Parking space identification method, apparatus and device, and storage medium

Abstract

A parking space identification method, apparatus and device, and a storage medium. The method comprises: acquiring real-time parking lot information of a target parking lot and historical parking lot information corresponding to the target parking lot (S110); determining the confidence of a target parking space on the basis of real-time parking space data in the real-time parking lot information and historical parking space data in the historical parking lot information (S120); and determining the parking space corresponding to the confidence of the target parking space that meets a preset condition as a target parking space, wherein the preset condition comprises that the confidence of the target parking space is greater than or equal to a preset threshold (S130).

Description

Parking space identification method, device, equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 28, 2023, with application number 202311611425.1. The entire contents of the above application are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving technology, for example, to a parking space recognition method, device, equipment and storage medium. Background Art

[0003] With the rapid development of artificial intelligence (AI), automated parking technology has been widely adopted by many vehicles. This technology primarily involves three aspects: parking space recognition, trajectory planning, and parking control. Parking space recognition, as the foundation of automated parking technology, has a significant impact on its performance.

[0004] The efficiency and accuracy of parking space recognition methods in related technologies are significantly affected by the environment. For example, in newer residential underground parking lots, open-air parking lots during the day, and parking lots near nightclubs during the day, the recognition efficiency and accuracy may be relatively high. However, in older residential areas, due to disrepair or long-term cargo hauling, the parking space lines may become blurred. At night, in some open-air parking lots, insufficient lighting (or lack of lighting) may reduce the grayscale difference between the parking space lines and the ground, or severe light pollution may make it difficult to distinguish parking spaces. These environments will bring difficulties to parking space recognition methods, resulting in reduced efficiency and accuracy, which in turn affects users' parking.

[0005] Summary of the Invention

[0006] The present application provides a parking space recognition method, apparatus, device and storage medium to solve the problem that related parking space recognition methods are affected by the environment, resulting in low efficiency and accuracy of parking space recognition.

[0007] According to one aspect of the present application, a parking space identification method is provided, comprising:

[0008] Obtain the real-time parking information of the target parking lot and the historical parking information corresponding to the target parking lot;

[0009] Determine the target vehicle position reliability based on the real-time parking space data in the real-time parking information and the historical parking space data in the historical parking information;

[0010] The parking space corresponding to the target vehicle position reliability that meets the preset conditions is determined as the target parking space, wherein the preset conditions include that the target vehicle position reliability is greater than or equal to a preset threshold.

[0011] According to another aspect of the present application, a parking space recognition device is provided, comprising:

[0012] An information acquisition module is configured to acquire real-time parking lot information of a target parking lot and historical parking lot information corresponding to the target parking lot;

[0013] a confidence determination module configured to determine the target vehicle position confidence based on the real-time parking space data in the real-time parking information and the historical parking space data in the historical parking information;

[0014] The parking space determination module is configured to determine a parking space corresponding to a target vehicle position reliability meeting a preset condition as a target parking space, wherein the preset condition includes that the target vehicle position reliability is greater than or equal to a preset threshold.

[0015] According to another aspect of the present application, a parking space recognition device is provided, the parking space recognition device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the parking space recognition method of any embodiment of the present application.

[0019] According to another aspect of the present application, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the parking space recognition method of any embodiment of the present application when executed.

[0020] The technical solution provided by the embodiments of the present application obtains real-time parking information of a target parking lot and historical parking information corresponding to the target parking lot; determines the target vehicle position reliability based on the real-time parking space data in the real-time parking information and the historical parking space data in the historical parking information; and identifies the parking space corresponding to the target vehicle position reliability that meets preset conditions as the target parking space, wherein the preset conditions include the target vehicle position reliability being greater than or equal to a preset threshold. Considering that when the environment deteriorates, parking space lines may become blurred or incomplete, thereby affecting real-time parking space identification, if parking spaces in the parking lot have been previously identified under relatively good conditions, the historical parking space data can be used to assist in real-time parking space identification. Specifically, the real-time parking space data from the real-time parking information and the historical parking space data from the historical parking information are combined to comprehensively identify the parking space. This effectively solves the problem in related art parking space identification methods that are affected by the environment, resulting in low efficiency and accuracy in parking space identification. This effectively reduces environmental interference and improves the efficiency and accuracy of parking space identification.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] FIG1 is a flow chart of a parking space identification method provided in Example 1 of the present application;

[0024] FIG2 is a flow chart of a parking space identification method provided in Example 2 of the present application;

[0025] FIG3 is a schematic diagram of a parking space grayscale image provided in an embodiment of the present application;

