A method and device for updating a map

Abstract

The embodiment of the present invention provides a method and device for updating a map, the method comprising: when the vehicle has not passed the target parking space, obtaining first parking space information collected by the vehicle, and constructing target map data based on the first parking space information; when the vehicle passes the target parking space, obtaining second parking space information collected for the target parking space; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems; based on the first parking space information and the second parking space information, determining deviation information of the target parking space; and updating the target map data according to the deviation information. Through the embodiment of the present invention, the parking space information is collected based on two parking space recognition systems, and the parking space elements can still be ensured in the map when one of the parking space recognition systems misses recognition or even fails, thereby increasing the robustness of parking space recognition and making real-time map data more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular to a method and device for updating a map. Background Art

[0002] In smart cars, parking spaces are important semantic elements in maps, which directly affect the accuracy of indoor positioning. In parking lots, there are a large number of parking spaces. How to identify and use more parking space information is crucial for vehicles to build accurate maps and park.

[0003] Currently, a vehicle can be equipped with a parking space recognition system for identifying parking spaces in the environment. However, once the parking space recognition system fails or has low accuracy, the identified parking spaces may not be accurate enough, or even some parking spaces may not be recognized at all. Summary of the invention

[0004] In view of the above problems, a method and device for map updating, an electronic device, and a storage medium are proposed to overcome the above problems or at least partially solve the above problems, including:

[0005] A method for updating a map, the method comprising:

[0006] When the vehicle does not pass the target parking space, first parking space information collected by the vehicle is acquired, and target map data is constructed based on the first parking space information;

[0007] When the vehicle passes the target parking space, second parking space information collected for the target parking space is obtained; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems;

[0008] Determining deviation information of the target parking space based on the first parking space information and the second parking space information;

[0009] The target map data is updated according to the deviation information.

[0010] Optionally, updating the target map data according to the deviation information includes:

[0011] Determining whether the deviation information matches preset deviation information;

[0012] When the deviation information matches the preset deviation information, obtaining fused parking space information based on the first parking space information and the second parking space information;

[0013] According to the fused parking space information, the first parking space information in the target map data is updated.

[0014] Optionally, it also includes:

[0015] When the deviation information does not match the preset deviation information, the second parking space information is written into the target map data to update the target map data.

[0016] Optionally, the deviation information includes a distance deviation, and determining the deviation information of the target parking space based on the first parking space information and the second parking space information includes:

[0017] The distance deviation of the target parking space is determined according to the first corner point information of the first parking space information and the second corner point information corresponding to the first corner point information in the second parking space information.

[0018] Optionally, the deviation information includes a direction deviation, and determining the deviation information of the target parking space based on the first parking space information and the second parking space information includes:

[0019] The direction deviation of the target parking space is determined according to the first direction information of the first parking space information and the second direction information of the second parking space information.

[0020] Optionally, the deviation information includes a projection deviation, and determining the deviation information of the target parking space based on the first parking space information and the second parking space information includes:

[0021] Determine first ratio information of a coincident line segment obtained by projection relative to the second line segment according to a projection of the first corner point information and the third corner point information of the first parking space information on a second line segment formed by the second corner point information and the fourth corner point information of the second parking space information;

[0022] Determine, according to the projection of the second corner point information and the fourth corner point information on the first line segment formed by the first corner point information and the third corner point information, second ratio information of the overlapped line segment obtained by the projection relative to the first line segment;

[0023] A projection deviation of the target parking space is determined according to the first ratio information and the second ratio information.

[0024] Optionally, constructing target map data based on the first parking space information includes:

[0025] Determining whether the first parking space information is valid parking space information;

[0026] When determining that the first parking space information is valid parking space information, converting the coordinates of the corner points of the first parking space information according to a map coordinate system;

[0027] Based on the converted first parking space information, target map data is constructed.

