside lines identified as noise from the roadside line set to achieve noise removal of the roadside line set.

[0009] Optionally, in a fifth implementation of the first aspect of the present invention, the vehicle trajectory line and the roadside line are vectors; after acquiring the pre-collected set of vehicle trajectory lines and the set of roadside lines, the method further includes: constructing a subordinate relationship between the set of vehicle trajectory lines and the set of roadside lines; constructing a plurality of perpendicular lines for the vehicle trajectory lines in the set of vehicle trajectory lines; determining whether the perpendicular lines intersect with more than two roadside lines that have a subordinate relationship; if so, determining that there is noise in the roadside lines of the subordinate relationship.

[0010] Optionally, in a sixth implementation of the first aspect of the present invention, the step of constructing a subordinate relationship between the vehicle trajectory line set and the roadside line set includes: selecting multiple vehicle trajectory lines in the vehicle trajectory line set that are closest to multiple roadside points in the roadside line to obtain a vehicle trajectory line set; and selecting the vehicle trajectory line in the vehicle trajectory line set that appears most frequently to construct a subordinate relationship with the roadside line.

[0011] A second aspect of the present invention provides a roadside noise detection device, comprising: a map acquisition module for acquiring a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, the second roadside line being the roadside lines in the set excluding the first roadside line; a detection range generation module for generating a detection range corresponding to a roadside point based on a roadside point on the first roadside line and the nearest vehicle trajectory point in the set of vehicle trajectory lines; a noise detection module for detecting whether a second roadside line satisfying a preset detection condition exists within the detection range; and a noise determination module for determining that noise exists within the detection range if such a roadside line exists.

[0012] Optionally, in a first implementation of the second aspect of the present invention, the detection range generation module is specifically used for: selecting a roadside point in a first roadside line, and connecting the roadside point with vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set to obtain the connection distance between the roadside point and each vehicle trajectory point; identifying the vehicle trajectory point closest to the roadside point based on the connection distance to obtain the nearest vehicle trajectory point of the roadside point; connecting the roadside point with the corresponding nearest vehicle trajectory point to obtain a first line segment; generating a circular area with the first line segment as the radius and the roadside point as the center, and using the circular area as the detection range of the roadside point.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the noise detection module is specifically used for: an intersection judgment unit, which determines whether the detection range intersects with the second roadside line; a reverse extension unit, which, if so, extends the first line segment in reverse to a preset length based on the roadside point in the first line segment to obtain the second line segment; and a detection condition determination unit, which determines whether there is a second roadside line that meets the preset detection conditions based on the intersection state of the second line segment with any vehicle trajectory line or roadside line.

[0014] Optionally, in a third implementation of the second aspect of the present invention, the intersection judgment unit is specifically used to: determine whether there is a road edge point of a second road edge in the detection range, wherein the second road edge is composed of a plurality of second road edge points; if there is, determine whether the second road edge to which the second road edge point belongs intersects with the first line segment, and obtain a judgment result; and determine whether the detection range intersects with the second road edge based on the judgment result.

[0015] Optionally, in a fourth implementation of the second aspect of the present invention, the roadside noise detection device further includes a traversal noise reduction module, which is specifically used to: compare the lengths of a first roadside line and a second roadside line to obtain a comparison result; identify the shorter roadside line between the first roadside line and the second roadside line as noise based on the comparison result; and remove the roadside lines identified as noise from the roadside line set to achieve noise reduction of the roadside line set.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the roadside noise detection device further includes a second noise determination module, which is specifically used for: a subordinate relationship construction unit for constructing a subordinate relationship between the vehicle trajectory line set and the roadside line set; a perpendicular line construction unit for constructing a plurality of perpendicular lines for the vehicle trajectory lines in the vehicle trajectory line set; an intersection judgment unit for determining whether the perpendicular line intersects with more than two roadside lines that have a subordinate relationship; and a noise determination unit, if so, determining that there is noise on the roadside line in the subordinate relationship.

[0017] Optionally, in a sixth implementation of the second aspect of the present invention, the subordinate relationship construction unit is specifically used to: select multiple vehicle trajectory lines in the vehicle trajectory line set that are closest to multiple roadside points in the roadside line to obtain a vehicle trajectory line set; and select the vehicle trajectory line in the vehicle trajectory line set that appears most frequently to construct a subordinate relationship with the roadside line.

