A memory parking map management method and device, electronic equipment and storage medium

Abstract

The application discloses a memory parking map management method and device, an electronic device and a computer readable storage medium. The method comprises the following steps: acquiring the latest combined navigation positioning information received before a vehicle enters a parking lot, determining a corresponding current parking lot according to the combined navigation positioning information; when memory parking is started, acquiring height information output by a current barometer, and determining a current floor according to the height information; in the process of memory parking, image data is collected, and a slam map is constructed based on the image data; wherein the slam map comprises parking path information and map information; when the vehicle reaches a parking space, the constructed slam map is uploaded to a cloud server, so that the cloud server stores the slam map in map data of the current floor of the current parking lot. The application realizes map management of memory parking.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, more particularly, to a memory parking map management method and device, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the development of automatic driving technology, parking technology has developed from the initial APA (Auto Parking Assist) to the current HPA (Home-zone Parking Assist). APA mainly uses the wheel odometer information and ultrasonic information of the vehicle itself for automatic parking, and the environment needs to be observed manually during parking, which is not safe enough. HPA mainly uses the image information of the surround view camera to establish a slam (Simultaneous Localization and Mapping) map, and then the car can automatically park according to the route and map in the map.

[0003] Therefore, how to realize the map management of memory parking is a technical problem to be solved by those skilled in the art. SUMMARY

[0004] The present application aims to provide a memory parking map management method and device, an electronic device and a computer readable storage medium, which realizes the map management of memory parking.

[0005] To achieve the above-mentioned purpose, the present application provides a memory parking map management method, comprising:

[0006] Obtaining the latest combined navigation positioning information received before the vehicle enters the parking lot, determining the corresponding current parking lot according to the combined navigation positioning information;

[0007] When the memory parking is started, obtaining the height information output by the current barometer, and determining the current floor according to the height information;

[0008] In the process of memory parking, image data is collected, and a slam map is constructed based on the image data; wherein the slam map comprises parking path information and map information;

[0009] When the vehicle reaches the parking space, the constructed slam map is uploaded to the cloud server, so that the cloud server stores the slam map in the map data of the current floor of the current parking lot.

[0010] The method further comprises:

[0011] searching, according to the combined navigation positioning information, a nearest parking lot position in map data of all parking lots in the cloud server;

[0012] determining whether a distance between the combined navigation positioning information and the nearest parking lot position is less than a preset value;

[0013] if yes, determining the nearest parking lot position as a current parking lot corresponding to the combined navigation positioning information;

[0014] if no, adding the combined navigation positioning information into the map data of the cloud server to create a new parking lot for the combined navigation positioning information as the current parking lot.

[0015] wherein the cloud server manages map data of all parking lots through a k-d tree, and accordingly, the searching, according to the combined navigation positioning information, a nearest parking lot position in map data of all parking lots in the cloud server comprises:

[0016] searching, according to the combined navigation positioning information, a nearest parking lot position in the k-d tree in the cloud server;

[0017] correspondingly, the adding the combined navigation positioning information into the map data of the cloud server comprises:

[0018] adding the combined navigation positioning information into the k-d tree in the cloud server.

[0019] wherein the determining a current floor according to the height information comprises:

[0020] determining whether a slam map corresponding to the current parking lot exists in the cloud server;

[0021] if no, setting the height information as a reference height and determining an index value of the current floor as zero;

[0022] if yes, calculating a height difference between the height information and the reference height set in advance, and determining the index value of the current floor according to a ratio between the height difference and a floor height of the current parking lot;

[0023] determining the current floor according to the index value.

[0024] wherein before the constructing a slam map based on the image data, the method further comprises:

[0025] matching the collected image data with map data of the current floor of the current parking lot in the cloud server;

[0026] If the matching is successful, a matched slam map is acquired to perform memory parking based on the slam map.

[0027] If the matching fails, the step of constructing a slam map based on the image data is performed.

[0028] The cloud server manages map data of the same floor through a Hash table, and accordingly, the matching of the collected image data with the map data of the current floor of the current parking lot in the cloud server comprises:

[0029] In the target Hash table corresponding to the current floor of the current parking lot in the cloud server, the collected image data is matched with the map data in the target Hash table.

[0030] After the matched slam map is acquired, the method further comprises:

[0031] The matched slam map is fused with the collected image data.

[0032] Accordingly, the memory parking based on the slam map comprises:

[0033] The memory parking is performed based on the fused slam map.