[0028] Optionally, before determining the deviation information of the target parking space based on the first parking space information and the second parking space information, the method further includes:

[0029] Determining whether the second parking space information is valid parking space information;

[0030] When it is determined that the second parking space information is valid parking space information, the coordinates of the corner points of the second parking space information are converted according to the map coordinate system of the target map data.

[0031] Optionally, the first parking space information is parking space information collected by a parking space recognition system for side front parking space detection, and the second parking space information is parking space information collected by a parking space recognition system for surround view parking space detection.

[0032] A map updating device, comprising:

[0033] a target map data construction module, configured to obtain first parking space information collected by the vehicle when the vehicle has not passed the target parking space, and to construct target map data based on the first parking space information;

[0034] A second parking space information acquisition module, configured to acquire second parking space information collected for the target parking space when the vehicle passes through the target parking space; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems;

[0035] a deviation information determining module, configured to determine deviation information of the target parking space based on the first parking space information and the second parking space information;

[0036] The target map data updating module is used to update the target map data according to the deviation information.

[0037] A vehicle comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the map updating method as described above when executed by the processor.

[0038] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the map updating method described above is implemented.

[0039] The embodiments of the present invention have the following advantages:

[0040] In an embodiment of the present invention, there are at least two parking space recognition systems for a vehicle. During the driving process of the vehicle, first parking space information and second parking space information are collected through different parking space recognition systems, and then based on the first parking space information and the second parking space information, deviation information of the target parking space is determined. Therefore, according to the deviation information, target map data constructed based on the first parking space information can be updated, thereby realizing the collection of parking space information based on the two parking space recognition systems and updating of map data. In addition, even if one of the parking space recognition systems misses recognition or even fails, it can still ensure that there are parking space elements in the map, thereby increasing the robustness of parking space recognition and making real-time map data more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0042] Figure 1 is a flowchart of a method for updating a map provided by an embodiment of the present invention;

[0043] Figure 2a is a flowchart of another method for updating a map provided by an embodiment of the present invention;

[0044] Figure 2b This is a parking space schematic diagram provided by an embodiment of the present invention;

[0045] Figure 2c It is a schematic diagram of calculating the projection overlap length provided by an embodiment of the present invention;

[0046] Figure 3 It is a structural diagram of a map updating device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Reference Figure 1 , shows a flowchart of a method for updating a map provided by an embodiment of the present invention, which may specifically include the following steps:

[0049] Step 101, when the vehicle has not passed the target parking space, obtaining first parking space information collected by the vehicle, and constructing target map data based on the first parking space information;

[0050] In order to obtain more accurate parking space information, two or more parking space recognition systems may be provided in the vehicle, so that different parking space recognition systems can be combined to recognize parking spaces during vehicle driving, thereby improving the accuracy of parking space recognition.

[0051] When a vehicle is driving in a parking lot, relative to a target parking space, before the vehicle reaches the target parking space (i.e., before passing the target parking space), the vehicle can collect first parking space information in the surrounding environment through a parking space recognition system. The first parking space information can be parking space information collected for the target parking space, or can be parking space information collected for other parking spaces in the parking lot.

[0052] The vehicle obtains the collected first parking space information, and a map can be constructed in real time based on the first parking space information. Specifically, the collected first parking space information can be written into the map to construct a current real-time map.

[0053] Among them, the first parking space information may include corner point information (such as corner point coordinates), direction information, parking space attributes (such as parallel parking space or vertical parking space, whether the parking space is occupied, whether there are obstacles in the parking space, etc.). In the embodiment of the present invention, there are no excessive restrictions on the first parking space information.

[0054] In one example, the first parking space information is parking space information collected by a parking space recognition system where the side front parking space is detected.

[0055] In actual applications, the first parking space information can be collected through the front side parking space detection (Front Side Detect, FSD). The characteristic of FSD is that it can identify the parking space before passing through the certain parking space, that is, when a parking space that a vehicle has not passed through is within the preset detection range of the vehicle, the parking space information of the parking space can be collected through the front side parking space detection without the vehicle driving into the parking space.