[0026] FIG4 is a schematic structural diagram of a parking space recognition device provided in Example 3 of the present application;

[0027] FIG5 is a schematic diagram of the structure of a parking space identification device provided in the implementation of this application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] FIG1 is a flow chart of a parking space identification method provided in Example 1 of the present application. This embodiment is applicable to situations where parking spaces are to be identified. The method can be performed by a parking space identification device, which can be implemented in the form of hardware and / or software and can be configured in a parking space identification device. Optionally, the parking space identification device can be a vehicle, or the parking space identification device can be integrated into a vehicle. As shown in FIG1 , the method includes:

[0032] S110: Acquire real-time parking lot information of a target parking lot and historical parking lot information corresponding to the target parking lot.

[0033] In this embodiment, the target parking lot is the parking lot where the vehicle currently identifies a parking space. Real-time parking lot information may include relevant information about the target parking lot identified by the vehicle at the current moment. For example, real-time parking lot information may include real-time environmental data, real-time parking space data, and real-time positioning data. Real-time environmental data is environmental data other than real-time parking space data and real-time positioning data. For example, real-time environmental data may include parking lot signs, entrance security booths, and entrance railings. Historical parking lot information includes relevant information about the target parking lot identified by the vehicle at times prior to the current moment. Historical parking lot information includes historical environmental data, historical parking space data, and historical positioning data. Historical environmental data is environmental data other than historical parking space data and historical positioning data. For example, the content of the real-time environmental data corresponds one-to-one with the real-time environmental data.

[0034] Specifically, by identifying the current parking lot through relevant equipment on the vehicle, real-time parking lot information can be obtained. For example, through image recognition equipment such as surround-view cameras, real-time environmental data of the target parking lot can be obtained, and the real-time positioning data of the vehicle can be obtained using positioning equipment. The real-time positioning data in the real-time parking lot information can be used to search for the historical positioning data of the target parking lot. If found, the historical parking lot information corresponding to the target parking lot can be determined.

[0035] S120 : Determine the target vehicle position reliability based on the real-time parking space data in the real-time parking lot information and the historical parking space data in the historical parking lot information.

[0036] In this embodiment, real-time parking space data includes information about the parking space identified by the vehicle at the current moment in the target parking lot, such as the coordinates of the four corner points of the real-time candidate parking space. Historical parking space data includes information about candidate parking spaces identified by the vehicle in the target parking lot prior to the current moment. The target vehicle position confidence indicates the probability that the identified candidate parking space is a real parking space.

[0037] Specifically, the image recognition device identifies the environment surrounding the vehicle, obtains candidate parking spaces and their corresponding data, and generates real-time parking data based on the candidate parking data. The real-time parking data is then compared with historical parking data to determine the reliability of the target vehicle's location.

[0038] Optionally, in order to increase the accuracy of parking space recognition, visual parking spaces can be identified through image recognition equipment, and obstacles around the current vehicle can be perceived in real time through ultrasonic sensors to construct real-time spatial parking spaces, and candidate parking spaces can be determined based on visual parking spaces and spatial parking spaces.

[0039] S130. Determine a parking space corresponding to the target vehicle position reliability that meets a preset condition as a target parking space, wherein the preset condition includes that the target vehicle position reliability is greater than or equal to a preset threshold.

[0040] In this embodiment, the preset threshold is a value set in advance, and the preset condition is a condition set in advance based on actual conditions. The parking space corresponding to the target vehicle position reliability includes the candidate parking space.

[0041] Specifically, the target vehicle position confidence level indicates the probability that an identified candidate parking space is actually a real space. If the probability of an identified candidate parking space being a real space is low, the target vehicle position confidence level is low. Conversely, if the probability of an identified candidate parking space being a real space is high, the target vehicle position confidence level is high. Therefore, a target vehicle position confidence level greater than or equal to a preset threshold is used as a pre-set condition, and parking spaces that meet this condition are identified as target spaces. This effectively prevents misidentification of parking spaces and further improves parking space recognition accuracy by not identifying parking spaces that do not meet the pre-set condition as target spaces.

[0042] Optionally, the target parking space can be presented on the central control display screen of the vehicle, so that the user can park according to the target parking space displayed on the central control display screen.

