A map building method, apparatus and vehicle

Abstract

This application provides a map construction method, apparatus, and vehicle. The method includes: acquiring map information, the map information including a first set of parking spaces, the first set of parking spaces including one or more parking spaces; performing a forward rotation transformation on the one or more parking spaces to obtain a first bounding box, the first bounding box including the one or more parking spaces; arranging the one or more parking spaces according to the size of the first bounding box and a preset parking space size; and performing a reverse rotation transformation on the arranged one or more parking spaces to obtain the repaired one or more parking spaces. This application can be applied to intelligent vehicles or electric vehicles, helping to improve the efficiency of repairing parking spaces in maps, saving labor costs, and also helping to improve the intelligence level of vehicles.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicles, and more specifically, to a map building method, apparatus, and vehicle. Background Technology

[0002] Parking spaces are an important component of parking lot maps. Currently, parking spaces on the parking lot map can be repaired offline. However, this method is time-consuming and labor-intensive. Summary of the Invention

[0003] This application provides a map building method, apparatus, and vehicle, which helps improve the efficiency of repairing parking spaces in a map, saves labor costs, and enhances the intelligence of the vehicle.

[0004] The term "vehicle" in this application can be used in a broad sense, including transportation vehicles (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of this application do not specifically limit the type of vehicle.

[0005] In a first aspect, a map construction method is provided, the method comprising: acquiring map information, the map information including a first set of parking spaces, the first set of parking spaces including one or more parking spaces; performing a forward rotation transformation on the one or more parking spaces to obtain a first bounding box, the first bounding box being determined by a rectangle formed by the outermost points of the one or more parking spaces; arranging the one or more parking spaces according to the size of the first bounding box and a preset parking space size; and performing a reverse rotation transformation on the arranged one or more parking spaces to obtain the repaired one or more parking spaces.

[0006] In this embodiment, an outer frame is obtained by performing a forward rotation transformation on one or more parking spaces. The parking spaces are then arranged according to the size of the outer frame and preset parking space sizes. After a reverse rotation transformation, the repaired parking spaces are obtained. This eliminates the need for offline repair of parking spaces on the map, saving labor costs and improving the intelligence level of vehicles.

[0007] In some possible implementations, the method further includes: determining a transformation angle based on the orientation angle of one or more parking spaces, wherein performing a positive rotation transformation on the one or more parking spaces includes: performing a positive rotation transformation on the one or more parking spaces based on the transformation angle.

[0008] In some possible implementations, the one or more parking spaces are rotated in a positive direction according to the transformation angle, including: rotating in a positive direction around a preset point according to the transformation angle.

[0009] In some possible implementations, the preset point can be the origin of the Odom coordinate system or other points in the Odom coordinate system.

[0010] In some possible implementations, the preset point can also be a point in other coordinate systems (e.g., vehicle coordinate system).

[0011] In some possible implementations, the first bounding box is formed by one or more of the outermost points of the first parking space set.

[0012] In some possible implementations, the preset parking space size is the size after weighted average of the sizes of all parking spaces in the map; or, the preset parking space size is the size after weighted average of the sizes of one or more parking spaces; or, the length and width of the parking space in the preset parking space size are preset values ​​(e.g., the length and width of a standard parking space).

[0013] In some possible implementations, when the one or more parking spaces are multiple parking spaces, the distance between the multiple parking spaces is less than or equal to a preset distance, and / or the difference between the orientation angles of every two parking spaces is less than or equal to a preset angle.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, arranging one or more parking spaces according to the size of the first outer frame and the preset parking space size includes: determining the number of rows and columns of parking spaces included in the first outer frame according to the size of the first outer frame and the preset parking space size; and arranging the one or more parking spaces according to the number of rows and columns of parking spaces included in the first outer frame.

[0015] In this embodiment, the number of rows and columns of parking spaces in the first outer frame can be determined by the size of the first outer frame and the preset parking space size. The parking spaces can then be rearranged according to the number of rows and columns to obtain neatly arranged parking spaces. This eliminates the need for offline repair of parking spaces in the map, thus saving manpower costs. At the same time, it helps improve the aesthetics and accuracy of the constructed map and also helps improve the intelligence level of vehicles.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the map information further includes a second set of parking spaces, which includes one or more parking spaces. The method further includes: performing a forward rotation transformation on one or more parking spaces in the second set of parking spaces to obtain a second bounding box; and when the first bounding box and the second bounding box overlap, adjusting the first bounding box and / or the second bounding box so that the first bounding box and the second bounding box do not overlap.

[0017] In this embodiment, when there is overlap between the first outer frame and the second outer frame, the first outer frame and / or the second outer frame can be adjusted so that they do not overlap. This helps to avoid overlapping portions between the repaired parking spaces and improves the aesthetics of the constructed map.

[0018] In some possible implementations, when the first outer frame and the second outer frame overlap, the first outer frame and / or the second outer frame are adjusted, including: when the first outer frame and the second outer frame overlap and the number of visually detected parking spaces in the first outer frame is greater than the number of visually detected parking spaces in the second outer frame, the second outer frame is adjusted.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: aligning the first outer frame and the second outer frame along a preset direction.

[0020] In this embodiment, when the first and second bounding boxes are not aligned along a preset direction, they can be aligned along the preset direction. This helps ensure that the parking spaces in the repaired first and second parking space sets are aligned along the preset direction. The parking spaces obtained after the inverse rotation transformation are also aligned along a certain direction, which helps improve the aesthetics of the constructed map.

[0021] In some possible implementations, the preset direction is the first side of the first outer frame, or the preset direction is the second side of the second outer frame.

[0022] In some possible implementations, when the number of visually detected parking spaces in the first outer frame is greater than the number of visually detected parking spaces in the second outer frame, the preset direction can be determined as the first side of the first outer frame.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, before obtaining the repaired one or more parking spaces, the method further includes: determining that the repaired one or more parking spaces match the original one or more parking spaces.