[0034] To achieve the above object, the present application provides a memory parking map management device, comprising:

[0035] A first determination module is configured to acquire the latest combined navigation positioning information received before a vehicle enters a parking lot, and determine a corresponding current parking lot according to the combined navigation positioning information.

[0036] A second determination module is configured to acquire height information output by a barometer when memory parking is started, and determine a current floor according to the height information.

[0037] A construction module is configured to collect image data during memory parking, and construct a slam map based on the image data, wherein the slam map comprises parking path information and map information.

[0038] An uploading module is configured to upload the constructed slam map to a cloud server when the vehicle reaches a parking space, so that the cloud server stores the slam map in map data of the current floor of the current parking lot.

[0039] To achieve the above object, the present application provides an electronic device, comprising:

[0040] A memory is configured to store a computer program.

[0041] A processor is used to implement the steps of the memory parking map management method described above when executing the computer program.

[0042] To achieve the above objectives, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the memory parking map management method described above.

[0043] As can be seen from the above scheme, the memory parking map management method provided in this application includes: obtaining the latest combined navigation positioning information received before the vehicle enters the parking lot, and determining the corresponding current parking lot based on the combined navigation positioning information; when memory parking is activated, obtaining the current height information output by the barometer, and determining the current floor based on the height information; during the memory parking process, collecting image data, and constructing an SLAM map based on the image data; wherein, the SLAM map includes parking path information and map information; when the vehicle arrives at the parking space, uploading the constructed SLAM map to the cloud server, so that the cloud server stores the SLAM map in the map data of the current floor of the current parking lot.

[0044] The memory parking map management method provided in this application locates the parking lot using the vehicle's combined navigation positioning information and the floor level using the altitude information output by the barometer. It then uploads the SLAM map of each parking space on each floor of each parking lot to a cloud server. This cloud server enables map management of memory parking and facilitates cross-regional map sharing, solving the problems of complexity, geographical randomness, and floor randomness in memory parking applications. This application also discloses a memory parking map management device, an electronic device, and a computer-readable storage medium, which can achieve the same technical effects.

[0045] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The drawings are used to provide a further understanding of this disclosure and constitute a part of the specification. They are used together with the following detailed description to explain this disclosure, but do not constitute a limitation of this disclosure. In the drawings:

[0047] Figure 1 FIG. 1 is a flowchart of a memory parking map management method according to an example embodiment;

[0048] Figure 2 FIG. 2 is a flowchart of another memory parking map management method according to an example embodiment;

[0049] Figure 3 FIG. 3 is a flowchart of memory parking map management in an application example provided by the present application;

[0050] Figure 4 FIG. 4 is a detailed flowchart of memory parking map management in an application example provided by the present application;

[0051] Figure 5 FIG. 5 is a structural diagram of a memory parking map management device according to an example embodiment;

[0052] Figure 6 FIG. 6 is a structural diagram of an electronic device according to an example embodiment. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application. In addition, in the embodiments of the present application, "first", "second", etc. are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence.

[0054] The embodiments of the present application disclose a memory parking map management method, which realizes map management of memory parking.

[0055] Referring to FIG. 1, a flowchart of a memory parking map management method according to an example embodiment includes the following steps: Figure 1 Figure 1

[0056] S101: Obtain the latest combined navigation positioning information received before the vehicle enters the parking lot, and determine the corresponding current parking lot according to the combined navigation positioning information;

[0057] Before the vehicle enters the parking lot, the last received combined navigation positioning information is taken as the current position of the vehicle, and the current parking lot is positioned according to the current position of the vehicle. Combined navigation refers to a navigation system that integrates various navigation devices and is controlled by a monitor and a computer. The combined navigation positioning information can include longitude and latitude information.

[0058] ​​As a feasible implementation, the determining the corresponding current parking lot according to the combined navigation positioning information comprises: searching the closest parking lot position in the map data of all parking lots in the cloud server according to the combined navigation positioning information; judging whether the distance between the combined navigation positioning information and the closest parking lot position is less than a preset value; if yes, determining the closest parking lot position as the current parking lot corresponding to the combined navigation positioning information; if no, adding the combined navigation positioning information into the map data of the cloud server to create a new parking lot for the combined navigation positioning information as the current parking lot.

[0059] In a specific implementation, the cloud server stores the map data of all parking lots, searches the closest parking lot position in the map data of all parking lots according to the combined navigation positioning information, calculates the distance between the combined navigation positioning information and the closest parking lot position, i.e. the distance between the current position and the closest parking lot position, and if the distance is less than a preset value, determines the closest parking lot position as the current parking lot, otherwise, creates a new parking lot and adds the combined navigation positioning information into the map data of the cloud server as the position information of the new parking lot. It should be noted that the preset value is not specifically limited here and can be flexibly set by the user according to the actual situation, for example, can be set to 50 meters.