[0043] The technical solution provided in Example 1 of the present application obtains real-time parking information of a target parking lot and historical parking information corresponding to the target parking lot; determines the target vehicle position reliability based on the real-time parking space data in the real-time parking information and the historical parking space data in the historical parking information; and identifies the parking space corresponding to the target vehicle position reliability that meets preset conditions as the target parking space, wherein the preset conditions include the target vehicle position reliability being greater than or equal to a preset threshold. Considering that when the environment deteriorates, parking space lines may become blurred or incomplete, thereby affecting real-time parking space identification, if parking spaces in the parking lot have been previously identified under relatively good conditions, the historical parking space data can be used to assist in real-time parking space identification. That is, the real-time parking space data from the real-time parking information and the historical parking space data from the historical parking information are combined to comprehensively identify the parking space. This effectively solves the problem in related art parking space identification methods that are affected by the environment, resulting in low efficiency and accuracy in parking space identification. This effectively reduces environmental interference and improves the efficiency and accuracy of parking space identification.

[0044] In some embodiments, historical parking lot information is determined by: using a preset device on a target vehicle to identify the target vehicle's surroundings to obtain environmental identification information; based on the environmental identification information, determining whether a parking space exists; if so, marking the parking lot in the environmental identification information with a preset identifier, and determining historical parking lot information based on the environmental identification information, wherein the preset identifier uniquely identifies the parking lot. This technical solution effectively determines historical parking lot information.

[0045] In this embodiment, the target vehicle is a vehicle that requires identification of its surrounding environment. Preset equipment is mounted on the target vehicle and is used to identify the surrounding environment. The preset equipment may include image recognition equipment and positioning equipment. Environmental identification information includes environmental information that has undergone identification processing. Environmental identification information may include positioning information and visual parking spaces. Preset identifiers include pre-set symbols, such as numbers, letters, etc. For example, the preset identifiers are 1, 2, 3, etc., where the preset identifiers are used to uniquely identify parking lots. Historical parking lot information corresponds one-to-one with real-time parking lot information.

[0046] Specifically, the target vehicle's surrounding environment is identified using pre-set equipment installed on the target vehicle to obtain environmental identification information. For example, image recognition equipment such as a surround-view camera can be used to obtain environmental information surrounding the target vehicle, while positioning equipment can be used to obtain positioning information of the target vehicle. This environmental identification information may include parking space information, environmental information, and positioning information, where environmental information may include information other than parking space information and positioning information. Based on the environmental identification information, it is possible to determine whether a parking space exists around the target vehicle. If a parking space exists, it indicates that the location is a parking lot, and the parking lot in the environmental identification information is then marked with a pre-set identifier. If a parking lot has already been marked, it can be marked in a sequential order. For example, if a parking lot marked as 3 already exists, the identified parking lot should be marked as 4. Historical parking lot information is then determined based on the environmental identification information. For example, the positioning information in the environmental identification information is determined as historical positioning data, the parking space information in the environmental identification information is determined as historical parking space data, and the environmental information in the environmental identification information is determined as historical environmental data.

[0047] Optionally, in order to increase the accuracy of parking space recognition, in addition to identifying visual parking spaces through image recognition equipment, ultrasonic sensors can be used to perceive obstacles around the current vehicle in real time, and use this to construct real-time spatial parking spaces, and then generate parking space information in environmental recognition information based on visual parking spaces and spatial parking spaces.

[0048] In some embodiments, historical parking lot information is stored locally in the current vehicle and / or in a cloud server corresponding to the current vehicle.

[0049] Specifically, the acquired historical parking information can be stored locally on the current vehicle, which helps improve the efficiency of acquiring historical parking information for that vehicle. Alternatively, the historical parking information can be stored on a cloud server corresponding to the current vehicle. Storing the historical parking information on a cloud server allows the current vehicle and other vehicles to share this historical parking information at different points in time. This effectively reduces storage costs for the current vehicle and allows other vehicles to directly access historical parking information from the cloud, effectively saving time and costs and facilitating vehicle identification. The current vehicle in this embodiment can be the target vehicle or a vehicle different from the target vehicle.

[0050] Example 2

[0051] FIG2 is a flow chart of a parking space identification method provided in Example 2 of the present application. This embodiment optimizes and expands upon the aforementioned optional embodiments. This embodiment further illustrates how to determine the target vehicle position reliability based on real-time parking space data in real-time parking information and historical parking space data in historical parking information. The real-time parking space data includes real-time parking space coordinates and real-time vehicle position reliability; the historical parking space data includes historical parking space coordinates and historical vehicle position reliability. As shown in FIG2 , the method includes:

[0052] S210: Acquire real-time parking lot information of a target parking lot and historical parking lot information corresponding to the target parking lot.