[0018] A third aspect of the present invention provides a roadside noise detection device, comprising: a memory and at least one processor, wherein the memory stores a request, and the memory and the at least one processor are interconnected via a line; the at least one processor invokes the request in the memory to cause the roadside noise detection device to perform the steps of the roadside noise detection method described above.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium storing a request that, when executed on a computer, causes the computer to perform the steps of the roadside noise detection method described above.

[0020] In the technical solution of this invention, a pre-collected set of vehicle trajectory lines and a set of roadside lines are acquired. The set of roadside lines includes a first roadside line and a second roadside line, where the second roadside line is any roadside line in the set other than the first roadside line. A detection range corresponding to each roadside point is generated based on the nearest vehicle trajectory point in the set of vehicle trajectory lines and the roadside point on the first roadside line. The existence of a second roadside line within the detection range that meets preset detection conditions is detected. If so, noise is determined to exist within the detection range. This application uses the geometric relationship between vehicle trajectory lines and roadside lines to determine the location of noise, thus more conveniently optimizing noise data in electronic maps and improving the map optimization process. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the first embodiment of the roadside noise detection method in this invention;

[0022] Figure 2 This is a schematic diagram of a second embodiment of the roadside noise detection method in this invention;

[0023] Figure 3 This is a schematic diagram of a third embodiment of the roadside noise detection method in this invention;

[0024] Figure 4 This is a schematic diagram of one embodiment of the roadside noise detection device according to the present invention;

[0025] Figure 5 This is a schematic diagram of another embodiment of the roadside noise detection device in this invention;

[0026] Figure 6 This is a schematic diagram of one embodiment of the roadside noise detection device in this invention. Detailed Implementation

[0027] In the technical solution of this invention, a pre-collected set of vehicle trajectory lines and a set of roadside lines are acquired. The set of roadside lines includes a first roadside line and a second roadside line, where the second roadside line is any roadside line in the set other than the first roadside line. A detection range corresponding to each roadside point is generated based on the nearest vehicle trajectory point in the set of vehicle trajectory lines and the roadside point on the first roadside line. The existence of a second roadside line within the detection range that meets preset detection conditions is detected. If so, noise is determined to exist within the detection range. This application uses the geometric relationship between vehicle trajectory lines and roadside lines to determine the location of noise, thus more conveniently optimizing noise data in electronic maps and improving the map optimization process.

[0028] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar elements and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of the roadside noise detection method in this invention includes:

[0030] 101. Obtain the pre-collected vehicle trajectory line set and roadside line set;

[0031] In this embodiment, the vehicle uses sensors such as LiDAR and cameras, combined with perception and positioning outputs, to collect several sets of vehicle trajectory lines and roadside lines. However, in real-world applications, "quasi-roadsides" or "false roadsides" with highly similar shapes to the roadside often appear nearby. For example, small fences around flower beds outside sidewalks or illegally parked vehicles on the roadside are often mistaken for roadside edges. For autonomous driving, the focus of semantic map roadside data is mainly on the sides of drivable roads. These false roadsides are useless redundant data, increasing computational load and complexity, and even affecting the safety of autonomous driving. Therefore, after acquiring the collected vehicle trajectory line sets and roadside line sets, a noise reduction algorithm is needed to detect and eliminate this noise.

[0032] 102. Generate the detection range corresponding to the curb point based on the nearest vehicle trajectory point in the set of curb points and vehicle trajectory lines along the first road;

[0033] In this embodiment, an arbitrary roadside line is selected as the first roadside line, and the roadside points on the first roadside line are connected to the nearest vehicle trajectory point in the vehicle trajectory line set to obtain the detection range corresponding to the roadside point.

[0034] Specifically, there are several roadside points along the first road, and the detection range of any roadside point is from the roadside point to the nearest vehicle trajectory point.

[0035] 103. Check whether there is a second path along the detection range that meets the preset detection conditions;

[0036] In this embodiment, by determining whether there is a second road edge that meets the preset detection conditions within the detection range, it is determined whether the first or second road edge corresponding to the road edge point is noise.

[0037] 104. If so, then noise is confirmed to exist within the detection range.

[0038] In this embodiment, determining that noise exists within the detection range means determining that one of the first or second paths is noise.