[0024] In this embodiment of the application, one or more parking spaces after repair can be matched with one or more parking spaces before repair. This can exclude parking spaces that do not exist in the actual scene and help improve the accuracy of the constructed map.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when the opening direction of at least some of the parking spaces does not correspond to the direction of the road, adjusting the opening direction of the at least some parking spaces to correspond to the direction of the road.

[0026] In this embodiment of the application, when the openings of at least some of the parking spaces do not correspond to the road direction, the opening direction of those at least some parking spaces can be adjusted to correspond to the road direction. This ensures that the openings of the repaired parking spaces all correspond to the road direction, thus improving the aesthetics of the constructed map.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: aligning associated elements in one or more parking spaces, the associated elements including parking locks and / or wheel chocks.

[0028] In this embodiment of the application, when the one or more parking spaces include related elements, the related elements can be aligned, which helps to improve the aesthetics of the constructed map.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when the one or more parking spaces are located between two obstacles, adjusting the size of the one or more parking spaces along a first direction according to the size between the two obstacles, the first direction corresponding to the direction of the line connecting the two obstacles.

[0030] In this embodiment of the application, after repairing one or more parking spaces, the dimensions of one or more parking spaces along the first direction can be further corrected according to the distance between two obstacles. This can make the dimensions of the repaired parking spaces more accurate and also help to further improve the accuracy of the constructed map.

[0031] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: obtaining the first parking space set from the map information according to the nearest neighbor algorithm or the disjoint-set data structure algorithm.

[0032] In this embodiment of the application, the first parking space set can be obtained by using the nearest neighbor algorithm or the disjoint set algorithm, which helps to improve the accuracy of repairing one or more parking spaces in the first parking space set.

[0033] In conjunction with the first aspect, in some implementations of the first aspect, the acquisition of map information includes: acquiring the map information during the process of detecting automatic parking of a vehicle.

[0034] In this embodiment, the map information can be obtained based on data collected by sensors during automatic parking. The original map information may contain misaligned or disordered parking spaces. The map construction method described in this embodiment can correct the parking spaces in the map information in real time, resulting in a neatly arranged and aesthetically pleasing map, which helps improve the user experience and also enhances the vehicle's intelligence.

[0035] In some possible implementations, the acquisition of map information includes: acquiring the map information of a parking lot when a vehicle is detected to be entering a parking lot for the first time.

[0036] Alternatively, if a vehicle is detected entering a parking lot for the first time before the map of that parking lot is fully constructed, the vehicle can continue to build a complete parking lot map based on the data collected by the sensors when it enters the parking lot a second time, and the parking spaces in the parking lot map can be repaired.

[0037] In some possible implementations, the method further includes controlling an in-vehicle display screen to show the map information, which includes one or more repaired parking spaces.

[0038] Secondly, a map building apparatus is provided, comprising: an acquisition unit for acquiring map information, the map information including a first set of parking spaces, the first set of parking spaces including one or more parking spaces; a transformation unit for performing a forward rotation transformation on the one or more parking spaces to obtain a first bounding box, the first bounding box being determined by a rectangle formed by the outermost points of the one or more parking spaces; an arrangement unit for arranging the one or more parking spaces according to the size of the first bounding box and a preset parking space size; the transformation unit is further configured to perform a reverse rotation transformation on the arranged one or more parking spaces to obtain a repaired one or more parking spaces.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the arrangement unit is used to: determine the number of rows and columns of parking spaces included in the first outer frame according to the size of the first outer frame and the preset parking space size; and arrange the one or more parking spaces according to the number of rows and columns of parking spaces included in the first outer frame.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the map information further includes a second parking space set, which includes one or more parking spaces. The transformation unit is further configured to perform a forward rotation transformation on one or more parking spaces in the second parking space set to obtain a second bounding box. The device further includes a first adjustment unit, configured to adjust the first bounding box and / or the second bounding box when the first bounding box and the second bounding box overlap, so that the first bounding box and the second bounding box do not overlap.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes: a first alignment unit for aligning the first outer frame and the second outer frame along a preset direction.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the apparatus further includes: a determining unit, configured to determine, before obtaining the repaired one or more parking spaces, that the repaired one or more parking spaces match the original one or more parking spaces.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes: a second adjustment unit, used to adjust the opening direction of at least some of the parking spaces to correspond to the direction of the road when the opening direction of at least some of the parking spaces does not correspond to the direction of the road.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes: a second alignment unit for aligning associated elements in the one or more parking spaces, the associated elements including parking locks and / or wheel chocks.

[0045] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes: a third adjustment unit, configured to adjust the size of the one or more parking spaces along a first direction according to the size between the two obstacles when the one or more parking spaces are located between two obstacles, the first direction corresponding to the direction of the line connecting the two obstacles.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the acquisition unit is further configured to: acquire the first parking space set from the map information according to the nearest neighbor algorithm or the disjoint-set data structure algorithm.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the acquisition unit is used to: acquire the map information during the process of detecting automatic parking of the vehicle.

[0048] Thirdly, a map building apparatus is provided, the apparatus including a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit to cause the apparatus to perform any of the possible methods in the first aspect.

[0049] Optionally, the processing unit may include at least one processor, and the storage unit may be a memory, wherein the memory may be an on-chip storage unit (e.g., register, cache, etc.) or an off-chip storage unit located in the vehicle (e.g., read-only memory, random access memory, etc.).

[0050] Fourthly, a map building system is provided, which includes one or more sensors and a computing platform, the computing platform including the apparatus described in any one of the second or third aspects above.

[0051] Fifthly, a vehicle is provided that includes the device described in either the second or third aspect above, or the system described in the fourth aspect above.

[0052] Sixthly, a server is provided that includes the apparatus described in either the second or third aspect above.

[0053] In a seventh aspect, a computer program product is provided, the computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform any of the possible methods described in the first aspect above.

[0054] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or packaged separately from the processor. This application embodiment does not specifically limit this.

[0055] Eighthly, a computer-readable medium is provided that stores program code, which, when run on a computer, causes the computer to perform any of the possible methods described in the first aspect above.

