A parking lot map generation method and device, a vehicle, and a storage medium

Abstract

Embodiments of the present application provide a parking lot map generation method and device, a vehicle and a storage medium, the method comprising: acquiring point cloud map data and reference line data; performing vectorization processing on the point cloud map data to generate vector point cloud data; fitting the reference line data according to the vector point cloud data to determine drawing line data; generating an identifier element based on the reference line data and the drawing line data; and combining the identifier element to generate a parking lot map. Embodiments of the present application vectorize point cloud map data, thereby reducing storage space and loading time, and making it more intuitive. Furthermore, the point cloud data is converted into corresponding identifiers, thereby greatly reducing the time for drawing a full-field base map and improving the production efficiency of the map.

Description

Technical Field

[0001] This invention relates to the field of map drawing technology, and in particular to a parking lot map generation method, a parking lot map generation device, a vehicle, and a storage medium. Background Technology

[0002] For the parking lot full-site map function, a crowdsourcing approach was adopted to stitch together trajectory data collected from multiple vehicle trips to produce a parking lot map for the entire country. This resulted in a massive amount of point cloud map data collected from vehicles. Loading this point cloud data into the editor, with its excessively long loading and response times, significantly reduced the editing experience for users. Furthermore, the large and dense point cloud data also affected the editor's judgment during base map stitching and drawing, greatly increasing the difficulty of map editing and impacting its accuracy. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a parking map generation method, a parking map generation device, a vehicle, and a storage medium that overcome or at least partially solve the above problems.

[0004] This invention discloses a parking lot map generation method, including:

[0005] Acquire point cloud map data and reference line data;

[0006] The point cloud map data is vectorized to generate vector point cloud data;

[0007] The reference line data is fitted based on the vector point cloud data to determine the drawing line data;

[0008] Based on the reference line data and the drawn line data, generate identifier elements;

[0009] Combine the aforementioned signage elements to generate a parking lot map.

[0010] Optionally, the step of fitting the reference line data to the vector point cloud data to determine the drawing line data includes:

[0011] A vector reference line is generated by performing linear regression fitting on the reference line data based on the vector point cloud data.

[0012] The drawing area corresponding to the vector reference line is determined based on the vector point cloud data;

[0013] In the drawing area, equidistant lines are generated perpendicular to the vector reference lines;

[0014] Filter the equidistant lines to generate drawing line data.

[0015] Optionally, the step of determining the drawing area corresponding to the vector reference line based on the vector point cloud data includes:

[0016] Based on the position of the vector reference line, the vector point cloud data is divided into a first region point cloud data and a second region point cloud data;

[0017] Determine the number of first point clouds corresponding to the point cloud data of the first region and the number of second point clouds corresponding to the point cloud data of the second region;

[0018] When the number of the first point cloud is greater than the number of the second point cloud, the area where the first region point cloud data is located is determined as the drawing area;

[0019] When the number of the first point cloud is less than the number of the second point cloud, the area where the second region point cloud data is located is determined as the drawing area.

[0020] Optionally, the step of filtering the equidistant lines to generate the drawing line data includes:

[0021] The judgment area of ​​the equidistant line is determined according to the preset distance value;

[0022] The region point cloud is determined based on the vector point cloud data covered by the determined region;

[0023] Calculate the number of point clouds in the region and the standard deviation of the point clouds;

[0024] The point cloud quality is determined based on the number of point clouds in the region and the standard deviation of the point clouds.

[0025] The isometric lines are filtered according to the point cloud quality to generate drawing line data.

[0026] Optionally, the step of filtering the equidistant lines according to the point cloud quality to generate drawing line data includes:

[0027] The target equidistant line is determined in the equidistant line based on the point cloud quality;

[0028] Determine the location of the target equidistant line, and use the equidistant lines on both sides with a preset number of filtering quantities as filtering lines;

[0029] The filtered lines are then used to generate plotted line data.

[0030] Optionally, the step of generating identifier elements based on the reference line data and the drawn line data includes:

[0031] Get grouping criteria;

[0032] When the reference line data and the drawn line data meet the grouping conditions, the reference line data is grouped to generate connection line data; and

[0033] The identifier element is generated by combining the connection line data and the drawing line data;

[0034] When the reference line data and the drawn line data do not meet the grouping conditions, an identifier element is generated by combining the reference line data and the drawn line data.