[0039] In this embodiment, a pre-collected set of vehicle trajectory lines and a set of roadside lines are acquired. The roadside line set includes a first roadside line and a second roadside line, where the second roadside line is any roadside line in the set other than the first roadside line. A detection range is generated based on the roadside point on the first roadside line and the nearest vehicle trajectory point in the vehicle trajectory line set. The system detects whether a second roadside line meeting preset detection conditions exists within the detection range. If so, noise is determined to exist within the detection range. This application uses the geometric relationship between vehicle trajectory lines and roadside lines to determine the location of noise, making it easier to optimize noise data in electronic maps and improving the map optimization process.

[0040] Please see Figure 2 The second embodiment of the roadside noise detection method in this invention includes:

[0041] 201. Obtain the pre-collected vehicle trajectory line set and roadside line set;

[0042] 202. Select the roadside points along the first road and connect the roadside points to the vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set to obtain the connection distance between the roadside points and each vehicle trajectory point.

[0043] In this embodiment, by selecting the roadside line in the first roadside line and connecting the selected roadside point with the vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set, the connection distance between the roadside point and each vehicle trajectory point is obtained.

[0044] On the one hand, the distance between the curb point and the vehicle trajectory point can be limited, and the vehicle trajectory point outside the limited distance will not be included in the calculation range, thus saving computing resources.

[0045] Specifically, the selection method for curb points can be to determine the first curb line, and then select the curb points in the first curb line in sequence based on the direction of the curb line.

[0046] 203. Based on the connection distance, identify the vehicle trajectory point closest to the curb point, and obtain the nearest vehicle trajectory point to the curb point;

[0047] In this embodiment, based on several determined connection distances, the vehicle trajectory point with the shortest connection distance to the curb point is selected and identified to obtain the nearest vehicle trajectory point to the curb point.

[0048] Specifically, based on the connection distance between the curb point and each vehicle trajectory point obtained in step 202, the vehicle trajectory point corresponding to the minimum connection distance is selected as the nearest vehicle trajectory point to the curb point.

[0049] 204. Connect the curb point with the corresponding nearest vehicle trajectory point to obtain the first line segment;

[0050] In this embodiment, a first line segment is obtained by connecting the curb point with the corresponding nearest vehicle trajectory point, and the length of the first line segment is the connection distance in step 202 above.

[0051] On one hand, the first line segment is perpendicular to the first roadside line where the roadside point is located, and the foot of the perpendicular.

[0052] 205. Using the first line segment as the radius and the curb point as the center, generate a circular area, and use the circular area as the detection range of the curb point;

[0053] In this embodiment, a circular region is generated with the curb point as the center and the length of the first line segment as the radius, and it is determined whether there is a curb point of the second curb line in the circular region.

[0054] Specifically, by generating a specific detection range, the detection time for a single roadside point is reduced, saving computational resources.

[0055] 206. Determine whether there is a roadside point along the second road within the detection range;

[0056] In this embodiment, after generating the detection range in step 205 and determining that there is a road edge point along the second road, it is necessary to detect whether there is a second road edge within the detection range.

[0057] On the other hand, if the edge point of the second path falls on the edge of the detection range, it is also considered to be included in the detection range.

[0058] On the one hand, after obtaining the first line segment in step 204, it can be determined whether there is a second path that intersects with the second line segment, and the corresponding judgment result can be generated.

[0059] On the other hand, if a second road edge exists within the detection range, and this second road edge does not intersect with the first road edge, then a road edge point within the detection range of the second road edge is selected as the second road edge point. This second road edge point is then connected to the nearest vehicle trajectory point determined in step 204 to obtain a third line segment. This third line segment intersects with the first road edge. Subsequently, using the second road edge point as a fixed point, the third line segment is extended in the reverse direction to a preset length to obtain a fourth line segment. It is then determined whether there are other road edges or other vehicle trajectory lines intersecting with the fourth line segment. If none exist, then the first road edge or the second road edge existing within the monitoring range is determined to be noise.

[0060] 207. If it exists, determine whether the second path line to which the second path point belongs intersects with the first line segment, and obtain the judgment result;

[0061] In this embodiment, by determining whether the second road line intersects with the first line segment, it is determined whether there is more than one road line in the same direction. The determination results include whether the second road line intersects with the first line segment and whether the second road line does not intersect with the first line segment.