[0056] Step 102, when the vehicle passes the target parking space, obtaining second parking space information collected for the target parking space; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems;

[0057] In one embodiment of the present invention, the second parking space information is parking space information collected by a parking space recognition system for surround-view parking space detection.

[0058] When the vehicle passes the target parking space, the second parking space information collected for the target parking space can be obtained, wherein the second parking space information includes corner point information, direction information, and parking space attributes (such as a parallel parking space or a vertical parking space, whether the parking space is occupied, whether there are obstacles in the parking space, etc.). In the embodiment of the present invention, there are no excessive restrictions on the second parking space information.

[0059] In practical applications, the second parking space information may be collected through an Around View Monitor (AVM). AVM is characterized in that it can identify a parking space when a vehicle passes by it.

[0060] Step 103, determining deviation information of the target parking space based on the first parking space information and the second parking space information;

[0061] After acquiring the first parking space information and the second parking space information, deviation information of the target parking space can be determined based on the first parking space information and the second parking space information. The deviation information can be used to determine whether the first parking space information matches the second parking space information, or to determine whether the first parking space information is the parking space information collected for the target parking space.

[0062] The deviation information may include distance deviation, direction deviation, and projection deviation.

[0063] Step 104: Update the target map data according to the deviation information.

[0064] After the deviation information is determined, it can be determined whether the first parking space information is the parking space information collected for the target parking space, so that the target map data can be updated according to the deviation information.

[0065] In an embodiment of the present invention, there are at least two parking space recognition systems for a vehicle. During the driving process of the vehicle, first parking space information and second parking space information are collected through different parking space recognition systems, and then based on the first parking space information and the second parking space information, deviation information of the target parking space is determined. Therefore, according to the deviation information, target map data constructed based on the first parking space information can be updated, thereby realizing the collection of parking space information based on the two parking space recognition systems and updating of map data. In addition, even if one of the parking space recognition systems misses recognition or even fails, it can still ensure that there are parking space elements in the map, thereby increasing the robustness of parking space recognition and making real-time map data more accurate.

[0066] Reference Figure 2a , shows a flowchart of another method for updating a map provided by an embodiment of the present invention, which may specifically include the following steps:

[0067] Step 201, when the vehicle has not passed the target parking space, obtaining first parking space information collected by the vehicle, and constructing target map data based on the first parking space information;

[0068] When a vehicle is driving in a parking lot, relative to a target parking space, before the vehicle reaches the target parking space (i.e., before passing the target parking space), the vehicle can collect first parking space information in the surrounding environment through a parking space recognition system. The first parking space information can be parking space information collected for the target parking space, or can be parking space information collected for other parking spaces in the parking lot.

[0069] The vehicle obtains the collected first parking space information, and a map can be constructed in real time based on the first parking space information. Specifically, the collected first parking space information can be written into the map to construct a current real-time map.

[0070] Among them, the first parking space information may include corner point information (such as corner point coordinates), direction information, parking space attributes (such as parallel parking space or vertical parking space, whether the parking space is occupied, whether there are obstacles in the parking space, etc.). In the embodiment of the present invention, there are no excessive restrictions on the first parking space information.

[0071] In an embodiment of the present invention, step 201 may include the following sub-steps:

[0072] Step 2011, determining whether the first parking space information is valid parking space information;

[0073] In practical applications, in order to ensure the accuracy of data in the map, before writing the data, it is possible to first confirm whether the data to be written is valid data. Only when the data is valid data, the data is written into the map.

[0074] After the first parking space information is obtained, it can be determined whether the first parking space information is valid by comparing it with the parking space information measured last time.