[0035] Optionally, the grouping conditions include:

[0036] At least one of the following conditions must be met: the distance between the drawn line data is outside a preset distance range; the number of vector point cloud data covered by the reference line data is less than a preset number; and the standard deviation of the vector point cloud data within the preset range of the reference line data is greater than a preset difference.

[0037] This invention also discloses a parking lot map generation device, comprising:

[0038] The acquisition module is used to acquire point cloud map data and reference line data;

[0039] The vectorization module is used to perform vectorization processing on the point cloud map data to generate vector point cloud data;

[0040] The fitting module is used to fit the reference line data to the vector point cloud data to determine the drawing line data;

[0041] The generation module is used to generate identifier elements based on the reference line data and the drawing line data;

[0042] The combination module is used to combine the signage elements to generate a parking lot map.

[0043] This invention also discloses a vehicle, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the steps of the parking map generation method described above.

[0044] This invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the parking lot map generation method described above.

[0045] The embodiments of the present invention have the following advantages:

[0046] This invention acquires point cloud map data and reference line data; performs vectorization processing on the point cloud map data to generate vector point cloud data; vectorization of the point cloud map data reduces storage space and loading time, making the base map more intuitive when drawing the map; fits the reference line data to the vector point cloud data to determine the drawing line data; generates marker elements based on the reference line data and the drawing line data; automatically fits the point cloud data to the reference line data, converting the point cloud map data into corresponding marker elements, avoiding manual identification and classification of markers in the point cloud map data, greatly reducing the time for drawing the entire base map and improving production efficiency; combines the marker elements to generate a parking lot map; and improves the accuracy of map drawing. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating the steps of an embodiment of the parking lot map generation method of the present invention;

[0048] Figure 2 This is a flowchart illustrating the steps of another embodiment of the parking lot map generation method of the present invention;

[0049] Figure 3 This is a structural block diagram of an embodiment of a parking lot map generation device according to the present invention. Detailed Implementation

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] In related technologies, map data collection relies on surveying vehicles collecting data from actual roads. All collected data is then imported into a map editor. Due to the massive data volume, the loading time for importing data into the map editor is long, and the editor's response time is also long, leading to low production efficiency. Furthermore, editors need to determine the specific types of landmarks during map drawing, which can result in human errors and map rendering mistakes. This invention addresses how to quickly and accurately draw different geographic elements from massive amounts of point cloud data on various parking lots across the country, making map visualization more intuitive and ultimately producing a comprehensive map of parking lots nationwide.

[0052] Reference Figure 1 The diagram illustrates a flowchart of an embodiment of a parking lot map generation method according to the present invention, which may specifically include the following steps:

[0053] Step 101: Obtain point cloud map data and reference line data;

[0054] It should be noted that the point cloud map data in this embodiment of the invention is generated based on crowdsourced map data. The crowdsourced data refers to road data collected by mass-produced vehicles during actual driving conditions. After collecting the road data, the mass-produced vehicles store it in their storage space. When connected to a cloud server, the road data is then uploaded to the cloud server. The cloud server receives the road data, converts it into point cloud map data, and stores it at a designated address. When editing the point cloud map data is needed, it can be retrieved from the designated address; the designated address can be the storage address of the cloud server's own storage space or a cloud storage address. This embodiment of the invention does not impose specific limitations on this.

[0055] Reference line data can be generated based on a reference line manually entered by the editor in the editor. The reference line data can be obtained at the start of editing based on the editor's input in the editor.

[0056] Step 102: Perform vectorization processing on the point cloud map data to generate vector point cloud data;

[0057] In practical applications, vectorization algorithms can be used to convert point clouds in point cloud map data into vectorized data, generating vector point cloud data, thereby reducing the number of point clouds. The specific vectorization algorithm used can be selected by those skilled in the art based on actual needs; this embodiment of the invention does not impose specific limitations on the vectorization algorithm.

[0058] Step 103: Fit the reference line data to the vector point cloud data to determine the drawing line data;

[0059] After obtaining the vector point cloud data, the reference line data can be fitted based on the vector point cloud data to generate multiple drawing line data, so as to simulate the outline of the marker corresponding to the vector point cloud data near the reference line data and determine the type of marker.