[0062] On the one hand, for steps 206-208, it can be determined whether the second path intersects with the first line segment to obtain a judgment result; based on the judgment result, it can be determined whether the second path exists within the detection range.

[0063] 208. Based on the judgment result, determine whether the detection range intersects with the second path;

[0064] 209. If so, then extend the first line segment in the opposite direction to the preset length based on the road edge point in the first line segment to obtain the second line segment;

[0065] In this embodiment, the second line segment is obtained by extending the length of the first line segment in the opposite direction from the curb point of the first line segment as the endpoint.

[0066] Specifically, by generating a second line segment, it is determined whether the second line segment intersects with other roadside lines or vehicle trajectory lines, thereby determining whether any of the first or second roadside lines within the detection range is noise.

[0067] Specifically, the reason for generating the second line segment is to determine whether the first or second roadside line within the detection range belongs to the same vehicle trajectory line. If so, it indicates that there are two roads, and the two roadside lines serve to separate the two roads, and it cannot be confirmed that there is noise.

[0068] 210. Based on the intersection status of the second line segment with any vehicle trajectory line or roadside line, determine whether there is a second roadside line that meets the preset detection conditions;

[0069] In this embodiment, by confirming the intersection status of the second line segment with any vehicle trajectory line or roadside line, if the intersection status is that there is an intersection, then the second roadside line meets the preset detection conditions; if the intersection status is that there is no intersection, then the second roadside line does not meet the preset detection conditions.

[0070] 211. If so, then noise is confirmed to exist within the detection range;

[0071] 212. Compare the lengths along the first path and the second path to obtain the comparison results;

[0072] 213. Based on the comparison results, the shorter road edge between the first and second road edges is identified as noise;

[0073] 214. Remove roadside lines that are identified as noise in the set of roadside lines to achieve noise reduction of the roadside line set.

[0074] This embodiment, based on the previous embodiment, describes in detail the process of selecting a roadside point in the first roadside line, and connecting the roadside point to vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set to obtain the connection distance between the roadside point and each vehicle trajectory point; based on the connection distance, identifying the vehicle trajectory point closest to the roadside point to obtain the nearest vehicle trajectory point of the roadside point; connecting the roadside point to the corresponding nearest vehicle trajectory point to obtain a first line segment; generating a circular area with the first line segment as the radius and the roadside point as the center, and using the circular area as the detection range of the roadside point. Compared with the traditional method, this embodiment clarifies the geometric relationship of the vehicle trajectory lines corresponding to the first roadside line, and creates corresponding auxiliary lines based on the geometric relationship to determine the detection range, optimize the detection time, and prevent the overflow of invalid computational data.

[0075] Please see Figure 3 The third embodiment of the roadside noise detection method in this invention includes:

[0076] 301. Obtain the pre-collected vehicle trajectory line set and roadside line set;

[0077] 302. Select the vehicle trajectory lines that are closest to multiple roadside points in the roadside line to obtain the vehicle trajectory line set;

[0078] In this embodiment, the first roadside is first determined, and based on the roadside points existing in the first roadside, the closest vehicle trajectory line corresponding to the roadside point is selected through traversal to obtain the set of vehicle trajectory lines corresponding to the roadside points in the first roadside.

[0079] Specifically, a first roadway is defined, which has three roadway points a, b, and c. By traversing the roadway, the closest vehicle trajectory line to point a is identified as l1, the closest vehicle trajectory line to point b is l2, and the closest vehicle trajectory line to point c is l1. This results in a set of vehicle trajectory lines (l1 / l2 / l1). The vehicle trajectory line (l1) that appears most frequently in the set of vehicle trajectory lines is selected and a subordinate relationship is established with the corresponding roadway line (the first roadway). That is, the first roadway line and the vehicle trajectory line l1 form a subordinate relationship.

[0080] 303. Select the vehicle trajectory line that appears most frequently in the set of vehicle trajectory lines and establish a subordinate relationship with the roadside line;

[0081] Specifically, because the vehicle trajectory line is collected by continuously driving through several road segments, and because the roadside lines cross intersections, equipment factors, corners, etc., there will be several roadside lines that are subordinate to the vehicle trajectory line.