[0056] Ninthly, embodiments of this application provide a chip system including circuitry for performing any of the possible methods described in the first aspect above. Attached Figure Description

[0057] Figure 1 This is a functional block diagram of the vehicle provided in the embodiments of this application.

[0058] Figure 2 This is the parking space map before repair provided in the embodiments of this application.

[0059] Figure 3 This is a schematic flowchart of the map construction method provided in the embodiments of this application.

[0060] Figure 4 This is a schematic diagram of five local clusters provided in the embodiments of this application.

[0061] Figure 5 This is a schematic diagram of local clustering a provided in this application after forward and inverse rotation transformations.

[0062] Figure 6 This is a schematic diagram of removing overlap between outer frame 1 and outer frame 2 provided in an embodiment of this application.

[0063] Figure 7 This is a schematic diagram illustrating the alignment of five outer frames according to an embodiment of this application.

[0064] Figure 8 This is a schematic diagram illustrating the matching of the reverse-rotated parking space with the original parking space, as provided in an embodiment of this application.

[0065] Figure 9 This is a schematic diagram of the repaired parking lot map provided in the embodiments of this application.

[0066] Figure 10 This is another illustrative flowchart of the map construction method provided in the embodiments of this application.

[0067] Figure 11 This is a schematic block diagram of the map building apparatus provided in the embodiments of this application. Detailed Implementation

[0068] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0069] The prefixes such as "first" and "second" used in this application embodiment are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not constitute unnecessary restrictions due to the use of such prefixes. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0070] Figure 1 This is a functional block diagram of a vehicle 100 provided in an embodiment of this application. The vehicle 100 may include a sensing system 120, a display device 130, and a computing platform 150. The sensing system 120 may include one or more sensors for sensing information about the environment surrounding the vehicle 100. For example, the sensing system 120 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou Navigation Satellite System, or another positioning system. The sensing system 120 may also include one or more of the following: an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0071] Some or all of the functions of vehicle 100 can be controlled by computing platform 150. Computing platform 150 may include one or more processors, such as processors 151 to 15n (n being a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include memory for storing instructions, and some or all of the processors 151 to 15n can call the instructions in memory to implement the corresponding functions.

[0072] The in-cabin display devices 130 are mainly divided into two categories: the first is the in-vehicle display screen; the second is the projection display screen, such as the head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of the in-vehicle infotainment system. Multiple displays can be installed in the cabin, such as the digital instrument cluster display, the central control screen, the display screen in front of the front passenger (also known as the front-seat passenger), the display screen in front of the left rear passenger, the display screen in front of the right rear passenger, and even the car window can be used as a display screen. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device in front of the driver (such as the windshield). This reduces the driver's eye-shift time, avoids pupil changes caused by eye-shifting, and improves driving safety and comfort. Examples of HUDs include combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems. It should be understood that HUDs can also evolve into other types of systems as technology progresses, and this application does not limit them.

[0073] Figure 2 This illustrates a parking space map before repair, as provided in an embodiment of this application. This parking space map can be a parking space map determined by a parking space detection system and a positioning system, wherein the positioning system may include a Global Positioning System, an Inertial Measurement Unit, and a wheel odometer. Figure 2 As shown, when a vehicle enters a parking lot, it can collect a map of the parking lot through a camera outside the cabin while driving in the parking lot.

[0074] For example, a parking space detection system can acquire image information from external cameras. These cameras may include a front-view camera, a rear-view camera, and two side-view cameras (located on the left and right sides of the vehicle, respectively). These four cameras may also be equipped with fisheye lenses. The front-view camera, rear-view camera, the camera on the left side of the vehicle, and the camera on the right side of the vehicle can output image information from the front, rear, left, and right sides of the vehicle, respectively, to the parking space detection system. The parking space detection system can then use inverse perspective mapping (IPM) to synthesize the image information from the four cameras into a single IPM image.

[0075] Parking space detection systems can extract features from IPM images. For example, a parking space detection system can input an IPM image into a U-shaped (UNET) network for feature extraction. The UNET network outputs a semantic feature for each pixel in the IPM image. These semantic features include, but are not limited to, parking spaces converted from stationary vehicles, visually detected parking spaces, speed bumps, pillars, and other obstacles.

[0076] The parking spaces created by converting stationary vehicles can be understood as spaces generated from stationary vehicles parked on the ground. A parking space may or may not exist at the location where a stationary vehicle is parked. Visually detected parking spaces can be understood as parking spaces accurately captured by a camera device.

[0077] It should be understood that the process by which the parking space detection system outputs semantic features through IPM images can also be understood as the process by which the parking space detection system constructs a semantic layer.

[0078] After feature extraction from the IPM image, the parking space detection system can begin constructing a parking space map. The system determines the vehicle's position in a vehicle coordinate system using an IMU and wheel speed odometer. This position can be the vehicle's current location relative to its initial position upon entering the parking lot (e.g., the origin of the vehicle coordinate system). Alternatively, the system can determine the vehicle's absolute position in a world coordinate system using a Global Positioning System (GPS). Using GPS, IMU, and wheel speed odometer, a positioning layer can be constructed for the vehicle.

[0079] By matching the location layer and the semantic layer, the parking space detection system can construct a map of the parking lot. Figure 2 The parking map shown includes parking spaces converted from stationary vehicles and parking spaces detected by cameras (or visually detected parking spaces). It can be seen that the parking spaces converted from stationary vehicles and the visually detected parking spaces are misaligned and disordered. If a vehicle drives around the parking lot multiple times, there may also be overlapping parking spaces.

[0080] This application provides a map building method, apparatus, and vehicle. By collecting parking lot data online, it automatically aligns parking spaces, resulting in aesthetically pleasing alignment without requiring manual intervention. This improves the efficiency of parking space restoration, saves labor costs, and enhances vehicle intelligence. Furthermore, the restored parking lot map allows vehicles to perform automated parking (e.g., automated valet parking, AVP), improving the user's driving experience.