[0060] Step 104: Generate identifier elements based on the reference line data and the drawn line data;

[0061] After generating the drawing line data, the drawing line data is connected with the reference line data to form multiple marker elements, so as to generate various markers in the parking lot on the point cloud map data;

[0062] Step 105: Combine the sign elements to generate a parking lot map.

[0063] The obtained marker elements are combined according to their point cloud positions to generate a complete parking lot map. This allows the parking lot map to be drawn automatically simply by the editor inputting reference lines.

[0064] This invention acquires point cloud map data and reference line data; performs vectorization processing on the point cloud map data to generate vector point cloud data; vectorization of the point cloud map data reduces storage space and loading time, making the base map more intuitive when drawing the map; fits the reference line data to the vector point cloud data to determine the drawing line data; generates marker elements based on the reference line data and the drawing line data; automatically fits the point cloud data to the reference line data, converting the point cloud map data into corresponding marker elements, avoiding manual identification and classification of markers in the point cloud map data, greatly reducing the time for drawing the entire base map and improving production efficiency; combines the marker elements to generate a parking lot map; and improves the accuracy of map drawing.

[0065] Reference Figure 2 The diagram illustrates a flowchart of another embodiment of the parking lot map generation method of the present invention, which may specifically include the following steps:

[0066] Step 201: Obtain point cloud map data and reference line data;

[0067] Point cloud map data generated based on crowdsourced data is obtained from the cloud storage address, and reference line data corresponding to the reference line is obtained based on a reference line input by the editor. The reference line input by the editor can be drawn in a location with dense point cloud data in the point cloud map data, and can be either a straight line or a curve; this embodiment of the invention does not impose specific limitations on this.

[0068] Step 202: Perform vectorization processing on the point cloud map data to generate vector point cloud data;

[0069] Point cloud map data often contains a lot of duplicates. To address this, point cloud map data is vectorized to generate vector point cloud data. This makes the display more intuitive during the base map stitching process, allowing editors to stitch the point cloud map into a more complete map data through operations such as moving and rotating.

[0070] In addition, the stitching process needs to be able to stitch and merge adjacent parts in different point cloud data. This requires interpolation of the vector point cloud data, and then optimization and fusion of the interpolated point cloud data with the vector point cloud data, thereby further reducing the amount of point cloud data.

[0071] Step 203: Perform linear regression fitting on the reference line data based on the vector point cloud data to generate a vector reference line;

[0072] For the reference line data, the drawn lines are fitted and adjusted using algorithms such as linear fitting, least squares method, and PCA (principal components analysis) based on the vector point cloud data to generate vector reference lines, thereby correcting the manually input reference lines and further avoiding the influence of human factors on the accuracy of map drawing.

[0073] Step 204: Determine the drawing area corresponding to the vector reference line based on the vector point cloud data;

[0074] After determining the vector reference line, a drawing area can be established on one side of the vector reference line based on the vector point cloud data, thus defining the area to be drawn for subsequent content.

[0075] In an optional embodiment of the present invention, the step of determining the drawing area corresponding to the vector reference line based on the vector point cloud data includes:

[0076] Sub-step S2041: According to the position of the vector reference line, the vector point cloud data is divided into a first region point cloud data and a second region point cloud data;

[0077] Based on the position of the vector reference line, and using the vector reference line as the dividing standard, the vector point cloud data is divided into two parts: the first region point cloud data and the second region point cloud data. The first and second regions refer to the different areas on either side of the vector reference line; for example, if the vector reference line is a vertical straight line, the first and second regions could refer to the left and right sides, respectively. If the vector reference line is a horizontal straight line, the first and second regions could refer to the upper and lower sides, respectively. The point cloud data within each corresponding region is then designated as the point cloud data for that region.

[0078] Sub-step S2042: Determine the number of first point clouds corresponding to the point cloud data of the first region and the number of second point clouds corresponding to the point cloud data of the second region;

[0079] Determine the first point cloud quantity corresponding to the point cloud data of the first region, where the first point cloud quantity is the total point cloud quantity of all point cloud data in the first region. Determine the second point cloud quantity corresponding to the point cloud data of the second region, where the second point cloud quantity is the total point cloud quantity of all point cloud data in the second region.