[0082] 304. Construct several perpendicular lines for the vehicle trajectory lines where the vehicle trajectory lines are concentrated;

[0083] In this embodiment, the vehicle trajectory lines in the selected vehicle trajectory line set are traversed, and several perpendicular lines are constructed based on a preset spacing.

[0084] On the one hand, the preset spacing can also be based on vehicle trajectory points in the vehicle trajectory line, wherein the vehicle trajectory line contains a number of vehicle trajectory points.

[0085] 305. Determine whether a perpendicular line intersects with more than two roadside lines that have a subordinate relationship;

[0086] In this embodiment, noise is determined to exist when the perpendicular line corresponding to the vehicle trajectory line intersects with more than two roadside lines that have a subordinate relationship.

[0087] Specifically, after determining the subordinate relationship between the roadside line and the vehicle trajectory line, since a vehicle trajectory can only exist on both sides of the roadside at most at the same time, and there cannot be more than one roadside line on a single side, it is possible to determine whether there is noise between the roadside lines based on the subordinate relationship.

[0088] On the one hand, for the vehicle trajectory lines in the vehicle trajectory line set, the vehicle trajectory points in the set can be traversed and several rays can be constructed based on the vehicle trajectory points as endpoints; it can be determined whether the ray intersects with more than one roadside line with a subordinate relationship; if so, it can be determined that there is noise between the roadside lines that intersect with the ray at the same time.

[0089] It is understandable that by comparing the lengths of the roadside sections where noise exists, the shorter roadside section is selected as the noise source.

[0090] 306. If so, then it is determined that there is noise along the roadside in the subordinate relationship.

[0091] This embodiment, based on the previous embodiment, details the process of constructing a dependency relationship between the vehicle trajectory line set and the roadside line set; constructing several perpendicular lines for the vehicle trajectory lines in the vehicle trajectory line set; determining whether the perpendicular lines intersect with more than two roadside lines with a dependency relationship; if so, determining that noise exists on the roadside lines in the dependency relationship. Compared with traditional methods, this embodiment clarifies the dependency relationship between roadside lines and vehicle trajectory lines. Since a vehicle trajectory can only exist on two roadside lines at most simultaneously, and there cannot be more than one roadside line on one side, it is possible to determine whether noise exists between roadside lines based on the dependency relationship.

[0092] The roadside noise detection method in the embodiments of the present invention has been described above. The roadside noise detection device in the embodiments of the present invention will be described below. Please refer to [link / reference]. Figure 4 One embodiment of the roadside noise detection device in this invention includes:

[0093] The map acquisition module 401 is used to acquire a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, and the second roadside line is the roadside line in the set of roadside lines other than the first roadside line;

[0094] The detection range generation module 402 is used to generate the detection range corresponding to the roadside point based on the nearest vehicle trajectory point in the set of the roadside points on the first roadside line and the vehicle trajectory lines.

[0095] Noise detection module 403 is used to detect whether there is a second path along the detection range that meets the preset detection conditions;

[0096] The noise determination module 404 is used to determine that noise exists within the detection range if the noise is present.

[0097] In this embodiment of the invention, the roadside noise detection device operates the aforementioned roadside noise detection method, including: acquiring a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, the second roadside line being the roadside lines in the set excluding the first roadside line; generating a detection range corresponding to the roadside point based on the roadside point on the first roadside line and the nearest vehicle trajectory point in the set of vehicle trajectory lines; detecting whether a second roadside line satisfying preset detection conditions exists within the detection range; and if so, determining that noise exists within the detection range. This application uses the geometric relationship between vehicle trajectory lines and roadside lines to determine the location of noise, more conveniently optimizing noise data in electronic maps and improving the map optimization process.

[0098] Please see Figure 5 A second embodiment of the roadside noise detection device in this invention includes:

[0099] The map acquisition module 401 is used to acquire a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, and the second roadside line is the roadside line in the set of roadside lines other than the first roadside line;

[0100] The detection range generation module 402 is used to generate the detection range corresponding to the roadside point based on the nearest vehicle trajectory point in the set of the roadside points on the first roadside line and the vehicle trajectory lines.

[0101] Noise detection module 403 is used to detect whether there is a second path along the detection range that meets the preset detection conditions;

[0102] The noise determination module 404 is used to determine that noise exists within the detection range if the noise is present.