[0075] Specifically, when the accuracy flag directly output by the parking space recognition system of FSD is the best, it can be determined that the first parking space information is valid parking space information; at the same time, it can also be determined whether the first parking space information is valid parking space information by whether the NF (a front corner point in the parking space information) distance of the parking space information recognized twice by adjacent FSDs is greater than a preset value (such as 1.5m); it can also be determined whether the first parking space information is valid parking space information by determining whether the XY coordinates of the parking space NF are greater than 0.

[0076] Step 2012: when determining that the first parking space information is valid parking space information, converting the corner point coordinates of the first parking space information according to the map coordinate system;

[0077] When determining that the first parking space information is valid parking space information, in order to conveniently write the first parking space information into the map data, the coordinates of the corner points of the first parking space information may be converted into a coordinate system in the map data.

[0078] Step 2013: construct target map data based on the converted first parking space information.

[0079] After the coordinate conversion of the first parking space information is completed, the target map data may be constructed based on the converted first parking space information.

[0080] Step 202, when the vehicle passes the target parking space, obtaining second parking space information collected for the target parking space; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems;

[0081] When the vehicle passes the target parking space, the second parking space information collected for the target parking space can be obtained, wherein the second parking space information includes corner point information, direction information, and parking space attributes (such as a parallel parking space or a vertical parking space, whether the parking space is occupied, whether there are obstacles in the parking space, etc.). In the embodiment of the present invention, there are no excessive restrictions on the second parking space information.

[0082] Step 203, determining deviation information of the target parking space based on the first parking space information and the second parking space information;

[0083] After acquiring the first parking space information and the second parking space information, the deviation information between the first parking space information and the second parking space information can be determined. The deviation information can be for the target parking space. Thus, the deviation information can be used to determine whether the first parking space information matches the second parking space information, or to determine whether the first parking space information is the parking space information collected for the target parking space.

[0084] The deviation information may include distance deviation, direction deviation, and projection deviation.

[0085] In an embodiment of the present invention, the deviation information includes a distance deviation, and step 203 may specifically include:

[0086] The distance deviation of the target parking space is determined according to the first corner point information of the first parking space information and the second corner point information in the second parking space information corresponding to the first corner point information.

[0087] In practical applications, the distance deviation can be determined through the corner point information of the first parking space information and the second parking space information. Specifically, the first parking space information may include the first corner point information, and the first corner point information may include the corner point coordinates of the first corner point. The second parking space information may include the second corner point information, and the second corner point information may include the corner point coordinates of the second corner point. There is a corresponding relationship between the first corner point information and the second corner point information (for example, the first corner point information is the NF corner point of the parking space). Therefore, the distance deviation of the target parking space can be obtained by calculating the distance between the corner point coordinates of the first corner point and the corner point coordinates of the second corner point.

[0088] For example, the parking space for vehicle recognition is represented by four corner points as follows Figure 2b As shown, NF and NR represent the two corner points at the front end of the parking space, FF and FR represent the two corner points at the rear end of the parking space, and the parking space direction is defined as the direction of the line from the center point of the parking space to the front corner point.

[0089] In another embodiment of the present invention, the deviation information includes a direction deviation, and step 203 may specifically include:

[0090] A direction deviation of the target parking space is determined according to the first direction information of the first parking space information and the second direction information of the second parking space information.

[0091] In practical applications, the collected parking space information may also include direction information, thereby determining the first direction information of the first parking space information and the second direction information of the second parking space information, and further determining the direction deviation of the target parking space through the first direction information and the second direction information.

[0092] In another embodiment of the present invention, the deviation information includes projection deviation, and step 203 may specifically include the following sub-steps:

[0093] Sub-step 2031, determining first ratio information of the overlapped line segment obtained by projection relative to the second line segment according to the projection of the first corner point information and the third corner point information of the first parking space information onto the second line segment formed by the second corner point information and the fourth corner point information of the second parking space information;

[0094] In practical applications, the first parking space information may include first corner point information and third corner point information, and the first corner point information and the third corner point information are corner points at the same end, such as the front corner point or the rear corner point in a certain parking space. The second parking space information may include second corner point information and fourth corner point information, and the second corner point information and the fourth corner point information are corner points at the same end, such as the front corner point or the rear corner point of the target parking space.