[0080] Sub-step S2043: When the number of the first point cloud is greater than the number of the second point cloud, determine the area where the first region point cloud data is located as the drawing area;

[0081] When the number of points in the first point cloud is greater than the number of points in the second point cloud, that is, there is a point cloud corresponding to an object in the first region, the region where the point cloud data of the first region is located is determined as the drawing region, that is, the first region is determined as the drawing region.

[0082] Sub-step S2044: When the number of the first point cloud is less than the number of the second point cloud, determine the area where the second region point cloud data is located as the drawing area.

[0083] When the number of points in the first point cloud is less than the number of points in the second point cloud, that is, there is a point cloud corresponding to an object in the second region, the region where the point cloud data of the second region is located can be determined as the drawing region, that is, the second region is determined as the drawing region.

[0084] Step 205: In the drawing area, generate equidistant lines perpendicular to the vector reference lines;

[0085] In the drawing area, line segments of fixed length are drawn at equal intervals perpendicular to the vector reference lines to generate equidistant lines. The distance between these equidistant lines and the length of the line segments can be selected by those skilled in the art according to actual needs; this embodiment of the invention does not impose specific limitations on this.

[0086] Step 206: Filter the equidistant lines to generate drawing line data;

[0087] The equidistant lines are filtered out to remove interfering lines, and the remaining equidistant lines are determined as the drawing line data.

[0088] In an optional embodiment of the present invention, the step of filtering the equidistant lines to generate drawing line data includes:

[0089] Sub-step S2061: Determine the judgment area of ​​the equidistant line according to the preset distance value;

[0090] According to a preset distance value, the regions on both sides of the equidistant line with the same width as the preset distance value are determined as the judgment region. The preset distance value is less than the distance between the equidistant lines. The preset distance value is related to the sampling radius of the data; therefore, those skilled in the art can determine the preset distance value based on the sampling radius. This embodiment of the invention does not limit the specific value of the preset distance value.

[0091] Sub-step S2062: Determine the region point cloud based on the vector point cloud data covered by the determined region;

[0092] In practical applications, the vector point cloud data covered by the judgment area can be identified as the regional point cloud within the judgment area. Specifically, this can be determined based on the location of the vector point cloud data; when its location falls within the corresponding location range of the judgment area, the vector point cloud data is identified as the regional point cloud.

[0093] Sub-step S2063: Calculate the number of point clouds in the region and the standard deviation of the point clouds;

[0094] Calculate the specific number of point clouds in each region and the standard deviation of point clouds between regions. Specifically, the specific number of point clouds in each region can be determined statistically, and then the standard deviation of point clouds can be calculated based on the positions of the point clouds between them.

[0095] Sub-step S2064: Determine the point cloud quality based on the number of point clouds in the region and the standard deviation of the point clouds;

[0096] Given the number of point clouds in the region and the standard deviation of the point clouds, these two parameters can be used as evaluation conditions and fed into the quality evaluation function P(quality) = (number of point clouds in the region, standard deviation of point clouds) to calculate the point cloud quality. In one example of this invention, the quality evaluation function can be the sum of the product of the ratio of the number of point clouds in the region to the total number of point cloud data, multiplied by a first weight value, and the product of the standard deviation of the point clouds and a second weight value.

[0097] Sub-step S2065: Filter the equidistant lines according to the point cloud quality to generate drawing line data.

[0098] Based on the point cloud quality, equidistant lines with low point cloud quality are filtered out to generate drawing line data.

[0099] In an optional embodiment of the present invention, the step of filtering the equidistant lines according to the point cloud quality to generate drawing line data includes:

[0100] Sub-step S20651: Determine the target equidistant line in the equidistant line based on the point cloud quality;

[0101] Based on the point cloud quality, the equidistant line with the highest quality is selected as the target equidistant line from among the equidistant lines.

[0102] Sub-step S20652: Determine the location of the target equidistant line, with the equidistant lines on both sides having a preset number of filtering parameters serving as filtering lines;

[0103] Based on the location of the target equidistant line, determine the equidistant lines on both sides of the target equidistant line with a preset number of filters as filter lines; for example, determine the two equidistant lines on the left and the two equidistant lines on the right of the target equidistant line as filter lines.

[0104] Sub-step S20653: Filter the lines to generate drawing line data.

[0105] The filter lines are filtered out, while the target equidistant lines are retained. Then, new target equidistant lines and filter lines are determined repeatedly until all equidistant lines have passed the point cloud quality screening, generating the drawing line data.