[0060] Preferably, the cloud server manages the map data of all parking lots through a k-d tree, and correspondingly, the searching the closest parking lot position in the map data of all parking lots in the cloud server according to the combined navigation positioning information comprises: searching the closest parking lot position in the k-d tree in the cloud server according to the combined navigation positioning information; and correspondingly, the adding the combined navigation positioning information into the map data of the cloud server comprises: adding the combined navigation positioning information into the k-d tree in the cloud server.

[0061] In practice, the cloud server manages all parking lot map data using a kd-tree (k-dimensional tree), with the parking lot location as the initial index. During the initial SLAM map construction, the cloud server creates the kd-tree and adds the integrated navigation positioning information as the current parking lot's location. In subsequent SLAM map construction, the server searches the kd-tree for the nearest parking lot to the current location based on the integrated navigation positioning information. It calculates the distance between the integrated navigation positioning information and the nearest parking lot location; if the distance is less than a preset value, the nearest parking lot is designated as the current parking lot. Otherwise, a new parking lot is created, and the integrated navigation positioning information is added to the kd-tree as the new parking lot's location.

[0062] S102: When memory parking is activated, obtain the current height information output by the barometer and determine the current floor based on the height information;

[0063] When a vehicle enters the parking area and is about to activate memory parking, the user can manually tap the vehicle's central control screen to activate the memory parking function. At this time, the current height information output by the barometer is recorded, and the current floor is located based on the height information.

[0064] As a feasible implementation method, determining the current floor based on the height information includes: determining whether a SLAM map corresponding to the current parking lot exists in the cloud server; if not, setting the height information as a reference height and determining the index value of the current floor as zero; if yes, calculating the height difference between the height information and the preset reference height, determining the index value of the current floor based on the ratio between the height difference and the floor height of the current parking lot; and determining the current floor based on the index value.

[0065] In practice, the system checks whether the cloud server stores an SLAM map corresponding to the current parking lot. If not, it indicates that this is the first time an SLAM map for the current parking lot is being built. In this case, the current barometer output height is set as the reference height, and the index value of the current floor is set to zero. If the cloud server stores an SLAM map corresponding to the current parking lot, it means this is not the first time an SLAM map for the current parking lot is being built, i.e., the reference height has already been set. In this case, the height difference between the current barometer output height and the reference height is calculated, and the index value of the current floor is determined as an approximation of the ratio between this height difference and the floor height of the current parking lot. Using the current floor index value as the precise index, the current floor can be determined.

[0066] S103: In the process of memory parking, image data is collected, and a slam map is constructed based on the image data; wherein the slam map includes parking path information and map information;

[0067] After starting memory parking, image data is collected by the surround view camera. In the absence of a slam map of the current parking space, the vehicle is manually parked in the current parking space, and image data is collected in real time by the surround view camera. A slam map of the current parking space is constructed based on the collected image data, including parking path information and map information, and of course can also include vehicle state information, which is not specifically limited here.

[0068] As a feasible implementation, before constructing the slam map based on the image data, it further includes: matching the collected image data with the map data of the current floor of the current parking lot in the cloud server; if the matching is successful, the matched slam map is obtained to perform memory parking based on the slam map; if the matching fails, the step of constructing the slam map based on the image data is performed.

[0069] In a specific implementation, it is judged whether the slam map corresponding to the current floor of the current parking lot is stored in the cloud server. If not, it means that it is the first time to construct the slam map of the current floor of the current parking lot, and visual slam mapping is directly performed at this time. If the slam map corresponding to the current floor of the current parking lot is stored in the cloud server, it means that it is not the first time to construct the slam map of the current floor of the current parking lot, and the collected image data is matched with the map data of the current floor of the current parking lot in the cloud server at this time. If the matching is successful, memory parking can be directly performed based on the matched slam map, and it is not necessary to re-construct the slam map. Preferably, after obtaining the matched slam map, the matched slam map can be fused with the collected image data, and memory parking is performed based on the fused slam map. If the matching fails, visual slam mapping is performed.

[0070] Preferably, the cloud server manages the map data of the same floor through a Hash table, and correspondingly, the matching of the collected image data with the map data of the current floor of the current parking lot in the cloud server includes: matching the collected image data with the map data in the target Hash table corresponding to the current floor of the current parking lot in the cloud server.