[0095] The first corner point information and the third corner point information may form a first line segment, and the second corner point information and the fourth corner point information may form a second line segment.

[0096] The projection deviation can calculate the overlap degree of the front corner point line. For parallel parking spaces and vertical parking spaces, mismatching may occur if this projection deviation is not added. The first corner point information and the third corner point information are projected onto the second line segment respectively to obtain the first overlapped line segment, thereby obtaining the first ratio information of the first overlapped line segment relative to the second line segment.

[0097] Sub-step 2032, determining second ratio information of the projected coincident line segment relative to the first line segment based on the projection of the second corner point information and the fourth corner point information on the first line segment formed by the first corner point information and the third corner point information;

[0098] The second corner point information and the first corner point information are respectively projected onto the first line segment to obtain a second coincident line segment, thereby obtaining first ratio information of the second coincident line segment relative to the first line segment.

[0099] Sub-step 2033, determining the projection deviation of the target parking space according to the first ratio information and the second ratio information.

[0100] After the first proportion information and the second proportion information are obtained, the projection deviation of the target parking space may be determined according to the first proportion information and the second proportion information.

[0101] For example, the following combination Figure 2c Explain the calculation process of projection deviation:

[0102] (1) Calculate the lengths of the line segments between the front corner points of the FSD and AVM parking spaces, Len_fsd and Len_avm, calculate the overlap length overlap_len1 of the line segment projected from the front corner point of the FSD parking space to the front corner point of the AVM parking space, and calculate the overlap length overlap_len2 of the line segment projected from the front corner point of the AVM parking space to the front corner point of the FSD parking space.

[0103] (2) Calculate the ratio Rate1 (i.e., first ratio information) of the overlap length of the FSD to AVM projection and the length of the line segment of the front corner point of the AVM (i.e., the length of the second line segment).

[0104] Rate1 = overlap_len1 / Len_avm

[0105] Calculate the ratio Rate2 (i.e., the second ratio information) of the overlap length of the AVM to FSD projection and the length of the FSD front corner point line segment (i.e., the length of the first limit).

[0106] Rate2 = overlap_len2 / Len_fsd

[0107] In an embodiment of the present invention, before step 203, the following steps may also be included:

[0108] Step S11, determining whether the second parking space information is valid parking space information;

[0109] In practical applications, in order to ensure the accuracy of data in the map, before writing the data, it is possible to first confirm whether the data to be written is valid data. Only when the data is valid data, the data is written into the map.

[0110] After the second parking space information is obtained, it can be determined whether the second parking space information is valid by comparing it with the parking space information measured last time.

[0111] Specifically, when the accuracy mark directly output by the parking space recognition system of the AVM is the best, it can be determined that the second parking space information is valid parking space information; at the same time, it can also be determined whether the second parking space information is valid parking space information by whether the NF (a front corner point in the parking space information) distance of the twice recognized parking space information is greater than a preset value (such as 1.5m); it can also be determined whether the XY coordinates of the parking space NF are greater than 0 to determine whether the second parking space information is valid parking space information.

[0112] Step S12: when it is determined that the second parking space information is valid parking space information, the coordinates of the corner points of the second parking space information are converted according to the map coordinate system of the target map data.

[0113] When determining that the second parking space information is valid parking space information, in order to conveniently write the second parking space information into the map data, the coordinates of the corner points of the second parking space information may be converted into a coordinate system in the map data.

[0114] Step 204, determining whether the deviation information matches the preset deviation information;

[0115] The preset deviation information is a limited range of the deviation. Different types of deviation information correspond to different preset deviation information. After determining the deviation information, the preset deviation information of the corresponding category can be obtained to determine whether the deviation information matches the preset deviation information, so as to determine whether the first parking space information matches the second parking space information.