[0081] Figure 3A schematic flowchart of a map construction method 300 provided in an embodiment of this application is shown. This method 300 can be executed by a vehicle, or by the aforementioned computing platform, or by a system-on-a-chip (SOC) within the computing platform, or by a processor within the computing platform, or by a server. The method 300 includes:

[0082] S301 performs local clustering of the original parking spaces in the map information.

[0083] In one embodiment, the original parking spaces are clustered to obtain multiple local clusters, including: using the K-Nearest Neighbor (KNN) algorithm or a disjoint-set data structure to perform local clustering of the original parking spaces.

[0084] In one embodiment, the original parking space may include Figure 2 Parking spaces for stationary vehicles and visually detected parking spaces.

[0085] In one embodiment, parking spaces that meet one or more of the following conditions can be locally clustered:

[0086] (1) The distance between parking spaces is less than or equal to the preset distance (e.g., 0.5 meters);

[0087] (2) The parking spaces are roughly the same or opposite in orientation. For example, the difference in orientation angle between parking spaces is less than or equal to 10°.

[0088] For example, the orientation angle of a parking space can be the angle between the direction of the parking space opening and a preset direction (e.g., the horizontal rightward X-axis).

[0089] Figure 4 This diagram illustrates five local clusters provided in an embodiment of this application. Since the distance between parking spaces 4 and 5 is greater than 0.5 meters, and parking spaces 7 and 8 are separated by pillars, as are parking spaces 10 and 11, and parking spaces 13 and 14, parking spaces 1-16 can be respectively divided into local clusters 1, 2, 3, 4, and 5. Local cluster 1 includes parking spaces 1-4; local cluster 2 includes parking spaces 5-7; local cluster 3 includes parking spaces 8-10; local cluster 4 includes parking spaces 11-13; and local cluster 5 includes parking spaces 14-16.

[0090] S302 performs global clustering on multiple local clusters.

[0091] In one embodiment, the plurality of local clusters may be local clusters that satisfy preset conditions. For example, the difference in orientation angles among the local clusters is less than or equal to 10°.

[0092] The orientation angle of the above local clusters can be the weighted average of the orientation angles of multiple parking spaces in the local cluster. For example, if the orientation angle of parking space 1 is 81°, the orientation angle of parking space 2 is 81°, the orientation angle of parking space 3 is 81°, and the orientation angle of parking space 4 is 77° in local cluster 1, then the orientation angle of local cluster 1 is 80°.

[0093] S303 performs a weighted average of the orientation angle and parking space size of multiple local clusters.

[0094] For example, if the orientation angle of local cluster 1 is 80°, the orientation angle of local cluster 2 is 80°, the orientation angle of local cluster 3 is 83°, the orientation angle of local cluster 4 is 79°, and the orientation angle of local cluster 5 is 78°, then the orientation angle after weighted average is 80°.

[0095] For example, the dimensions of parking spaces 1 to 16 can be weighted and averaged. The weighted average dimension is 5.2 meters in the length direction and 2.3 meters in the width direction.

[0096] S304. Perform a forward rotation transformation on the parking spaces in each local cluster to obtain the bounding box (edge) of each local cluster.

[0097] S305 arranges the parking spaces in each local cluster according to the size of the outer frame and the weighted parking space size.

[0098] In one embodiment, the bounding box of the locally clustered parking spaces can be obtained by performing a forward rotation transformation. Based on the dimensions of the parking spaces obtained by weighting in S303, the number of rows and columns of parking spaces in the local cluster is determined. For example, the bounding box can have a certain number of rows and columns of parking spaces. Figure 5 The diagram shows a local cluster a undergoing both forward and inverse rotation transformations.

[0099] like Figure 5As shown in (a), taking the example of a 95° orientation angle obtained after global clustering of multiple local clusters in S303. All parking spaces in local cluster a are rotated around the Odom coordinate system (the global coordinate system of this map) and transformed (rotated 95° clockwise) to obtain bounding box 501. Bounding box 501 is a rectangle formed by the outermost points of multiple parking spaces in local cluster a. Bounding box 501 can be a rectangle with its center point O, a length of 11.2 meters, and a width of 5 meters. Since the weighted parking space calculated in S303 has a length of 5.2 meters and a width of 2.3 meters, dividing the length of bounding box 501 by the length of the weighted parking space yields 2.15, and dividing the width of bounding box 501 by the width of the weighted parking space yields 2.17. After rounding, bounding box 501 includes two rows and two columns of parking spaces.

[0100] The above description uses the bounding box 501 as an example, which is a rectangle formed by the outermost points of multiple parking spaces in local cluster a. The embodiments of this application are not limited to this.

[0101] For example, the outer bounding box 501 can also be a rectangle formed by multiplying the outermost points of multiple parking spaces in local cluster a by a preset multiple (e.g., 0.9 or 1.1).

[0102] For example, the outer frame 501 can also be a rectangle formed by extending the outermost points of multiple parking spaces in local cluster a by a preset length (e.g., both the length and width are extended outward by 0.1m).

[0103] For example, the outer frame 501 can also be a rectangle formed by extending the outermost points of multiple parking spaces in local cluster a by a preset length (e.g., both the length and width are extended inward by 0.1m).

[0104] like Figure 5 As shown in (b), after determining that the outer frame 501 includes two rows and two columns of parking spaces, the size of the outer frame 501 can be adjusted to obtain the outer frame 502. The center point of the outer frame 502 and the outer frame 501 can both be point O. The outer frame 502 is 10.4 meters long and 4.6 meters wide.

[0105] S306, the rearranged parking spaces are transformed by reverse rotation to obtain the repaired parking spaces.

[0106] The above inverse rotation transformation can also be called the anti-rotation transformation.

[0107] like Figure 5 As shown in (c), after obtaining the outer frame 502, the outer frame 502 can be rotated around the Odom system by a reverse rotation transformation (rotated 95° counterclockwise) to obtain the repaired parking space.

[0108] In one embodiment, when two adjacent bounding boxes overlap, at least a portion of the bounding boxes in the two bounding boxes are adjusted to remove the overlapping portion between the two bounding boxes.