[0106] Step 207: Generate identifier elements based on the reference line data and the drawn line data;

[0107] Then, when it is necessary to cut and group the reference line data, the reference line data and the drawn line data are combined with the marker elements, which include, but are not limited to, parking spaces, lane edge lines, lane center lines, speed bumps, lane arrows, and error areas.

[0108] In an optional embodiment of the present invention, the step of generating identifier elements based on the reference line data and the drawn line data includes:

[0109] Sub-step 2071: Obtain the grouping conditions;

[0110] Obtain grouping conditions for cutting groups based on the reference line data, wherein the grouping conditions may differ based on the non-passage of the marker elements.

[0111] In one example of the present invention, the grouping condition includes one of the following conditions:

[0112] If the distance between the drawn line data is outside the preset distance range, that is, if the distance between two drawn line segments is greater than the maximum parking space width or less than the minimum parking space width, it means that there is no parking space in between, and the reference line data between the drawn lines is cut off.

[0113] If the reference line data covers less than a preset number of vector point cloud data, that is, if the reference line data covers too few points, and there are no marker elements at this point, the reference line will be cut off and discarded.

[0114] If the standard deviation of the vector point cloud data within the preset range of the reference line data is greater than the preset difference, and the point cloud under the reference line is too densely distributed on both sides, the standard deviation of the corresponding calculated point cloud is too large, then this segment of reference line data is discarded.

[0115] Sub-step 2072: When the reference line data and the drawn line data meet the grouping conditions, the reference line data is grouped to generate connection line data; and the connection line data and the drawn line data are combined to generate identifier elements.

[0116] When the reference line data and the drawing line data meet the grouping conditions, that is, the reference line data needs to be cut and grouped, the reference line data can be grouped according to the requirements of the grouping conditions to generate multiple connecting line data. Then, the connecting line data is connected with the corresponding drawing line data to generate marker elements.

[0117] Sub-step 2074: When the reference line data and the drawn line data do not meet the grouping conditions, generate an identifier element by combining the reference line data and the drawn line data.

[0118] When neither the reference line data nor the drawing line data meets the grouping condition, that is, the reference line data does not need to be cut off from the group, the reference line data and the drawing line data can be directly connected to generate the marker element.

[0119] Step 208: Combine the signage elements to generate a parking lot map.

[0120] Combine all the obtained landmark elements according to their location to generate a parking lot map.

[0121] This invention acquires point cloud map data and reference line data; performs vectorization processing on the point cloud map data to generate vector point cloud data; vectorization of the point cloud map data reduces storage space and loading time, making the base map more intuitive when drawing the map; fits the reference line data to the vector point cloud data to determine the drawing line data; performs linear regression fitting on the reference line data to generate vector reference lines; determines the drawing area corresponding to the vector reference lines based on the vector point cloud data; generates equidistant lines perpendicular to the vector reference lines in the drawing area; automatically generates multiple drawing lines to draw the outlines of marker elements, then filters the equidistant lines to generate drawing line data. Interfering lines are removed, and marker elements are generated based on the reference line data and the drawing line data; the point cloud data can be automatically fitted based on the reference line data, converting the point cloud map data into corresponding marker elements, avoiding manual identification and classification of markers in the point cloud map data, greatly reducing the time for drawing the entire base map and improving production efficiency; combines the marker elements to generate a parking lot map; and improves the accuracy of map drawing.

[0122] To enable those skilled in the art to better understand the embodiments of the present invention, the following example of drawing parking space elements will be used to illustrate the embodiments of the present invention:

[0123] 1. Draw a reference line on the edge of the parking space based on the editor's drawing, and then perform linear regression fitting on the drawn line based on the point cloud of the parking space edge.

[0124] 2. Determine which side of the reference line has more point clouds belonging to the parking space attribute, and draw a large number of line segments of a fixed length perpendicular to the vector reference line and at equal intervals on that side.

[0125] 3. Take the area around these large number of line segments. These areas are non-intersecting and serve as the judgment area. Calculate the number of points in the area and the standard deviation of the point cloud. Pass these two parameters as evaluation conditions into the quality evaluation function P(quality) = (number of points in the area, standard deviation of the point cloud).

[0126] 4. Calculate the evaluation quality of each line segment using the above function, and then sort them. Lines with a quality lower than 0.2 times the highest quality are discarded.