[0116] For example, with respect to distance deviation, the recognition results of the corner point positions of the same parking space should not differ too much. If the difference is too large, it is considered that the parking spaces recognized twice are not the same. The preset distance deviation can be determined based on the maximum recognition error (such as 0.8m) in the two parking space recognition systems. Usually, the preset distance deviation can be set to be smaller than this value.

[0117] As for the direction deviation, the direction deviation can be obtained by directly subtracting the directions of the two parking spaces and taking the absolute value. The preset deviation information can be determined based on the direction deviation calculated under the maximum recognition error of the two parking space recognition systems. The direction deviation can be used to quickly filter out the parking spaces that do not meet the conditions.

[0118] For projection deviation, the preset deviation information can be determined based on the recognition deviation of the parking space recognition system, the type of parking space, the size and specifications of the parking space, and other attributes. For example, the length of the front corner point line of a vertical parking space is approximately 2.4m, and the length of the front corner point line of a parallel parking space is approximately 4.8m. The ratio is approximately 0.5. A more stringent value must be taken for matching, so the preset deviation information can be set to a value greater than the ratio.

[0119] Step 205, when the deviation information matches the preset deviation information, obtaining fused parking space information based on the first parking space information and the second parking space information;

[0120] When the deviation information matches the preset deviation information, it is determined that the first parking space information matches the second parking space information, that is, the first parking space information is also parking space information collected for the target parking space.

[0121] Therefore, weighted fusion can be performed based on the first parking space information and the second parking space information to obtain fused parking space information, wherein weighted fusion refers to weighted fusion of the corner point coordinates of the parking space, such as NF=(NF_AVM+NF_FSD) / 2.

[0122] Step 206: Update the first parking space information in the target map data according to the fused parking space information.

[0123] After weighted fusion, the first parking space information in the target map data may be updated according to the fused parking space information, so that the target parking space information is more accurate.

[0124] In one embodiment of the present invention, it also includes:

[0125] When the deviation information does not match the preset deviation information, the second parking space information is written into the target map data to update the target map data.

[0126] In actual applications, when the deviation information does not match the preset deviation information, the first parking space information is not the parking space information collected for the target parking space, that is, only one parking space recognition system recognizes the target parking space. In order to ensure the integrity of the map information, the second parking space information of the newly added target parking space can be directly written into the target map data to complete the target map data.

[0127] In an embodiment of the present invention, a vehicle has at least two parking space recognition systems. During the driving process of the vehicle, first parking space information and second parking space information are collected through different parking space recognition systems, and then based on the first parking space information and the second parking space information, deviation information of the target parking space is determined, so that it can be determined whether the first parking space information matches the second parking space information according to the deviation information, and then the parking spaces are fused when they match, and the target map data constructed based on the first parking space information is updated, thereby realizing the collection of parking space information based on the two parking space recognition systems, the fusion of parking spaces and the updating of map data, and ensuring that there are parking space elements in the map when one of the parking space recognition systems misses recognition or even fails, thereby increasing the robustness of parking space recognition and making real-time map data more accurate.

[0128] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0129] Reference Figure 3 , shows a schematic diagram of the structure of a map updating device provided by an embodiment of the present invention, which may specifically include the following modules:

[0130] The target map data construction module 301 is used to obtain the first parking space information collected by the vehicle when the vehicle does not pass the target parking space, and construct the target map data based on the first parking space information;

[0131] A second parking space information acquisition module 302 is used to acquire second parking space information collected for the target parking space when the vehicle passes through the target parking space; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems;

[0132] A deviation information determining module 303, configured to determine deviation information of the target parking space based on the first parking space information and the second parking space information;

[0133] The target map data updating module 304 is used to update the target map data according to the deviation information.