[0109] Figure 6 This diagram illustrates the process of removing overlap between outer frame 1 and outer frame 2 according to an embodiment of this application. Figure 6 As shown, when there is an overlap between outer frame 1 and outer frame 2, at least one of the outer frames can be adjusted.

[0110] For example, you can keep outer box 2 stationary and move outer box 1 upwards until there is no overlap between outer box 1 and outer box 2.

[0111] For example, you can keep outer box 1 stationary and move outer box 2 down until there is no overlap between outer box 1 and outer box 2.

[0112] For example, you can move outer box 1 upwards and outer box 2 downwards until there is no overlap between outer box 1 and outer box 2.

[0113] In one embodiment, the weights of the parking spaces can be used to determine the adjustments to outer frame 1 and / or outer frame 2. For example, outer frame 1 may include 3 parking spaces, all of which are visually detected parking spaces, and outer frame 2 may include 3 parking spaces, all of which are converted parking spaces for stationary vehicles. In this case, the weights of the parking spaces in outer frame 1 can be set higher than the weights of the parking spaces in outer frame 2, thereby keeping outer frame 1 stationary while moving outer frame 2 downwards.

[0114] In one embodiment, the method further includes aligning the bounding boxes corresponding to the plurality of local clusters along a preset direction.

[0115] Figure 7 This illustration shows a schematic diagram of aligning five outer frames according to an embodiment of this application.

[0116] like Figure 7 As shown, when the distance difference between the right contour lines of outer boxes A, B, D, and E is less than a preset width (e.g., 0.5 meters), while the distance difference between the right contour line of outer box C and the right contour lines of outer boxes A, B, D, and E is greater than the preset width, the local cluster corresponding to outer box C can be considered as a local cluster that needs to be arranged separately, while the local clusters corresponding to outer boxes A, B, D, and E can be local clusters that need to be aligned.

[0117] In one embodiment, a certain outline of a certain bounding box can be selected as a reference line, and other bounding boxes can be aligned to the reference line; or, the reference line can be determined based on the deviation between the corresponding outlines of multiple bounding boxes; or, a certain preset direction can be selected as the reference line, and multiple bounding boxes can all be aligned to the preset direction.

[0118] For example, if the weight of a parking space in the local cluster corresponding to bounding box A is greater than the weight of a parking space in the local cluster corresponding to other bounding boxes, then the rightmost outline of bounding box A can be used as the baseline. For instance, using the rightmost outline of bounding box A as the baseline, the right outlines of bounding boxes B, D, and E are all aligned with this baseline.

[0119] In one embodiment, parking spaces are arranged in the outer frame according to the weighted parking space size, and the parking spaces after inverse rotation transformation are matched with the original parking spaces.

[0120] Figure 8 This illustration shows a schematic diagram of matching the reverse-rotated parking space with the original parking space, as provided in an embodiment of this application.

[0121] For example, the original parking spaces 1-5 are detected by the parking space detection and positioning system, but no parking space exists in area 1. After the above inverse rotation transformation, the repaired parking spaces 6-11 are obtained. Since the distance between the center point of parking space 6 and the center point of any of the original parking spaces 1-5 is greater than a preset distance (e.g., 2 meters), it can be considered that there is actually no parking space at parking space 6. The distance between the center point of the repaired parking space 7 and the center point of the original parking space 1 is less than the preset distance, so it can be considered that the repaired parking space 7 matches the original parking space 1. The distance between the center point of the repaired parking space 8 and the center point of the original parking space 2 is less than the preset distance, so it can be considered that the repaired parking space 8 matches the original parking space 2. The distance between the center point of the repaired parking space 9 and the center point of the original parking space 3 is less than the preset distance, so it can be considered that the repaired parking space 9 matches the original parking space 3. The distance between the center point of the repaired parking space 10 and the center point of the original parking space 4 is less than the preset distance, so it can be considered that the repaired parking space 10 matches the original parking space 4. If the distance between the center point of the repaired parking space 11 and the center point of the original parking space 5 is less than the preset distance, then the repaired parking space 11 and the original parking space 5 can be considered to be a match.

[0122] After matching, the final repaired parking space map can be obtained.

[0123] In one embodiment, the method 300 further includes: when the size of one or more parking spaces between two adjacent obstacles in the repaired parking map is greater than the size between the two obstacles in a first direction (e.g., along the line connecting the two obstacles), the size of the one or more parking spaces in the first direction is corrected according to the distance between the two obstacles.

[0124] For example, S303 specifies the width of a parking space as 2.3 meters. In the corrected parking space map, there are two adjacent pillars, with three parking spaces between them. However, if a camera or lidar detects that the distance between the two pillars is 6.3 meters, then the width of the parking space between the two pillars can be adjusted from 2.3 meters to 2.1 meters.

[0125] In one embodiment, the method 300 further includes: deleting abnormal parking spaces that are far from the road.

[0126] The above-mentioned abnormal parking spaces can refer to parking spaces that are not accessible by road or that vehicles cannot park in.

[0127] In one embodiment, the method 300 further includes: adjusting the opening direction of all parking spaces to face the actual road.

[0128] In one embodiment, the method 300 further includes aligning associated elements in the parking space.

[0129] For example, if the parking space includes related elements such as wheel chocks and parking locks (which can be elements at the four corners), these related elements can be arranged in fixed positions within the parking space.

[0130] For example, the wheel chocks are located in the middle of the parking space, and the parking lock is located about 4 / 5 of the way back in the parking space, with the opening direction consistent with the parking space. This allows for the alignment of related elements, further enhancing the aesthetics of the parking lot map.

[0131] Figure 9 A schematic diagram of the repaired parking lot map provided in this application embodiment is shown. It can be seen that the orientation angles of local parking spaces remain consistent and their boundaries are aligned. The openings of all parking spaces globally face the road. If there are related elements such as parking locks or wheel chocks, they can be arranged in a fixed position within the parking space, maintaining consistency with the alignment of the parking space.