[0071] In a specific implementation, the cloud server manages the map data of the same floor through a Hash table, and determines the target Hash table corresponding to the current floor according to the index value of the current floor. When the slam map of the current floor of the current parking lot is constructed for the first time, a visual slam map is directly constructed, the index of the slam map is set to zero, and the slam map is added to the target Hash table. When the slam map of the current floor of the current parking lot is not constructed for the first time, the collected image data is matched with the map data in the target Hash table. If the matching is successful, the memory parking can be directly performed based on the matched slam map, and it is not necessary to re-construct the slam map. If the matching fails, a visual slam map is constructed, an index value is assigned to the slam map, and the slam map is added to the target Hash table.

[0072] S104: When the vehicle reaches the parking space, the constructed slam map is uploaded to the cloud server, so that the cloud server stores the slam map in the map data of the current floor of the current parking lot.

[0073] When the vehicle reaches the parking space, a human clicks the vehicle central control screen to end the memory parking mapping, and the constructed slam map is uploaded to the cloud server through the Internet of Vehicles. The cloud server stores the received slam map in the map data of the current floor of the current parking lot, performs map fusion on the received slam map and other slam maps of the current floor, and forms a complete parking lot map of the current floor. When other vehicles need to perform memory parking in the current floor of the current parking lot, the cloud server can distribute the slam map to the other vehicles, so that the other vehicles automatically perform memory parking.

[0074] The memory parking map management method provided in the embodiments of the application positions the parking lot through the combined navigation positioning information of the vehicle, positions the floor through the height information output by the barometer, uploads the slam map of each parking space of each floor of each parking lot to the cloud server, and realizes the map management of memory parking through the cloud server, realizes the map sharing of memory parking across regions, and solves the problems of complexity, randomness of regions, and randomness of floors in the application scenario of memory parking.

[0075] The embodiment of the application discloses a memory parking map management method, which is further described and optimized compared with the previous embodiment. Specifically,

[0076] Referring to Figure 2 , according to another flowchart of the memory parking map management method shown in an example embodiment, as shown in Figure 2 , the method comprises:

[0077] S201: Obtain the latest combined navigation positioning information received before the vehicle enters the parking lot, and search for the closest parking lot position in the map data of all parking lots in the cloud server according to the combined navigation positioning information;

[0078] S202: Determine whether the distance between the combined navigation positioning information and the closest parking lot position is less than a preset value; if yes, go to S203; if no, go to S204;

[0079] S203: Determine the closest parking lot position as the current parking lot corresponding to the combined navigation positioning information;

[0080] S204: Add the combined navigation positioning information to the map data in the cloud server to create a new parking lot as the current parking lot for the combined navigation positioning information;

[0081] In a specific implementation, the cloud server stores map data of all parking lots. When building a slam map for the first time, a new parking lot is directly created, and the combined navigation positioning information is added to the map data in the cloud server as the position information of the new parking lot. When it is not the first time to build a slam map, the closest parking lot position to the current position is searched in the map data of all parking lots according to the combined navigation positioning information, the distance between the combined navigation positioning information and the closest parking lot position is calculated, that is, the distance between the current position and the closest parking lot position is calculated, if the distance is less than a preset value, the closest parking lot position is determined as the current parking lot, otherwise, a new parking lot is created, and the combined navigation positioning information is added to the map data in the cloud server as the position information of the new parking lot.

[0082] S205: When the memory parking is started, obtain the height information output by the current barometer;

[0083] S206: Determine whether there is a slam map corresponding to the current parking lot in the cloud server; if no, go to S207; if no, go to S208;

[0084] S207: Set the height information as the reference height, and determine the index value of the current floor as zero;

[0085] S208: Calculate the height difference between the height information and the preset reference height, and determine the index value of the current floor according to the ratio between the height difference and the floor height of the current parking lot;

[0086] S209: Determine the current floor according to the index value;

[0087] In a specific implementation, it is judged whether the slam map corresponding to the current parking lot is stored in the cloud server. If not, it means that it is the first time to build the slam map of the current parking lot. At this time, the height information output by the current barometer is set as the reference height, and the index value of the current floor is determined as zero. If the slam map corresponding to the current parking lot is stored in the cloud server, it means that it is not the first time to build the slam map of the current parking lot, that is, the reference height has been set in advance. At this time, the height difference between the height information output by the current barometer and the reference height is calculated, and the index value of the current floor is determined as the approximate value of the ratio between the height difference and the floor height of the current parking lot. The index value of the current floor is used as the accurate index, and the current floor can be determined through the index value of the current floor.