[0134] In one embodiment of the present invention, the target map data updating module 304 may include:

[0135] A matching judgment submodule, used to judge whether the deviation information matches the preset deviation information;

[0136] a fusion parking space submodule, configured to obtain fusion parking space information based on the first parking space information and the second parking space information when the deviation information matches the preset deviation information;

[0137] The first updating submodule is used to update the first parking space information in the target map data according to the fused parking space information.

[0138] In one embodiment of the present invention, the target map data updating module 304 may further include:

[0139] The second updating submodule is used for writing the second parking space information into the target map data to update the target map data when the deviation information does not match the preset deviation information.

[0140] In an embodiment of the present invention, the deviation information includes a distance deviation, and the deviation information determination module 303 may include:

[0141] The distance deviation determining submodule is used to determine the distance deviation of the target parking space according to the first corner point information of the first parking space information and the second corner point information corresponding to the first corner point information in the second parking space information.

[0142] In an embodiment of the present invention, the deviation information includes a direction deviation, and the deviation information determination module 303 may include:

[0143] The direction deviation determining submodule is used to determine the direction deviation of the target parking space according to the first direction information of the first parking space information and the second direction information of the second parking space information.

[0144] In one embodiment of the present invention, the deviation information includes projection deviation, and the deviation information determination module 303 may include:

[0145] A first ratio information determination submodule, configured to determine first ratio information of a coincident line segment obtained by projection relative to the second line segment based on a projection of the first corner point information and the third corner point information of the first parking space information on a second line segment formed by the second corner point information and the fourth corner point information of the second parking space information;

[0146] A second ratio information determination submodule, configured to determine, based on the projections of the second corner point information and the fourth corner point information on the first line segment formed by the first corner point information and the third corner point information, second ratio information of the coincident line segment obtained by the projection relative to the first line segment;

[0147] The projection deviation determining submodule is used to determine the projection deviation of the target parking space according to the first proportion information and the second proportion information.

[0148] In one embodiment of the present invention, the target map data construction module 301 may include:

[0149] A validity judgment submodule, used to judge whether the first parking space information is valid parking space information;

[0150] A coordinate system conversion submodule, configured to convert the coordinates of the corner points of the first parking space information according to a map coordinate system when determining that the first parking space information is valid parking space information;

[0151] The map construction submodule is used to construct target map data based on the converted first parking space information.

[0152] In one embodiment of the present invention, it also includes:

[0153] A validity judgment module, used for judging whether the second parking space information is valid parking space information;

[0154] A coordinate system conversion module is used to convert the coordinates of the corner points of the second parking space information according to the map coordinate system of the target map data when determining that the second parking space information is valid parking space information.

[0155] In one embodiment of the present invention, the first parking space information is parking space information collected by a parking space recognition system for side front parking space detection, and the second parking space information is parking space information collected by a parking space recognition system for surround view parking space detection.

[0156] In an embodiment of the present invention, there are at least two parking space recognition systems for a vehicle. During the driving process of the vehicle, first parking space information and second parking space information are collected through different parking space recognition systems, and then based on the first parking space information and the second parking space information, deviation information of the target parking space is determined. Therefore, according to the deviation information, target map data constructed based on the first parking space information can be updated, thereby realizing the collection of parking space information based on the two parking space recognition systems and updating of map data. In addition, even if one of the parking space recognition systems misses recognition or even fails, it can still ensure that there are parking space elements in the map, thereby increasing the robustness of parking space recognition and making real-time map data more accurate.

[0157] An embodiment of the present invention further provides a vehicle, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the above map updating method is implemented.

[0158] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above map updating method is implemented.

[0159] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0160] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0161] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product 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 codes.