[0053] S220: When the coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the historical parking space coordinate, determine whether the historical vehicle position reliability is greater than the real-time vehicle position reliability. If so, execute S230; if less than or equal to the real-time parking space coordinate, execute S240.

[0054] In this embodiment, the threshold range is set according to actual conditions. For example, the threshold range may be set to [x-15cm, x+15cm], where x may be the coordinate value corresponding to the historical parking space coordinate.

[0055] Specifically, when the coordinate value corresponding to the real-time parking space coordinates is within the threshold range corresponding to the historical parking space coordinates, it can be determined that there is a high possibility that a parking space exists at that location. By judging whether the historical vehicle position reliability is greater than the real-time vehicle position reliability, it is determined whether to further determine the candidate parking space corresponding to the real-time vehicle position reliability as the target parking space.

[0056] S230: Using the historical vehicle position reliability as the target vehicle position reliability.

[0057] Specifically, when the historical vehicle position reliability is greater than the real-time vehicle position reliability, it means that when the parking space is identified at the current moment, although the outline of the parking space is identified, it may be affected by the environment, making the parking space line blurred or difficult to distinguish, resulting in a low real-time vehicle position reliability. At this time, in order to better determine the parking space and avoid misidentification, the historical vehicle position reliability is used as the target vehicle confidence to increase the probability of identifying the parking space.

[0058] S240: Determine the target vehicle position reliability based on the real-time vehicle position reliability.

[0059] Specifically, when the historical vehicle position reliability is less than the real-time vehicle position reliability, it indicates that no parking space exists or is not affected by the environment at the current moment, and the identified candidate parking space is closer to the actual parking space. In this case, the target vehicle position reliability can be determined based on the real-time vehicle position reliability. When the historical vehicle position reliability is equal to the real-time vehicle position reliability, the probability that the two identified candidate parking spaces are the same can be determined as the target vehicle position reliability based on the real-time vehicle position reliability or the historical vehicle position reliability.

[0060] S250: Determine a parking space corresponding to a target vehicle position reliability that meets a preset condition as a target parking space, wherein the preset condition includes that the target vehicle position reliability is greater than or equal to a preset threshold.

[0061] The technical solution provided in Example 2 of the present application obtains the real-time parking lot information of the target parking lot and the historical parking lot information corresponding to the target parking lot. When the coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the historical parking space coordinate, it is judged whether the historical vehicle position reliability is greater than the real-time vehicle position reliability. If it is greater, the historical vehicle position reliability is used as the target vehicle position reliability. If it is less than or equal to, the real-time vehicle position reliability is used as the target vehicle position reliability. Through the above technical solution, the impact of poor environment on parking space recognition can be effectively avoided, and the efficiency and accuracy of parking space recognition can be further effectively improved.

[0062] In some embodiments, the real-time parking space data also includes a real-time environment score, and the historical parking space data also includes a historical environment score; the method also includes: if the historical vehicle position reliability is equal to the real-time vehicle position reliability, then determining whether the real-time environment score is greater than the historical environment score; if so, then updating the historical parking space data according to the real-time parking space data corresponding to the real-time environment score.

[0063] In this embodiment, the environmental score is used to determine the parking space based on the parking line and the background corresponding to the parking line. Generally speaking, the more obvious the parking line is and the greater the difference between the parking line and the background corresponding to the parking line is, the higher the environmental score is. Conversely, the less obvious the parking line is and the smaller the difference between the parking line and the background corresponding to the parking line is, the lower the environmental score is.

[0064] Specifically, when the historical vehicle position reliability and the real-time vehicle position reliability are equal, both the historical vehicle position reliability and the real-time vehicle position reliability can be used to determine the target parking space. However, in order to ensure the high quality of the historical parking lot information, it is necessary to further determine whether the real-time environment score is greater than the historical environment score. If so, the historical parking space data is updated according to the real-time parking space data corresponding to the real-time environment score to ensure the high quality of the historical parking lot information.

[0065] Optionally, if the historical vehicle position confidence is less than the real-time vehicle position confidence, the environmental score is no longer determined, and the historical parking space data can be directly updated according to the real-time parking space data corresponding to the real-time environmental confidence.

[0066] In some embodiments, the environmental score is determined by: converting a parking space image into a parking space grayscale image, wherein the parking space image is acquired by an image recognition device and includes parking space lines and a parking space line background corresponding to the parking space lines, with the parking space lines being determined by parking space coordinates; calculating the average parking space line grayscale value and parking space line grayscale standard deviation corresponding to the parking space lines in the parking space grayscale image, as well as the background average grayscale value and background grayscale standard deviation corresponding to the parking space line background; calculating the contrast between the parking space lines and the parking space line background based on the parking space line average grayscale value, parking space line grayscale standard deviation, background average grayscale value, and background grayscale standard deviation; and determining the environmental score based on the contrast. The above technical solution can effectively calculate the environmental score.