[0103] In this embodiment, the detection range generation module 402 is specifically used for:

[0104] Select a roadside point in the first roadside line, and connect the roadside point to the vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set to obtain the connection distance between the roadside point and each vehicle trajectory point; based on the connection distance, identify the vehicle trajectory point closest to the roadside point to obtain the nearest vehicle trajectory point of the roadside point; connect the roadside point to the corresponding nearest vehicle trajectory point to obtain a first line segment; generate a circular area with the first line segment as the radius and the roadside point as the center, and use the circular area as the detection range of the roadside point.

[0105] In this embodiment, the noise detection module 403 is specifically used for:

[0106] Intersection judgment unit 4031 determines whether the detection range intersects with the second roadside line; reverse extension unit 4032, if so, extends the first line segment to a preset length based on the roadside point in the first line segment to obtain the second line segment; detection condition determination unit 4033, based on the intersection state of the second line segment with any vehicle trajectory line or roadside line, determines whether there is a second roadside line that meets the preset detection conditions.

[0107] In this embodiment, the intersection determination unit 4031 is specifically used for:

[0108] Determine whether there are road edge points along the second road within the detection range, wherein the second road is composed of several second road edge points; if so, determine whether the second road edge to which the second road edge point belongs intersects with the first line segment to obtain a determination result; based on the determination result, determine whether the detection range intersects with the second road edge.

[0109] In this embodiment, the roadside noise detection device further includes a traversal noise reduction module 405, which is specifically used for:

[0110] The lengths of the first road edge and the second road edge are compared to obtain a comparison result; based on the comparison result, the shorter road edge between the first road edge and the second road edge is identified as noise; the road edges identified as noise in the road edge set are removed to achieve noise removal of the road edge set.

[0111] In this embodiment, the roadside noise detection device further includes a second noise determination module 406, which is specifically used for:

[0112] Subordination relationship construction unit 4061 constructs a subordinate relationship between the vehicle trajectory line set and the roadside line set; perpendicular line construction unit 4062 constructs several perpendicular lines for the vehicle trajectory lines in the vehicle trajectory line set; intersection judgment unit 4063 determines whether the perpendicular line intersects with more than two roadside lines with subordinate relationships; noise determination unit 4064, if so, determines that there is noise in the roadside lines of the subordinate relationships.

[0113] In this embodiment, the subordinate relationship construction unit 4061 is specifically used for:

[0114] Select the vehicle trajectory lines that are closest to multiple roadside points in the vehicle trajectory line set to obtain a vehicle trajectory line set; select the vehicle trajectory line that appears most frequently in the vehicle trajectory line set and establish a subordinate relationship with the roadside line.

[0115] Based on the previous embodiment, this embodiment describes in detail the specific functions of each module and the unit composition of some modules. Through the above modules, the specific functions of the original modules are refined, the operation of the roadside noise detection device is improved, its operational reliability is enhanced, and the actual logic between each step is clarified, thereby improving the practicality of the device.

[0116] above Figure 4 and Figure 5 The roadside noise detection device in this embodiment of the invention is described in detail from the perspective of modular functional entities. The roadside noise detection device in this embodiment of the invention is described in detail below from the perspective of hardware processing.

[0117] Figure 6 This is a schematic diagram of the structure of a roadside noise detection device 600 provided in an embodiment of the present invention. The roadside noise detection device 600 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. The memory 620 and storage media 630 can be temporary or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the diagram), each module may include a series of request operations on the roadside noise detection device 600. Furthermore, the processor 610 may be configured to communicate with the storage media 630 and execute the series of request operations in the storage media 630 on the roadside noise detection device 600 to implement the steps of the roadside noise detection method described above.

[0118] The roadside noise detection device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input / output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 6 The illustrated roadside noise detection device structure does not constitute a limitation on the roadside noise detection device provided in this application. It may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0119] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores a request that, when the request is executed on a computer, causes the computer to perform the steps of the roadside noise detection method.

[0120] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0121] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several requests to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0122] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting roadside noise, characterized in that, The roadside noise detection method includes: Obtain a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, and the second roadside line is the roadside line in the set of roadside lines excluding the first roadside line; A first line segment is obtained based on the nearest vehicle trajectory point in the set of vehicle trajectory lines and the road edge point on the first road edge line, and a detection range corresponding to the road edge point is generated based on the first line segment. Detect whether there is a second path within the detection range that meets the preset detection conditions; If so, then it is determined that noise exists within the detection range; The detection of whether a second path meeting preset detection conditions exists within the detection range includes: Determine whether the detection range intersects with the second roadside line; if so, extend the first line segment in the opposite direction to a preset length based on the roadside point in the first line segment to obtain the second line segment; based on the intersection state of the second line segment with any vehicle trajectory line or roadside line, determine whether there is a second roadside line that meets the preset detection conditions.