[0162] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0165] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0166] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0167] The above is a detailed introduction to a map updating method and device provided. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for updating a map, characterized in that: The method comprises: When the vehicle has not passed the target parking space, the first parking space information collected by the side front parking space detection FSD of the vehicle for the target parking space is obtained, and the first parking space information is determined to be valid according to the distance between the front corner points of the first parking space information identified twice by the adjacent side front parking space detection FSD and a preset value; When determining that the first parking space information is valid parking space information, converting the coordinates of the corner points of the first parking space information according to a map coordinate system; Constructing target map data based on the converted first parking space information; When the vehicle passes the target parking space, second parking space information collected for the target parking space is obtained; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems; Determining deviation information of the target parking space based on the first parking space information and the second parking space information; The target map data is updated according to the deviation information.

2. The method according to claim 1, characterized in that The updating of the target map data according to the deviation information includes: Determining whether the deviation information matches preset deviation information; When the deviation information matches the preset deviation information, obtaining fused parking space information based on the first parking space information and the second parking space information; According to the fused parking space information, the first parking space information in the target map data is updated.

3. The method according to claim 2, characterized in that Also includes: When the deviation information does not match the preset deviation information, the second parking space information is written into the target map data to update the target map data.

4. The method according to claim 1, 2 or 3, characterized in that: The deviation information includes a distance deviation, and determining the deviation information of the target parking space based on the first parking space information and the second parking space information includes: The distance deviation of the target parking space is determined according to the first corner point information of the first parking space information and the second corner point information corresponding to the first corner point information in the second parking space information.

5. The method according to claim 1, 2 or 3, characterized in that: The deviation information includes a direction deviation, and determining the deviation information of the target parking space based on the first parking space information and the second parking space information includes: The direction deviation of the target parking space is determined according to the first direction information of the first parking space information and the second direction information of the second parking space information.

6. The method according to claim 1, 2 or 3, characterized in that: The deviation information includes a projection deviation, and determining the deviation information of the target parking space based on the first parking space information and the second parking space information includes: Determine first ratio information of a coincident line segment obtained by projection relative to the second line segment according to a projection of the first corner point information and the third corner point information of the first parking space information on a second line segment formed by the second corner point information and the fourth corner point information of the second parking space information; Determine, according to the projection of the second corner point information and the fourth corner point information on the first line segment formed by the first corner point information and the third corner point information, second ratio information of the overlapped line segment obtained by the projection relative to the first line segment; A projection deviation of the target parking space is determined according to the first ratio information and the second ratio information.

7. The method according to claim 1, 2 or 3, characterized in that: Before determining the deviation information of the target parking space based on the first parking space information and the second parking space information, the method further includes: Determining whether the second parking space information is valid parking space information; When it is determined that the second parking space information is valid parking space information, the coordinates of the corner points of the second parking space information are converted according to the map coordinate system of the target map data.

8. The method according to claim 1, 2 or 3, characterized in that: The second parking space information is parking space information collected by a parking space recognition system for surround parking space detection.

9. A map updating device, characterized in that: The device comprises: A target map data construction module, used for obtaining first parking space information collected by the front side parking space detection FSD of the vehicle for the target parking space when the vehicle has not passed the target parking space, and constructing target map data based on the first parking space information; A second parking space information acquisition module, configured to acquire second parking space information collected for the target parking space when the vehicle passes through the target parking space; wherein the vehicle has at least two parking space recognition systems, and the first parking space information and the second parking space information are collected by different parking space recognition systems; a deviation information determining module, configured to determine deviation information of the target parking space based on the first parking space information and the second parking space information; A target map data updating module, used for updating the target map data according to the deviation information; Among them, the target map data construction module includes: A validity judgment submodule, used to judge whether the first parking space information is valid parking space information according to the distance between the front corner points of the first parking space information identified twice by the adjacent side front parking space detection FSD and a preset value; A coordinate system conversion submodule, configured to convert the coordinates of the corner points of the first parking space information according to a map coordinate system when determining that the first parking space information is valid parking space information; The map construction submodule is used to construct target map data based on the converted first parking space information.

10. A vehicle, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the map updating method according to any one of claims 1 to 8 when executed by the processor.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the map updating method according to any one of claims 1 to 8 is implemented.

Images