[0127] 5. Select the highest quality line from the sorted list as the target isometric line (select and keep it), then delete the two isometric lines on either side of the target isometric line, for a total of four lines. Remove the target isometric line that was selected to be kept and the deleted isometric lines, and update the list.

[0128] 6. Repeat the above steps until the quality assessment list is empty, then generate the drawing line.

[0129] 7. Cut the reference lines into groups and connect the cut reference lines with the drawn lines to generate parking space frames.

[0130] 8. Group the parking space frames according to their locations to generate a parking lot map.

[0131] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0132] Reference Figure 3 The diagram shows a structural block diagram of an embodiment of a parking lot map generation device according to the present invention, which may specifically include the following modules:

[0133] The acquisition module 301 is used to acquire point cloud map data and reference line data;

[0134] Vectorization module 302 is used to perform vectorization processing on the point cloud map data to generate vector point cloud data;

[0135] The fitting module 303 is used to fit the reference line data based on the vector point cloud data to determine the drawing line data;

[0136] Generation module 304 is used to generate identifier elements based on the reference line data and the drawing line data;

[0137] The combination module 305 is used to combine the sign elements to generate a parking lot map.

[0138] In an optional embodiment of the present invention, the fitting module 303 includes:

[0139] The fitting submodule is used to perform linear regression fitting on the reference line data based on the vector point cloud data to generate a vector reference line.

[0140] The drawing area determination submodule is used to determine the drawing area corresponding to the vector reference line based on the vector point cloud data;

[0141] An equidistant line generation submodule is used to generate equidistant lines perpendicular to the vector reference lines in the drawing area.

[0142] The filtering submodule is used to filter the equidistant lines and generate drawing line data.

[0143] In an optional embodiment of the present invention, the drawing area determination submodule includes:

[0144] A partitioning unit is used to divide the vector point cloud data into a first region point cloud data and a second region point cloud data according to the position of the vector reference line;

[0145] The quantity determination unit is used to determine the first point cloud quantity corresponding to the first area point cloud data and the second point cloud quantity corresponding to the second area point cloud data.

[0146] The first drawing area determination unit is used to determine the area where the first point cloud data is located as the drawing area when the number of the first point cloud is greater than the number of the second point cloud.

[0147] The second drawing region determination unit is used to determine the region where the second region point cloud data is located as the drawing region when the number of the first point cloud is less than the number of the second point cloud.

[0148] In an optional embodiment of the present invention, the filtering submodule includes:

[0149] The region determination unit is used to determine the region of the equidistant line according to a preset distance value.

[0150] The region point cloud determination unit is used to determine the region point cloud based on the vector point cloud data covered by the determined region.

[0151] A calculation unit is used to calculate the number of point clouds in the region and the standard deviation of the point clouds;

[0152] A point cloud quality determination unit is used to determine the point cloud quality based on the number of point clouds in the region and the standard deviation of the point clouds.

[0153] A filtering unit is used to filter the equidistant lines according to the point cloud quality to generate drawing line data.

[0154] In an optional embodiment of the present invention, the filtering unit includes:

[0155] A target equidistant line determination subunit is used to determine a target equidistant line in the equidistant line based on the point cloud quality.

[0156] The filter line determination subunit is used to determine the location of the target equidistant line, and the equidistant lines on both sides with a preset number of filters are the filter lines;

[0157] The filtering subunit is used to filter the filter lines and generate drawing line data.

[0158] In an optional embodiment of the present invention, the generation module 304 includes:

[0159] The `get` submodule is used to retrieve grouping conditions.

[0160] The first combining submodule is used to group the reference line data and generate connection line data when the reference line data and the drawing line data meet the grouping conditions; and to combine the connection line data and the drawing line data to generate identifier elements.

[0161] The second combining submodule is used to generate an identifier element by combining the reference line data and the drawn line data when the reference line data and the drawn line data do not meet the grouping conditions.

[0162] In an optional embodiment of the present invention, the grouping conditions include:

[0163] One of the following conditions must be met: the distance between the drawn line data is outside a preset distance range; the vector point cloud data covered by the reference line data is less than a preset number; and the standard deviation of the vector point cloud data within the preset range of the reference line data is greater than a preset difference.