[0067] In this embodiment, a parking space image is captured by an image recognition device, which may be a surround-view camera. The parking space image includes parking space lines and a corresponding parking space background. A parking space grayscale image includes an image with only one sampled color per pixel. The environmental score includes a historical environmental score and a real-time environmental score.

[0068] Specifically, Figure 3 is a schematic diagram of a parking space grayscale image provided by an embodiment of the present application. An image of a parking space, such as one captured by a surround-view camera, is acquired through an image recognition device. The image is then converted into a parking space grayscale image to reduce interference from other colors. As shown in Figure 3, the parking space grayscale image includes parking space lines 01 and a corresponding parking space line background 02, where the parking space lines are determined based on parking space coordinates.

[0069] Calculate the average grayscale value l1 and the grayscale standard deviation σ1 of the parking space line corresponding to the parking space line in the parking space grayscale image, and the average grayscale value l2 and the background grayscale standard deviation σ2 corresponding to the parking space line background. And based on the average grayscale value l1 of the parking space line, the grayscale standard deviation σ1 of the parking space line, the average grayscale value l2 of the background and the background grayscale standard deviation σ2, calculate the contrast between the parking space line and the parking space line background, as shown in the following formula: contrast = (l1-l2) / sqrt(σ1 2 +σ2 2 )

[0070] Among them, contrast represents the contrast between the parking space line and the parking space line background.

[0071] Furthermore, the contrast between the parking space line and the parking space line background is used as the environment score.

[0072] Similarly, for real-time environment scoring, a real-time parking space image is obtained through an image recognition device, such as a real-time parking space image taken by a surround-view camera, and the real-time parking space image is converted into a real-time parking space grayscale image to reduce interference from other colors. The real-time parking space grayscale image includes a real-time parking space line and a real-time parking space line background corresponding to the real-time parking space line, wherein the real-time parking space line is determined based on the real-time parking space coordinates.

[0073] Calculate the average grayscale value of the real-time parking space line corresponding to the real-time parking space line in the real-time parking space grayscale image and the real-time parking space line grayscale standard deviation Real-time background average grayscale value corresponding to the real-time parking space line background and real-time background grayscale standard deviation And based on the average gray value of the real-time parking space line Real-time parking space line grayscale standard deviation Real-time background average gray value And real-time background grayscale standard deviation Calculate the real-time contrast between the real-time parking space line and the real-time parking space line background, as shown in the following formula:

[0074] in, Indicates the real-time contrast between the real-time parking space line and the real-time parking space line background.

[0075] Furthermore, the real-time contrast between the real-time parking space line and the real-time parking space line background is used as the real-time environment score.

[0076] Similarly, for historical environment scoring, historical parking space images are obtained through image recognition equipment, such as historical parking space images taken by a surround-view camera, and the historical parking space images are converted into historical parking space grayscale images to reduce interference from other colors. The historical parking space grayscale image includes historical parking space lines and historical parking space line backgrounds corresponding to the historical parking space lines, wherein the historical parking space lines are determined based on the historical parking space coordinates.

[0077] Calculate the average grayscale value of the historical parking space line corresponding to the historical parking space line in the historical parking space grayscale map and the grayscale standard deviation of historical parking space lines The average grayscale value of the historical background corresponding to the historical parking space line background and historical background grayscale standard deviation And based on the average gray value of the historical parking space line Grayscale standard deviation of historical parking space lines Historical background average gray value And the historical background grayscale standard deviation Calculate the historical contrast between the historical parking space line and the historical parking space line background as follows:

[0078] in, Indicates the historical contrast between the historical parking space lines and the historical parking space line background.

[0079] Furthermore, the historical contrast between the historical parking space line and the historical parking space line background is used as the historical environment score.

[0080] In some embodiments, the parking space coordinates include four parking space corner coordinates; and the coordinate value corresponding to the real-time parking space coordinates is within a threshold range corresponding to the historical parking space coordinates, including: the coordinate values ​​of the four parking space corner coordinates corresponding to the real-time parking space coordinates are all within the threshold range corresponding to the four parking space corner coordinates corresponding to the historical parking space coordinates. The above technical solution can effectively ensure that the real-time identified parking space and the historically stored parking space are the same parking space.