[0088] S210: In the process of memory parking, image data is collected, and the collected image data is matched with the map data of the current floor of the current parking lot in the cloud server. If the matching is successful, S211 is entered. If the matching fails, S212 is entered.

[0089] S211: The matched slam map is obtained to perform memory parking based on the slam map.

[0090] S212: A slam map is constructed based on the image data. The slam map includes parking path information and map information.

[0091] In a specific implementation, it is judged whether the slam map corresponding to the current parking lot is stored in the cloud server. If not, it means that it is the first time to build the slam map of the current parking lot. At this time, the height information output by the current barometer is set as the reference height, and the index value of the current floor is determined as zero. If the slam map corresponding to the current parking lot is stored in the cloud server, it means that it is not the first time to build the slam map of the current parking lot, that is, the reference height has been set in advance. At this time, the height difference between the height information output by the current barometer and the reference height is calculated, and the index value of the current floor is determined as the approximate value of the ratio between the height difference and the floor height of the current parking lot. The index value of the current floor is used as the accurate index, and the current floor can be determined through the index value of the current floor.

[0092] S213: When the vehicle reaches the parking space, the constructed slam map is uploaded to the cloud server, so that the cloud server stores the slam map in the map data of the current floor of the current parking lot.

[0093] When the vehicle reaches the parking space, the human clicks the central screen in the vehicle, ends the memory parking mapping, and uploads the constructed slam map to the cloud server through the Internet of Vehicles. The cloud server stores the received slam map in the map data of the current floor of the current parking lot, fuses the received slam map with other slam maps of the current floor, and forms a complete parking lot map of the current floor. When other vehicles need to perform memory parking in the current floor of the current parking lot, the cloud server can distribute the slam map to other vehicles, so that other vehicles automatically perform memory parking.

[0094] The memory parking map management method provided by the embodiments of the application positions the parking lot through the combined navigation positioning information of the vehicle, positions the floor through the height information output by the barometer, uploads the slam map of each parking space of each floor of each parking lot to the cloud server, realizes the map management of memory parking through the cloud server, realizes the map sharing of memory parking across regions, and solves the problems of complexity, randomness of regions, and randomness of floors in the application scenario of memory parking.

[0095] An application embodiment provided by the application is introduced below. A flowchart of memory parking map management is shown in Figure 3 The longitude and latitude information of the last received combined navigation near the parking lot is used as the position to construct the Kd-tree, all parking lots are uniformly managed, and the parking lot map is managed across regions. The height information output by the barometer is used to manage all floors of a single parking lot, and the parking lot map is managed across floors. The map ID is used to manage all slam maps of a single floor, the cloud server updates the slam map in real time, the map fusion of the same floor is realized, so as to form a complete parking lot map, and automatic memory parking is realized.

[0096] A detailed flowchart of memory parking map management is shown in Figure 4 The detailed flowchart mainly includes the following steps:

[0097] Step 1: Before the vehicle enters the parking lot, the last received combined navigation positioning information of the vehicle is used as the position information of the parking lot. When the map is established for the first time, the position information is used to construct the Kd-tree. If it is not the first time to construct the map, the nearest neighbor parking lot position is searched in the Kd-tree, and the distance between the nearest neighbor position and the current position is calculated. If the distance is less than a certain threshold (50 m), it is indicated that the map of the parking lot has been established before, and the Kd-tree does not need to be modified. If the distance is greater than the threshold, the current position is added to the Kd-tree, and the current parking lot is recorded as current_park.

[0098] Step 2: When the vehicle is about to start the memory parking in the parking area, record the current height information output by the barometer; when building the map for the first time, the default floor id is 0, and a Hash table is used to manage the floors, the floors are indexed by id, and the parking maps of the same floor are managed by the value of Hash, and the current height information is set as the reference height H; when it is not the first time to build the map, calculate the absolute value of the height difference between the current height and the reference height; when the absolute value of the height difference is less than a certain threshold (1m), it is indicated that it is in the same floor, and there is no need to create a new floor id or update the floor Hash table; when the absolute value of the height difference is greater than the threshold, calculate the floor id, which is the approximate value of the ratio between the height difference and the floor height, and update the Hash table.