2. The roadside noise detection method according to claim 1, characterized in that, The step of obtaining a first line segment based on the nearest vehicle trajectory point in the set of vehicle trajectory lines and the roadside point on the first roadside line, and generating a detection range corresponding to the roadside point based on the first line segment, includes: Select the curb points in the first roadline, and connect the curb points with the vehicle trajectory points on each vehicle trajectory line in the vehicle trajectory line set to obtain the connection distance between the curb points and each vehicle trajectory point. Based on the connection distance, identify the vehicle trajectory point closest to the curb point, and obtain the nearest vehicle trajectory point to the curb point; Connect the curb point with the corresponding nearest vehicle trajectory point to obtain the first line segment; A circular region is generated with the first line segment as the radius and the curb point as the center, and the circular region is used as the detection range of the curb point.

3. The roadside noise detection method according to claim 2, characterized in that, The step of determining whether the detection range intersects with the second path includes: Determine whether there are road edge points along the second road within the detection range, wherein the second road consists of a plurality of second road edge points; If it exists, then determine whether the second path line to which the second path point belongs intersects with the first line segment, and obtain the determination result; Based on the judgment result, determine whether the detection range intersects with the second path.

4. The roadside noise detection method according to claim 3, characterized in that, After determining that noise exists within the detection range, the method further includes: Compare the lengths along the first path and the second path to obtain the comparison result; Based on the comparison results, the shorter roadside line between the first roadside line and the second roadside line is identified as noise; The roadside lines identified as noise are removed from the roadside line set to achieve noise reduction.

5. The roadside noise detection method according to claim 2, characterized in that, The vehicle trajectory line and the roadside line are vectors; After acquiring the pre-collected vehicle trajectory line set and roadside line set, the process also includes: Establish a hierarchy relationship between the vehicle trajectory line set and the roadside line set; Construct several perpendicular lines for the vehicle trajectory lines in the vehicle trajectory line set; Determine whether the perpendicular line intersects with more than two roadside lines that have a subordinate relationship; If so, then it is determined that there is noise along the roadside in the subordinate relationship.

6. The roadside noise detection method according to claim 5, characterized in that, The process of establishing a dependency relationship between the vehicle trajectory line set and the roadside line set includes: Select the vehicle trajectory lines that are closest to multiple roadside points in the roadside line from the vehicle trajectory line set to obtain the vehicle trajectory line set. The vehicle trajectory line that appears most frequently in the set of vehicle trajectory lines is selected and a subordinate relationship is established with the roadside line.

7. A roadside noise detection device, characterized in that, The roadside noise detection device includes: The map acquisition module is used to acquire a pre-collected set of vehicle trajectory lines and a set of roadside lines, wherein the set of roadside lines includes a first roadside line and a second roadside line, and the second roadside line is the roadside line in the set of roadside lines excluding the first roadside line; The detection range generation module is used to obtain a first line segment based on the nearest vehicle trajectory point in the set of vehicle trajectory lines and the road edge point on the first road edge line, and to generate the detection range corresponding to the road edge point based on the first line segment. The noise detection module is used to detect whether there is a second path along the detection range that meets the preset detection conditions; A noise determination module is used to determine, if yes, that noise exists within the detection range; The detection of whether a second path meeting preset detection conditions exists within the detection range includes: Determine whether the detection range intersects with the second roadside line; if so, extend the first line segment in the opposite direction to a preset length based on the roadside point in the first line segment to obtain the second line segment; based on the intersection state of the second line segment with any vehicle trajectory line or roadside line, determine whether there is a second roadside line that meets the preset detection conditions.

8. An electronic device, characterized in that, The electronic device includes a memory and at least one processor, the memory storing instructions; the at least one processor invokes the instructions in the memory to cause the electronic device to perform the steps of the roadside noise detection method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the roadside noise detection method as described in any one of claims 1-6.

Images