[0132] Figure 10A schematic flowchart of a map construction method 1000 provided in an embodiment of this application is shown. This method 1000 can be executed by a vehicle, or by a computing platform in the vehicle, or by a System-on-a-Chip (SoC) in the computing platform, or by a processor in the computing platform, or by a server. Figure 10 As shown, the method 1000 includes:

[0133] S1010, Obtain map information, which includes a first set of parking spaces, which includes one or more parking spaces.

[0134] In one embodiment, acquiring map information includes: acquiring the map information based on data collected by the vehicle's sensors.

[0135] In one embodiment, acquiring map information includes: acquiring map information based on data collected by the vehicle's sensors during the automatic parking process.

[0136] For example, the one or more parking spaces may include the parking spaces converted from stationary vehicles and / or visually detected parking spaces.

[0137] In one embodiment, when the one or more parking spaces are multiple parking spaces, the distance between any two adjacent parking spaces is less than or equal to a preset distance, and / or the difference between the orientation angles of any two parking spaces is less than or equal to a preset angle.

[0138] S1020, Perform a forward rotation transformation on the one or more parking spaces to obtain a first bounding box, which is determined by the rectangle formed by the outermost points of the one or more parking spaces.

[0139] In one embodiment, the first outer frame is formed by the outermost vertices of one or more parking spaces in the first parking space set.

[0140] In one embodiment, the first outer frame is obtained by extending a rectangular frame formed by the outermost vertices of one or more parking spaces in the first parking space set outward by a predetermined distance (e.g., extending both length and width outward by 0.1m), or by extending the rectangular frame inward by a predetermined distance (e.g., extending both length and width inward by 0.1m). Alternatively, it can be obtained by multiplying the size of the rectangular frame by a predetermined multiplier (e.g., 0.9 or 1.1).

[0141] For example, the one or more parking spaces are Figure 5 The parking spaces in the local cluster shown can have their first bounding box as the bounding box 501 mentioned above.

[0142] S1030, Arrange the one or more parking spaces according to the size of the first outer frame and the preset parking space size.

[0143] In one embodiment, arranging one or more parking spaces according to the size of the first outer frame and the preset parking space size includes: determining the number of rows and columns of parking spaces included in the first outer frame according to the size of the first outer frame and the preset parking space size; and arranging the one or more parking spaces according to the number of rows and columns of parking spaces included in the first outer frame.

[0144] The number of rows of parking spaces included in the first outer frame above can also be understood as the number of rows of parking spaces.

[0145] For example, such as Figure 5 As shown in (b), when the parking spaces in the outer frame are determined to be two rows and two columns based on the size of the outer frame 501 and the preset parking space size, the parking spaces in the outer frame can be rearranged.

[0146] For example, the preset parking space size is the size after weighted average of the sizes of all parking spaces in the map; or, the preset parking space size is the size after weighted average of the sizes of one or more parking spaces; or, the length and width of the parking space in the preset parking space size are preset values ​​(e.g., the length and width of a standard parking space).

[0147] S1040, the arranged one or more parking spaces are rotated in reverse to obtain the repaired one or more parking spaces.

[0148] For example, such as Figure 5 As shown in (c), the parking space in the outer frame 502 can be rotated around the Odom system by a reverse rotation transformation (rotating 95° counterclockwise) to obtain the repaired parking space.

[0149] In one embodiment, the method further includes: obtaining a second set of parking spaces, the second set of parking spaces including one or more parking spaces; performing a forward rotation transformation on one or more parking spaces in the second set of parking spaces to obtain a second bounding box; and when the first bounding box and the second bounding box overlap, adjusting the first bounding box and / or the second bounding box so that there is no overlap between the first bounding box and the second bounding box.

[0150] In one embodiment, the second outer frame is determined by a rectangle formed by the outermost points of one or more parking spaces in the second set of parking spaces.

[0151] The process of obtaining the second set of parking spaces can be referred to the process of obtaining the first set of parking spaces, and will not be repeated here.

[0152] In one embodiment, the method 1000 further includes aligning the first outer frame and the second outer frame along a preset direction.

[0153] For example, the preset direction is the first side of the first outer frame, or the preset direction is the second side of the second outer frame.

[0154] For example, when the number of visually detected parking spaces in the first outer frame is greater than the number of visually detected parking spaces in the second outer frame, the preset direction can be determined as the first side of the first outer frame.

[0155] In one embodiment, the method 1000 further includes: when the opening direction of at least some of the parking spaces does not correspond to the direction of the road, adjusting the opening direction of the at least some parking spaces to correspond to the direction of the road.

[0156] In one embodiment, the method 1000 further includes: aligning the associated elements in at least some of the parking spaces when associated elements exist in the one or more parking spaces.

[0157] For example, the associated elements include, but are not limited to, ground locks, wheel chocks, etc.

[0158] In one embodiment, the method 1000 further includes: controlling an in-vehicle display screen to display the map information, the map information including one or more repaired parking spaces.

[0159] The above embodiments illustrate the use of a forward rotation transformation followed by an inverse rotation transformation, but this application is not limited to this. For example, an inverse rotation transformation can be performed first to obtain a first outer frame, and then one or more parking spaces can be rearranged according to the size of the first outer frame and the preset parking space size. After rearranging one or more parking spaces, a forward rotation transformation is then performed to obtain the repaired parking space.

[0160] In this embodiment, a first bounding box is obtained by performing a forward rotation transformation on one or more parking spaces. Based on the dimensions of the bounding box and preset parking space dimensions, the parking spaces are rearranged and then subjected to a reverse rotation transformation to obtain the repaired parking spaces. This eliminates the need for offline repair of parking spaces on the map, saving labor costs; it also improves the aesthetics and accuracy of the constructed map and enhances the intelligence of vehicles.

[0161] This application also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes a unit (or means) for implementing the steps performed by a vehicle or a computing platform in a vehicle in any of the above methods.