[0099] Step 3: Start the memory parking and collect the image data of the surround view camera; when building the map for the first time, directly perform visual slam mapping, the id of the visual slam parking map is 0, and the map is added to the floor Hash table; when it is not the first time to build the map, traverse all the slam maps of the floor through the Hash table, and perform map matching using the current surround view camera image data; if the matching is successful, it indicates that there is already a slam map for memory parking at the current position, and direct map fusion is performed; if the matching fails, create a new slam map for memory parking at the current position.

[0100] Step 4: When the vehicle reaches the parking space, the driver clicks the central screen of the vehicle to end the memory parking, and the system saves the current vehicle path information and map information, as well as the state information of the vehicle

[0101] Step 5: After the slam map is created, upload the slam map to the cloud server through the Internet of Vehicles, and the cloud server can download the slam map to other vehicles when needed, realizing the sharing of slam maps.

[0102] Step 6: The cloud performs indexing and updating on the map to realize map fusion of the same floor, forming a complete parking lot map, and subsequent memory parking can be completely automated without the need for mapping.

[0103] As can be seen, the positioning information of the combined navigation is used to preliminarily locate the parking lot position, the positioning information is the preliminary index id of the memory parking map of the parking lot, the height information output by the barometer is used to identify the floor information of the parking lot, the height information is the accurate index id of the memory parking map, the cloud map is updated, OTA (Over-the-Air Technology, space download technology) is upgraded, the sharing and fusion of multi-vehicle maps are realized, and the problems of complexity, geographical randomness, and floor randomness of the memory parking application scenario are solved.

[0104] The memory parking map management device provided in the embodiment of the present application is introduced below, and the memory parking map management device described below can be referred to the memory parking map management method described above.

[0105] Referring to Figure 5 According to the structural diagram of the memory parking map management device shown in an example embodiment, as shown in Figure 5 , it comprises:

[0106] The first determining module 501 is configured to acquire the latest combined navigation positioning information received before the vehicle enters the parking lot, and determine the corresponding current parking lot according to the combined navigation positioning information.

[0107] The second determining module 502 is configured to acquire the height information output by the barometer when the memory parking is started, and determine the current floor according to the height information.

[0108] The constructing module 503 is configured to collect image data during the memory parking, and construct a slam map based on the image data; wherein the slam map comprises parking path information and map information.

[0109] The uploading module 504 is configured to upload the constructed slam map to the cloud server when the vehicle reaches the parking space, so that the cloud server stores the slam map in the map data of the current floor of the current parking lot.

[0110] The memory parking map management device provided in the embodiment of the present application positions the parking lot through the combined navigation positioning information of the vehicle, positions the floor through the height information output by the barometer, uploads the slam map of each parking space of each floor of each parking lot to the cloud server, and realizes the map management of memory parking through the cloud server, realizes the map sharing of memory parking across regions, and solves the problems of complexity, randomness of region, and randomness of floor in the application scenario of memory parking.

[0111] On the basis of the above-mentioned embodiment, as a preferred embodiment, the first determining module 501 comprises:

[0112] The first acquiring unit is configured to acquire the latest combined navigation positioning information received before the vehicle enters the parking lot.

[0113] The searching unit is configured to search the closest parking lot position in the map data of all parking lots in the cloud server according to the combined navigation positioning information.

[0114] The first determining unit is configured to determine whether a distance between the combined navigation positioning information and the nearest parking lot position is less than a preset value; if yes, a working process of the first determining unit is started; and if no, a working process of the creating unit is started.

[0115] The first determining unit is configured to determine whether a distance between the combined navigation positioning information and the nearest parking lot position is less than a preset value; if yes, a working process of the first determining unit is started; and if no, a working process of the creating unit is started.

[0116] The first determining unit is configured to determine whether a distance between the combined navigation positioning information and the nearest parking lot position is less than a preset value; if yes, a working process of the first determining unit is started; and if no, a working process of the creating unit is started.

[0117] In the above embodiment, as a preferred implementation, the cloud server manages map data of all parking lots through a k-d tree, and correspondingly, the searching unit is specifically configured to search, according to the combined navigation positioning information, the nearest parking lot position in the k-d tree in the cloud server.

[0118] In the above embodiment, as a preferred implementation, the cloud server manages map data of all parking lots through a k-d tree, and correspondingly, the searching unit is specifically configured to search, according to the combined navigation positioning information, the nearest parking lot position in the k-d tree in the cloud server.

[0119] In the above embodiment, as a preferred implementation, the second determining module 502 includes:

[0120] The second obtaining unit is configured to obtain height information output by a current barometer when memory parking is started.