[0081] In this embodiment, the four parking space corner coordinates include the coordinates of the four corners of the parking space, and the four parking space corner coordinates include the first corner coordinate, the second corner coordinate, the third corner coordinate, and the fourth corner coordinate. Similarly, the real-time parking space coordinates include the real-time first corner coordinate, the real-time second corner coordinate, the real-time third corner coordinate, and the real-time fourth corner coordinate. Similarly, the historical parking space coordinates include the historical first corner coordinate, the historical second corner coordinate, the historical third corner coordinate, and the historical fourth corner coordinate. The threshold range includes the first threshold range, the second threshold range, the third threshold range, and the fourth threshold range.

[0082] Specifically, the coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates are all within the threshold ranges corresponding to the four parking space corner point coordinates corresponding to the historical parking space coordinates, including the coordinate value of the real-time first corner point coordinates being within the first threshold range corresponding to the historical first corner point coordinates, and the coordinate value of the real-time second corner point coordinates being within the second threshold range corresponding to the historical second corner point coordinates, and the coordinate value of the real-time third corner point coordinates being within the third threshold range corresponding to the historical third corner point coordinates, and the coordinate value of the real-time fourth corner point coordinates being within the fourth threshold range corresponding to the historical fourth corner point coordinates.

[0083] In some embodiments, determining the target vehicle position reliability based on real-time parking space data in the real-time parking information and historical parking space data in the historical parking information also includes: if the coordinate value corresponding to the real-time parking space coordinates is not within a threshold range corresponding to the historical parking space coordinates, then using the historical vehicle position reliability as the target vehicle position reliability. This approach effectively avoids misidentification of parking spaces and utilizes historical parking information to effectively improve the accuracy of parking space recognition.

[0084] Specifically, if any of the coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates is not within the threshold range corresponding to the four parking space corner point coordinates corresponding to the historical parking space coordinates, it indicates that the real-time identified parking space may be inaccurate. However, due to the existence of historical parking space data, considering that the stored historical parking lot information is high-quality data, the historical vehicle position reliability can be directly used as the target vehicle position reliability.

[0085] Optionally, if an interfering line segment exists on the parking space line during real-time parking space identification, two real-time parking space coordinates will be identified, recorded as the first real-time parking space coordinate and the second real-time parking space coordinate, wherein the first real-time parking space coordinate is identified based on the interfering line segment, and the given first real-time vehicle position reliability is greater than the second real-time vehicle position reliability. If at this time the first real-time parking space coordinate and the second real-time parking space coordinate are both within the threshold range corresponding to the historical parking space coordinates, and the first real-time vehicle position reliability and the second real-time vehicle position reliability are both greater than the historical vehicle position reliability, then the target vehicle position reliability can be determined by the following method:

[0086] in, represents the target vehicle position confidence, represents the historical environment score, represents the historical vehicle position reliability, The above method can further improve the accuracy of parking space recognition.

[0087] Optionally, in all of the above embodiments, the real-time parking space data may further include a real-time parking space type, and the historical parking space type may further include a historical parking space type, wherein the real-time parking space type includes a real-time vertical type, a real-time horizontal type, and a real-time diagonal type, and the historical parking space type includes a historical vertical type, a historical horizontal type, and a historical diagonal type. When the real-time parking space type and the historical parking space type are the same, the target vehicle position reliability can be further determined based on other information in the real-time parking space data and other information in the historical parking space data. When the real-time parking space type and the historical parking space type are different, the historical vehicle position reliability can be directly used as the target vehicle position reliability. Therefore, identifying by parking space type can effectively reduce the amount of calculation and improve the efficiency of parking space determination.

[0088] Example 3

[0089] Figure 4 is a schematic diagram of the structure of a parking space identification device provided in Example 3 of the present application. As shown in Figure 4, the device includes: an information acquisition module 31 for acquiring real-time parking information of a target parking lot and historical parking information corresponding to the target parking lot; a confidence determination module 32 for determining the target vehicle position confidence based on the real-time parking space data in the real-time parking information and the historical parking space data in the historical parking information; and a parking space determination module 33 for determining, as the target parking space, a parking space corresponding to a target vehicle position confidence that meets a preset condition, wherein the preset condition includes the target vehicle position confidence being greater than or equal to a preset threshold.

[0090] The technical solution provided in Example 3 of the present application can effectively solve the problem that the parking space recognition method in the related technology is affected by the environment, resulting in low efficiency and accuracy of parking space recognition, effectively reduce environmental interference, and improve the efficiency and accuracy of parking space recognition.