[0162] Figure 11 A schematic block diagram of a map building device 1100 provided in an embodiment of this application is shown. The device 1100 includes: an acquisition unit 1110 for acquiring map information, the map information including a first parking space set, the first parking space set including one or more parking spaces; a transformation unit 1120 for performing a forward rotation transformation on the one or more parking spaces to obtain a first bounding box, the first bounding box being determined by a rectangle formed by the outermost points of the one or more parking spaces; an arrangement unit 1130 for arranging the one or more parking spaces according to the size of the first bounding box and a preset parking space size; the transformation unit 1120 is further used to perform a reverse rotation transformation on the arranged one or more parking spaces to obtain a repaired one or more parking spaces.

[0163] Optionally, the arrangement unit 1130 is used to: determine the number of rows and columns of parking spaces included in the first outer frame according to the size of the first outer frame and the preset parking space size; and arrange the one or more parking spaces according to the number of rows and columns of parking spaces included in the first outer frame.

[0164] Optionally, the map information also includes a second parking space set, which includes one or more parking spaces. The transformation unit 1120 is further configured to perform a forward rotation transformation on one or more parking spaces in the second parking space set to obtain a second outer frame. The device 1100 further includes a first adjustment unit, which is further configured to adjust the first outer frame and / or the second outer frame when the first outer frame and the second outer frame overlap, so that the first outer frame and the second outer frame do not overlap.

[0165] Optionally, the device 1100 further includes a first alignment unit for aligning the first outer frame and the second outer frame along a preset direction.

[0166] Optionally, the device 1100 further includes a determining unit for determining, before obtaining the repaired parking spaces, that the repaired parking spaces match the original parking spaces.

[0167] Optionally, the device 1100 further includes a second adjustment unit, used to adjust the opening direction of at least some of the parking spaces to correspond to the direction of the road when the opening direction of at least some of the parking spaces does not correspond to the direction of the road.

[0168] Optionally, the device 1100 further includes a second alignment unit for aligning associated elements in one or more parking spaces, the associated elements including parking locks and / or wheel chocks.

[0169] Optionally, the device 1100 further includes a third adjustment unit, used to adjust the size of the one or more parking spaces along a first direction according to the size between the two obstacles when the one or more parking spaces are located between two obstacles, the first direction corresponding to the direction of the line connecting the two obstacles.

[0170] Optionally, the acquisition unit 1110 is used to: acquire the first parking space set from the map information according to the nearest neighbor algorithm or the disjoint set algorithm.

[0171] Optionally, the acquisition unit 1110 is used to acquire the map information during the process of detecting automatic parking of the vehicle.

[0172] For example, the acquisition unit 1110 may be Figure 1 The computing platform or processing circuit, processor, or controller within the computing platform. Taking the acquisition unit 1110 as an example, which is the processor 151 in the computing platform, the processor 151 can acquire map information. For instance, during automatic parking, the processor 151 can construct the map information based on data collected by the camera device and radar.

[0173] For example, the transformation unit 1120 may be Figure 1 The computing platform or the processing circuit, processor or controller in the computing platform. Taking the transformation unit 1120 as the processor 152 in the computing platform as an example, the processor 152 can perform a forward rotation transformation on one or more parking spaces in the map information to obtain the bounding box; for example, the processor 152 can also perform a reverse rotation transformation on one or more rearranged parking spaces to obtain one or more repaired parking spaces.

[0174] For example, the arrangement unit 1130 can be Figure 1 The computing platform or the processing circuit, processor or controller in the computing platform. Taking the layout unit 1130 as the processor 153 in the computing platform as an example, the processor 153 can rearrange one or more parking spaces according to the size of the outer frame and the preset parking space size, so as to obtain one or more parking spaces after the rearrangement.

[0175] The functions implemented by the acquisition unit 1110, the transformation unit 1120, and the arrangement unit 1130 can be implemented by different processors, or they can be implemented by the same processor. This application embodiment does not limit this.

[0176] It should be understood that the division of units in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units in the device can be implemented by a processor calling software; for example, the device includes a processor connected to memory, which stores instructions. The processor calls the instructions stored in memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be, for example, a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. The functions of some or all units can be implemented through the design of the hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all units are implemented through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby implementing the functions of some or all units. All units of the above devices can be implemented entirely through processor calling software, or entirely through hardware circuits, or partially through processor calling software with the remaining parts implemented through hardware circuits.

[0177] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0178] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0179] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0180] This application also provides an apparatus comprising a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit to cause the apparatus to perform the methods or steps described in the above embodiments.

[0181] Optionally, if the device is located in a vehicle, the aforementioned processing unit may be Figure 1 The processors shown are 151-15n.

[0182] This application also provides a map building system, which may include sensors and a computing platform, and the computing platform may include the map building device 1100 described above.

[0183] This application also provides a server, which may include the map building device 1100 described above.

[0184] For example, during automatic parking, a vehicle can send data collected by sensors to a server, which can then construct a map based on that data. The server can also refine one or more parking spaces within this map. The server can then send the refined map information back to the vehicle, which can then display it on its in-vehicle display screen.

[0185] This application also provides a vehicle that may include the map building device or the map building system described above.

[0186] This application also provides a computer program product, which includes computer program code that, when run on a computer, causes the computer to perform the above-described method.

[0187] This application also provides a computer-readable medium storing program code that, when run on a computer, causes the computer to perform the above-described method.

[0188] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, power-on erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0189] It should be understood that in the embodiments of this application, the memory may include read-only memory and random access memory, and provides instructions and data to the processor.