[0121] The second determining unit is configured to determine whether a distance between the combined navigation positioning information and the nearest parking lot position is less than a preset value; if yes, a working process of the first determining unit is started; and if no, a working process of the creating unit is started.

[0122] The second determining unit is configured to determine whether a distance between the combined navigation positioning information and the nearest parking lot position is less than a preset value; if yes, a working process of the first determining unit is started; and if no, a working process of the creating unit is started.

[0123] The third determining unit is configured to calculate a height difference between the height information and the reference height, and determine an index value of a current floor according to a ratio between the height difference and a floor height of the current parking lot.

[0124] The fourth determining unit is configured to determine the current floor according to the index value.

[0125] In the above embodiment, as a preferred implementation, the constructing module 503 includes:

[0126] The acquisition unit is configured to acquire image data during memory parking;

[0127] The matching unit is configured to match the acquired image data with map data of the current floor of the current parking lot in the cloud server, and if the matching is successful, start a working process of the parking unit, and if the matching fails, start a working process of the construction unit.

[0128] The parking unit is configured to acquire the matched slam map, and perform memory parking based on the slam map.

[0129] The construction unit is configured to construct a slam map based on the image data.

[0130] On the basis of the above-mentioned embodiments, as a preferred embodiment, the cloud server manages the map data of the same floor through a Hash table, and correspondingly, the matching unit is specifically configured to match the acquired image data with the map data in a target Hash table corresponding to the current floor of the current parking lot in the cloud server.

[0131] On the basis of the above-mentioned embodiments, as a preferred embodiment, the parking unit is specifically configured to acquire the matched slam map, perform map fusion on the matched slam map and the acquired image data, and perform memory parking based on the fused slam map.

[0132] As to the device in the above-mentioned embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the method, and will not be described in detail here.

[0133] Based on the hardware implementation of the above-mentioned program modules, and in order to implement the method of the embodiments of the present application, the embodiments of the present application further provide an electronic device, Figure 6 As shown in FIG. 1, the electronic device includes: Figure 6

[0134] The communication interface 1 can interact with other devices such as network devices, etc.

[0135] The processor 2 is connected with the communication interface 1 to realize information interaction with other devices, and is used to run a computer program to execute the memory parking map management method provided by one or more technical solutions described above. The computer program is stored on the memory 3.

[0136] ​Of course, in a practical application, the various components of the electronic device are coupled together by a bus system 4. As will be appreciated, the bus system 4 is used to enable the components to communicate with one another. The bus system 4 includes, among other things, a data bus to facilitate the transfer of computer program instructions and / or data between components. The bus system 4 also includes a power bus, a control bus, and a state signal bus, although these are not shown for clarity of comprehension. Figure 6

[0137] The memory 3 in the embodiments of the present application is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer programs used to operate on the electronic device.

[0138] ​It can be understood that the memory 3 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM). The magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM can be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memory 3 described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.

[0139] The method disclosed in the embodiments of the present application can be applied in the processor 2 or implemented by the processor 2. The processor 2 can be an integrated circuit chip with processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 2 or the instruction in the form of software. The processor 2 described above can be a general processor, DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The processor 2 can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the execution can be directly embodied as hardware decoding processor or executed by the combination of hardware and software modules in the decoding processor. The software module can be located in the storage medium, which is located in the memory 3. The processor 2 reads the program in the memory 3 and combines the hardware to complete the steps of the above method.

[0140] The processor 2 implements the corresponding flow in each method of the embodiments of the present application when executing the program. For brevity, it will not be repeated here.

[0141] In the exemplary embodiments, the embodiments of the present application also provide a storage medium, i.e. a computer storage medium, specifically a computer readable storage medium, for example, including the memory 3 storing the computer program, the above computer program can be executed by the processor 2 to complete the steps of the above method. The computer readable storage medium can be FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, CD-ROM, etc.

[0142] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the above program can be stored in a computer readable storage medium. The program is executed to perform the steps of the above method embodiments; and the above storage medium includes mobile storage device, ROM, RAM, magnetic disc or optical disc, etc. Various media that can store program codes.

[0143] Alternatively, the above-mentioned integrated units of the present application, if realized in the form of software function modules and sold or used as independent products, can also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to make an electronic device (which can be a personal computer, a server, a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes: mobile storage devices, ROM, RAM, magnetic disks or optical disks, and various media that can store program codes.