[0091] Optionally, the real-time parking space data includes real-time parking space coordinates and real-time vehicle position reliability; the historical parking space data includes historical parking space coordinates and historical vehicle position reliability.

[0092] Optionally, the confidence determination module 32 includes: a confidence judgment unit, which is used to judge whether the historical vehicle position confidence is greater than the real-time vehicle position confidence when the coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the historical parking space coordinate; a first confidence determination unit, which is used to use the historical vehicle position confidence as the target vehicle position confidence if the historical vehicle position confidence is greater than the real-time vehicle position confidence; and a second confidence determination unit, which is used to determine the target vehicle position confidence based on the real-time vehicle position confidence if the historical vehicle position confidence is less than or equal to the real-time vehicle position confidence.

[0093] Optionally, the real-time parking space data also includes a real-time environment score, and the historical parking space data also includes a historical environment score.

[0094] Optionally, the parking space identification device also includes: a scoring judgment module, which is used to judge whether the real-time environment score is greater than the historical environment score if the historical vehicle position reliability is equal to the real-time vehicle position reliability; and a data updating module, which is used to update the historical parking space data according to the real-time parking space data corresponding to the real-time environment score if so.

[0095] Optionally, the environmental score is determined by: converting a parking space image into a parking space grayscale image, wherein the parking space image is acquired by an image recognition device, the parking space image includes parking space lines and parking space line backgrounds corresponding to the parking space lines, and the parking space lines are determined by parking space coordinates; calculating the parking space line average grayscale value and parking space line grayscale standard deviation corresponding to the parking space lines in the parking space grayscale image, as well as the background average grayscale value and background grayscale standard deviation corresponding to the parking space line background; calculating the contrast between the parking space lines and the parking space line background based on the parking space line average grayscale value, the parking space line grayscale standard deviation, the background average grayscale value and the background grayscale standard deviation; and determining the environmental score based on the contrast.

[0096] Optionally, the parking space coordinates include four parking space corner point coordinates.

[0097] Optionally, the coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the historical parking space coordinate, including: the coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinate are all within the threshold range corresponding to the four parking space corner point coordinates corresponding to the historical parking space coordinate.

[0098] Optionally, historical parking lot information is determined in the following manner: using a preset device of the target vehicle to identify the surrounding environment of the target vehicle to obtain environmental identification information; based on the environmental identification information, determining whether there is a parking space; if so, using a preset identifier to mark the parking lot in the environmental identification information, and determining historical parking lot information based on the environmental identification information, wherein the preset identifier is used to indicate the unique identity of the parking lot.

[0099] Optionally, historical parking lot information is stored locally in the current vehicle and / or in a cloud server corresponding to the current vehicle.

[0100] Optionally, the confidence determination module 32 further includes: a fourth confidence determination unit, configured to use the historical vehicle position confidence as the target vehicle position confidence if the coordinate value corresponding to the real-time parking space coordinate is not within a threshold range corresponding to the historical parking space coordinate.

[0101] Optionally, the second confidence determination unit is specifically used to determine the target vehicle position reliability based on the historical environment score, the historical vehicle position reliability and the second real-time vehicle position reliability if both the first real-time vehicle position reliability and the second real-time vehicle position reliability are greater than the historical vehicle position reliability, wherein the first real-time vehicle position reliability is greater than the second real-time vehicle position reliability, and the first parking space coordinate corresponding to the first real-time vehicle position reliability and the second parking space coordinate corresponding to the second real-time vehicle position reliability are both within the threshold range corresponding to the historical parking space coordinates.

[0102] The parking space recognition device provided in the embodiments of the present application can execute the parking space recognition method provided in any embodiment of the present application, and has the functional modules and effects corresponding to the execution method.

[0103] Example 4

[0104] FIG5 is a schematic diagram of the structure of a parking space identification device 10 provided in accordance with an embodiment of the present application. The parking space identification device may be an electronic device intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0105] As shown in FIG5 , the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, that is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0106] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0107] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the parking space recognition method.

[0108] In some embodiments, the parking space identification method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the parking space identification method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the parking space identification method in any other appropriate manner (e.g., via firmware).

[0109] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0113] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0114] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0115] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved. This is not limited herein.

Claims

1. A parking space recognition method, comprising: Acquire real-time parking lot information of a target parking lot and historical parking lot information corresponding to the target parking lot; Determining the target vehicle position reliability according to the real-time parking space data in the real-time parking lot information and the historical parking space data in the historical parking lot information; The parking space corresponding to the target vehicle position reliability that meets the preset condition is determined as the target parking space, wherein the preset condition includes that the target vehicle position reliability is greater than or equal to a preset threshold.