[0190] It should also be understood that, in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0191] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0192] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0193] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0194] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0195] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0196] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0197] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be covered. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A map construction method, characterized in that, include: Obtain map information, which includes a first parking space set and a second parking space set. The first parking space set includes multiple parking spaces, and the second parking space set includes one or more parking spaces. According to the first transformation angle, the plurality of parking spaces are subjected to a positive rotation transformation, wherein the first transformation angle is determined based on the orientation angle of the plurality of parking spaces in the first set of parking spaces; Based on the multiple parking spaces after positive rotation transformation, a first outer frame is obtained, which is determined by a rectangular frame formed by the outermost points of the multiple parking spaces. According to the second transformation angle, one or more parking spaces in the second parking space set are subjected to a positive rotation transformation to obtain a second outer frame. The second transformation angle is determined according to the orientation angle of one or more parking spaces in the second parking space set. When the first outer frame and the second outer frame overlap, the first outer frame and / or the second outer frame are adjusted so that the first outer frame and the second outer frame do not overlap; The plurality of parking spaces are arranged according to the size of the first outer frame and the preset parking space size; The multiple parking spaces after being arranged are subjected to a reverse rotation transformation to obtain the multiple parking spaces after being repaired.

2. The method according to claim 1, characterized in that, The step of arranging the plurality of parking spaces according to the size of the first outer frame and the preset parking space size includes: Based on the dimensions of the first outer frame and the preset parking space dimensions, determine the number of rows and columns of parking spaces included in the first outer frame; The multiple parking spaces are arranged according to the number of rows and columns of parking spaces included in the first outer frame.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Align the first outer frame and the second outer frame along a preset direction.

4. The method according to claim 1 or 2, characterized in that, Before the plurality of parking spaces are repaired, the method further includes: The repaired parking spaces obtained after the inverse rotation transformation are determined to match the original parking spaces.

5. The method according to claim 1 or 2, characterized in that, The method further includes: When the opening direction of at least some of the parking spaces does not correspond to the direction of the road, the opening direction of the at least some parking spaces shall be adjusted to correspond to the direction of the road.

6. The method according to claim 1 or 2, characterized in that, The method further includes: Align the associated elements in the plurality of parking spaces, the associated elements including parking locks and / or wheel chocks.

7. The method according to claim 1 or 2, characterized in that, The method further includes: When the plurality of parking spaces are located between two obstacles, the dimensions of the plurality of parking spaces along a first direction are adjusted according to the dimensions between the two obstacles, the first direction corresponding to the direction of the line connecting the two obstacles.

8. The method according to claim 1 or 2, characterized in that, The method further includes: The first set of parking spaces is obtained from the map information according to the nearest neighbor algorithm or the disjoint set algorithm.

9. The method according to claim 1 or 2, characterized in that, The acquisition of map information includes: When automatic parking of a vehicle is detected, the map information is obtained.

10. A map building device, characterized in that, include: The acquisition unit is used to acquire map information, which includes a first parking space set and a second parking space set. The first parking space set includes one or more parking spaces, and the second parking space set includes one or more parking spaces. A transformation unit is used to perform a positive rotation transformation on the plurality of parking spaces according to a first transformation angle, wherein the first transformation angle is determined based on the orientation angle of the plurality of parking spaces in the first set of parking spaces; The transformation unit is further configured to obtain a first outer frame based on the plurality of parking spaces after positive rotation transformation, wherein the first outer frame is determined by a rectangular frame formed by the outermost points of the plurality of parking spaces. The transformation unit is further configured to perform a positive rotation transformation on one or more parking spaces in the second parking space set according to the second transformation angle to obtain a second outer frame, wherein the second transformation angle is determined according to the orientation angle of one or more parking spaces in the second parking space set; The first adjustment unit is used to adjust the first outer frame and / or the second outer frame when the first outer frame and the second outer frame overlap, so that the first outer frame and the second outer frame do not overlap. The arrangement unit is used to arrange the plurality of parking spaces according to the size of the first outer frame and the preset parking space size; The transformation unit is also used to perform a reverse rotation transformation on the arranged parking spaces to obtain the repaired parking spaces.

11. The apparatus according to claim 10, characterized in that, The arrangement unit is used for: Based on the dimensions of the first outer frame and the preset parking space dimensions, determine the number of rows and columns of parking spaces included in the first outer frame; The multiple parking spaces are arranged according to the number of rows and columns of parking spaces included in the first outer frame.

12. The apparatus according to claim 10 or 11, characterized in that, The device further includes: The first alignment unit is used to align the first outer frame and the second outer frame along a preset direction.

13. The apparatus according to claim 10 or 11, characterized in that, The device further includes: A determining unit is used to determine, before obtaining the repaired plurality of parking spaces, whether the repaired plurality of parking spaces are matched with the original plurality of parking spaces.

14. The apparatus according to claim 10 or 11, characterized in that, The device further includes: The second adjustment unit is used to adjust the opening direction of at least some of the parking spaces to correspond to the direction of the road when the opening direction of at least some of the parking spaces does not correspond to the direction of the road.

15. The apparatus according to claim 10 or 11, characterized in that, The device further includes: The second alignment unit is used to align associated elements in the plurality of parking spaces, the associated elements including parking locks and / or wheel chocks.

16. The apparatus according to claim 10 or 11, characterized in that, The device further includes: The third adjustment unit is used to adjust the size of the plurality of parking spaces along a first direction according to the size between the two obstacles when the plurality of parking spaces are located between the two obstacles. The first direction corresponds to the direction of the line connecting the two obstacles.

17. The apparatus according to claim 10 or 11, characterized in that, The acquisition unit is further configured to: The first set of parking spaces is obtained from the map information according to the nearest neighbor algorithm or the disjoint set algorithm.

18. The apparatus according to claim 10 or 11, characterized in that, The acquisition unit is used for: When automatic parking of a vehicle is detected, the map information is obtained.

19. A map building device, characterized in that, The device includes: Memory, used to store computer programs; A processor for executing a computer program stored in the memory to cause the apparatus to perform the method as described in any one of claims 1 to 9.

20. A map building system, characterized in that, It includes sensors and a computing platform, wherein the computing platform includes the apparatus of any one of claims 10 to 19.

21. A vehicle, characterized in that, Includes the map building apparatus according to any one of claims 10 to 19, or the map building system according to claim 20.

22. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a computer, enables the implementation of the method as described in any one of claims 1 to 9.

23. A chip, characterized in that, Includes a circuit for performing the method as described in any one of claims 1 to 9.

Images