[0144] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for managing memory-based parking maps, characterized in that, include: Obtain the latest combined navigation positioning information received before the vehicle enters the parking lot, and determine the corresponding current parking lot based on the combined navigation positioning information; When memory parking is activated, the current height information output by the barometer is obtained, and the current floor is determined based on the height information. During the parking memory process, image data is collected and matched with the map data of the current floor of the current parking lot in the cloud server; wherein, the cloud server manages the map data of all parking lots through a kd-tree and the cloud server manages the map data of the same floor through a hash table; If a match is successful, the matched SLAM map is obtained, and parking memory is performed based on the SLAM map. If a match fails, an SLAM map is constructed based on the image data; wherein, the SLAM map includes parking route information and map information; When a vehicle arrives at a parking space, the completed SLAM map is uploaded to the cloud server so that the cloud server can store the SLAM map in the map data of the current floor of the current parking lot. The step of determining the current floor based on the height information includes: Determine whether the SLAM map corresponding to the current parking lot exists in the cloud server; If not, the height information is set as the reference height, and the index value of the current floor is set to zero; If so, calculate the height difference between the height information and the preset reference height, and determine the index value of the current floor based on the ratio between the height difference and the floor height of the current parking lot; The current floor is determined based on the index value.

2. The memory parking map management method according to claim 1, characterized in that, Determining the corresponding current parking lot based on the combined navigation positioning information includes: Based on the combined navigation positioning information, the nearest parking lot location is searched in the map data of all parking lots in the cloud server; Determine whether the distance between the combined navigation positioning information and the nearest parking lot location is less than a preset value; If so, the nearest parking lot location is determined as the current parking lot corresponding to the combined navigation positioning information; If not, the combined navigation positioning information is added to the map data of the cloud server to create a new parking lot as the current parking lot based on the combined navigation positioning information.

3. The memory parking map management method according to claim 2, characterized in that, The step of searching for the nearest parking lot location in the map data of all parking lots in the cloud server based on the combined navigation positioning information includes: Based on the combined navigation positioning information, the nearest parking lot location is searched in the kd tree in the cloud server; Accordingly, the combined navigation positioning information is added to the map data of the cloud server, including: The combined navigation positioning information is added to the kd tree in the cloud server.

4. The memory parking map management method according to claim 1, characterized in that, The step of matching the collected image data with the map data of the current floor of the current parking lot in the cloud server includes: The target hash table corresponding to the current floor of the current parking lot is obtained from the cloud server, and the collected image data is matched with the map data in the target hash table.

5. The memory parking map management method according to claim 1, characterized in that, After obtaining the matched SLAM map, the process also includes: The matched SLAM map is then fused with the collected image data; Accordingly, the memory parking based on the SLAM map includes: Parking memory is performed based on the merged SLAM map.

6. A memory parking map management device, characterized in that, include: The first determining module is used to obtain the latest combined navigation positioning information received before the vehicle enters the parking lot, and determine the corresponding current parking lot based on the combined navigation positioning information. The second determining module is used to obtain the current height information output by the barometer when memory parking is activated, and to determine the current floor based on the height information. A construction module is used to collect image data during the parking process and construct an SLAM map based on the image data; wherein, the SLAM map includes parking path information and map information; wherein, the cloud server manages the map data of all parking lots through a kd-tree, and the cloud server manages the map data of the same floor through a hash table; The upload module is used to upload the completed SLAM map to the cloud server when the vehicle arrives at the parking space, so that the cloud server can store the SLAM map in the map data of the current floor of the current parking lot; The second determining module includes: The second acquisition unit is used to acquire the current altitude information output by the barometer when memory parking is activated. The second determination unit is used to determine whether the SLAM map corresponding to the current parking lot exists in the cloud server; if not, the workflow of the second determination unit is started; if yes, the workflow of the third determination unit is started. The second determining unit is used to set the height information as a reference height and determine the index value of the current floor as zero; The third determining unit is used to calculate the height difference between the height information and the preset reference height, and to determine the index value of the current floor based on the ratio between the height difference and the floor height of the current parking lot. The fourth determining unit is used to determine the current floor based on the index value; The building module includes: The acquisition unit is used to acquire image data during the memory parking process; The matching unit is used to match the collected image data with the map data of the current floor of the current parking lot in the cloud server; if the matching is successful, the parking unit's workflow is started; if the matching fails, the construction unit's workflow is started. A parking unit is used to acquire the matched SLAM map in order to perform memory parking based on the SLAM map; A construction unit is used to construct an SLAM map based on the image data.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the memory parking map management method as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the memory parking map management method as described in any one of claims 1 to 5.

Images