[0164] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0165] This invention also provides a vehicle, comprising:

[0166] A processor and a storage medium are provided, the storage medium storing a computer program executable by the processor. When the vehicle is running, the processor executes the computer program to perform the method as described in any of the embodiments of the present invention. The specific implementation and technical effects are similar to those in the method embodiments, and will not be repeated here.

[0167] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the method described in any one of the embodiments of this invention. The specific implementation and technical effects are similar to those in the method embodiments, and will not be repeated here.

[0168] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0169] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0171] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0173] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0174] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0175] The above provides a detailed description of the parking lot map generation method, apparatus, vehicle, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for generating parking lot maps, characterized in that, include: Acquire point cloud map data and reference line data; The point cloud map data is vectorized to generate vector point cloud data; The reference line data is fitted based on the vector point cloud data to determine the drawing line data; Based on the reference line data and the drawn line data, generate identifier elements; Combine the aforementioned signage elements to generate a parking lot map; The step of fitting the reference line data to the vector point cloud data to determine the drawing line data includes: A vector reference line is generated by performing linear regression fitting on the reference line data based on the vector point cloud data. The drawing area corresponding to the vector reference line is determined based on the vector point cloud data; In the drawing area, equidistant lines are generated perpendicular to the vector reference lines; Filter the equidistant lines to generate drawing line data.

2. The method according to claim 1, characterized in that, The step of determining the drawing area corresponding to the vector reference line based on the vector point cloud data includes: Based on the position of the vector reference line, the vector point cloud data is divided into a first region point cloud data and a second region point cloud data; Determine the number of first point clouds corresponding to the point cloud data of the first region and the number of second point clouds corresponding to the point cloud data of the second region; When the number of the first point cloud is greater than the number of the second point cloud, the area where the first region point cloud data is located is determined as the drawing area; When the number of the first point cloud is less than the number of the second point cloud, the area where the second region point cloud data is located is determined as the drawing area.

3. The method according to claim 1, characterized in that, The step of filtering the equidistant lines to generate drawing line data includes: The judgment area of ​​the equidistant line is determined according to the preset distance value; The region point cloud is determined based on the vector point cloud data covered by the determined region; Calculate the number of point clouds in the region and the standard deviation of the point clouds; The point cloud quality is determined based on the number of point clouds in the region and the standard deviation of the point clouds. The isometric lines are filtered according to the point cloud quality to generate drawing line data.

4. The method according to claim 3, characterized in that, The step of filtering the equidistant lines according to the point cloud quality to generate drawing line data includes: The target equidistant line is determined in the equidistant line based on the point cloud quality; Determine the location of the target equidistant line, and use the equidistant lines on both sides with a preset number of filtering quantities as filtering lines; The filtered lines are then used to generate plotted line data.

5. The method according to claim 1, characterized in that, The step of generating identifier elements based on the reference line data and the drawn line data includes: Get grouping criteria; When the reference line data and the drawn line data meet the grouping conditions, the reference line data is grouped to generate connection line data; and The identifier element is generated by combining the connection line data and the drawing line data; When the reference line data and the drawn line data do not meet the grouping conditions, an identifier element is generated by combining the reference line data and the drawn line data.

6. The method according to claim 5, characterized in that, The grouping conditions include: One of the following conditions must be met: the distance between the drawn line data is outside a preset distance range; the vector point cloud data covered by the reference line data is less than a preset number; and the standard deviation of the vector point cloud data within the preset range of the reference line data is greater than a preset difference.

7. A parking lot map generation device, characterized in that, include: The acquisition module is used to acquire point cloud map data and reference line data; The vectorization module is used to perform vectorization processing on the point cloud map data to generate vector point cloud data; The fitting module is used to fit the reference line data to the vector point cloud data to determine the drawing line data; The generation module is used to generate identifier elements based on the reference line data and the drawing line data; The combination module is used to combine the sign elements to generate a parking lot map; The fitting module includes: The fitting submodule is used to perform linear regression fitting on the reference line data based on the vector point cloud data to generate a vector reference line. The drawing area determination submodule is used to determine the drawing area corresponding to the vector reference line based on the vector point cloud data; An equidistant line generation submodule is used to generate equidistant lines perpendicular to the vector reference lines in the drawing area. The filtering submodule is used to filter the equidistant lines and generate drawing line data.

8. A vehicle, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the parking map generation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the parking map generation method as described in any one of claims 1 to 6.

Images