2. The method according to claim 1, wherein: The real-time parking space data includes real-time parking space coordinates and real-time vehicle position reliability; the historical parking space data includes historical parking space coordinates and historical vehicle position reliability; Determining the target vehicle position reliability according to the real-time parking space data in the real-time parking lot information and the historical parking space data in the historical parking lot information includes: When the coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the historical parking space coordinate, determining whether the historical vehicle position reliability is greater than the real-time vehicle position reliability; If the historical vehicle position reliability is greater than the real-time vehicle position reliability, the historical vehicle position reliability is used as the target vehicle position reliability; If the historical vehicle position reliability is less than or equal to the real-time vehicle position reliability, the target vehicle position reliability is determined according to the real-time vehicle position reliability.

3. The method according to claim 2, wherein: The real-time parking space data also includes a real-time environment score, and the historical parking space data also includes a historical environment score; The method further comprises: If the historical vehicle position reliability is equal to the real-time vehicle position reliability, then determining whether the real-time environment score is greater than the historical environment score; If so, the historical parking space data is updated according to the real-time parking space data corresponding to the real-time environment score.

4. The method according to claim 2, wherein: The environmental score is determined by: Converting a parking space image into a parking space grayscale image, wherein the parking space image is acquired by an image recognition device, the parking space image includes a parking space line and a parking space line background corresponding to the parking space line, and the parking space line is determined by the parking space coordinates; Calculate the parking space line average grayscale value and parking space line grayscale standard deviation corresponding to the parking space line in the parking space grayscale image, and the background average grayscale value and background grayscale standard deviation corresponding to the parking space line background; Based on the average gray value of the parking space line, the gray standard deviation of the parking space line, the average gray of the background The contrast between the parking space line and the parking space line background is calculated by using the value and the background grayscale standard deviation; Based on the contrast, the environmental score is determined.

5. The method according to claim 2, wherein: The parking space coordinates include the coordinates of four parking space corner points; The coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the historical parking space coordinate, including: The coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates are all within the threshold ranges corresponding to the four parking space corner point coordinates corresponding to the historical parking space coordinates.

6. The method according to claim 1, wherein: The historical parking lot information is determined in the following manner: Using a preset device of the target vehicle to identify the surrounding environment of the target vehicle to obtain environment identification information; Based on the environment recognition information, determining whether there is a parking space; If so, the parking lot in the environment identification information is marked with a preset identifier, and historical parking lot information is determined based on the environment identification information, wherein the preset identifier is used to indicate a unique identity of the parking lot.

7. The method according to claim 1, wherein: The historical parking lot information is stored locally in the current vehicle and / or in a cloud server corresponding to the current vehicle.

8. The method according to claim 2, wherein: The determining the target vehicle position reliability according to the real-time parking space data in the real-time parking lot information and the historical parking space data in the historical parking lot information further includes: If the coordinate value corresponding to the real-time parking space coordinate is not within the threshold range corresponding to the historical parking space coordinate, the historical vehicle position reliability is used as the target vehicle position reliability.

9. The method according to claim 2, wherein: If the historical vehicle position reliability is less than the real-time vehicle position reliability, determining the target vehicle position reliability according to the real-time vehicle position reliability includes: If the first real-time vehicle position reliability and the second real-time vehicle position reliability are both greater than the historical vehicle position reliability, the target vehicle position reliability is determined according to the historical environment score, the historical vehicle position reliability and the second real-time vehicle position reliability, wherein the first real-time vehicle position reliability is greater than the second real-time vehicle position reliability, and the first parking position coordinate corresponding to the first real-time vehicle position reliability and the second parking position coordinate corresponding to the second real-time vehicle position reliability are both within the threshold range corresponding to the historical parking position coordinates.

10. A parking space recognition device, comprising: An information acquisition module, configured to acquire real-time parking lot information of a target parking lot and historical parking lot information corresponding to the target parking lot; A confidence determination module, configured to determine the target vehicle position confidence according to the real-time parking space data in the real-time parking information and the historical parking space data in the historical parking information; The parking space determination module is configured to determine the parking space corresponding to the target vehicle position reliability that meets the preset condition as the target parking space, wherein the preset condition includes that the target vehicle position reliability is greater than or equal to a preset threshold.

11. A parking space recognition device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the parking space recognition method according to any one of claims 1 to 9.

12. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the parking space recognition method according to any one of claims 1 to 9 when executed.

Images