Parking space recognition method, device, equipment, and storage medium

Abstract

A parking space recognition method, device, equipment, and storage medium includes the steps of: acquiring real-time parking information for a target parking lot and past parking information corresponding to the target parking lot (S110); determining a target parking space certainty factor based on real-time parking space data in the real-time parking information and past parking space data in the past parking information (S120); and determining, as the target parking space, a parking space corresponding to the target parking space certainty factor that satisfies predetermined conditions, including the target parking space certainty factor being equal to or greater than a predetermined threshold (S130).

Description

[Technical Field]

[0001] This application claims priority from a Chinese patent application bearing application number 202311611425.1, filed with the China Patent Office on November 28, 2023, the entire contents of which are incorporated herein by reference.

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

[0003] With the rapid development of artificial intelligence technology, automatic parking technology has been widely applied to many vehicles.Automatic parking technology for vehicles mainly involves three aspects: parking space recognition, trajectory planning, and parking control.Of these, parking space recognition is the foundation of automatic parking technology, and its accuracy affects the overall performance of automatic parking technology.

[0004] However, in the parking space recognition method of the related art, the efficiency and accuracy of its parking space recognition are greatly affected by the environment. For example, the efficiency and accuracy of parking space recognition may be relatively high in underground parking lots of relatively new housing complexes, open-air parking lots during the day, and parking lots near nightclubs during the day. However, in some old housing complexes, the parking frame lines are blurred due to long-term neglect of repairs or long-term dragging of cargo. In addition, at night, in some open-air parking lots, the lighting is insufficient (or there is no lighting), so the contrast between the parking frame lines and the ground is low, and the lighting pollution is severe, making it difficult to distinguish parking spaces. All of these environments pose difficulties for the parking space recognition method, resulting in a relatively low efficiency and accuracy of parking space recognition, which in turn affects users' parking. Summary of the Invention [Problem to be solved by the invention]

[0005] The present application provides a parking space recognition method, device, equipment and storage medium to solve the problem of low efficiency and accuracy of parking space recognition due to environmental influences in related parking space recognition methods. [Means for solving the problem]

[0006] According to one aspect of the present application, Acquiring real-time parking information of the target parking lot and historical parking information corresponding to the target parking lot; Determining a target parking space certainty factor based on real-time parking space data in the real-time parking information and historical parking space data in the historical parking information; determining, as the target parking space, a parking space corresponding to a target parking space certainty degree that satisfies a predetermined condition, including the target parking space certainty degree being equal to or greater than a predetermined threshold value; To provide a parking space recognition method.

[0007] According to another aspect of the present application, an information acquisition module configured to acquire real-time parking information of the target parking lot and historical parking information corresponding to the target parking lot; a certainty determination module configured to determine a target parking space certainty based on real-time parking space data in the real-time parking information and historical parking space data in the historical parking information; a parking space determination module configured to determine, as a target parking space, a parking space corresponding to a target parking space certainty degree that satisfies a predetermined condition, including the target parking space certainty degree being equal to or greater than a predetermined threshold value; To provide a parking space recognition device.

[0008] According to another aspect of the present application, at least one processor; a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by at least one processor, and when the computer program is executed by the at least one processor, the at least one processor can execute the parking space recognition method according to any one of the embodiments of the present application. Provides parking space recognition equipment.

[0009] According to another aspect of the present application, A method for detecting a parking space according to any one of the embodiments of the present application, comprising: storing computer instructions for, when executed by a processor, implementing the parking space recognition method according to any one of the embodiments of the present application; A computer-readable storage medium is provided. [Effects of the Invention]

[0010] The technical aspects of the present invention involve acquiring real-time parking information for a target parking lot and past parking information corresponding to the target parking lot, determining a target parking space certainty based on the real-time parking space data in the real-time parking information and the past parking space data in the past parking information, and determining as the target parking space a parking space corresponding to the target parking space certainty that satisfies certain conditions, including that the target parking space certainty is equal to or greater than a predetermined threshold. Considering that a poor environment may cause parking frame lines to become blurred or missing, which may ultimately affect real-time parking space recognition, if a parking space in this parking lot has previously been recognized under relatively good environmental conditions, the past parking space data can be used to assist in real-time parking space recognition. That is, by combining the real-time parking space data from the real-time parking information and the past parking space data from the past parking information to comprehensively recognize a parking space, the problem of low efficiency and accuracy of parking space recognition due to environmental influences in parking space recognition methods in related technologies can be effectively solved, effectively reducing environmental interference and improving the efficiency and accuracy of parking space recognition.

[0011] It should be understood that the contents described in this section are not intended to identify key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become more readily apparent from the following specification. [Brief explanation of the drawings]

[0012] In order to more clearly explain the technical aspects of the embodiments of the present application, the following briefly introduces the drawings that need to be used in the description of the embodiments. The drawings in the following description are only some embodiments of the present application, and it is obvious to those skilled in the art that other drawings can also be obtained based on these drawings without any creative work. [Figure 1] 1 is a flowchart of a parking space recognition method according to a first embodiment of the present invention. [Figure 2] 10 is a flowchart of a parking space recognition method according to a second embodiment of the present invention. [Figure 3] FIG. 1 is a schematic diagram of a parking space gradation diagram according to an embodiment of the present application. [Figure 4] FIG. 10 is a structural schematic diagram of a parking space recognition device according to a third embodiment of the present invention. [Figure 5] 1 is a structural schematic diagram of a parking space recognition device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0013] In order to enable those skilled in the art to better understand the aspects of the present application, the following will clearly and completely describe the technical aspects of the embodiments of the present application in conjunction with the drawings in the embodiments of the present application, but it is clear that the described embodiments are only a part of the embodiments of the present application, and do not cover all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without any creative work shall fall within the scope of protection of the present application.

[0014] It should be noted that the terms "first," "second," etc. in the specification, claims, and drawings of this application are not necessarily used to describe a particular order or sequence, but are merely used to distinguish between similar objects. Such used data may be substituted where appropriate, and it should be understood that the embodiments of this application described herein may be practiced in orders other than those illustrated or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusions; for example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to the explicitly recited steps or units, but may include other steps or units that are not explicitly recited or that are inherent to the process, method, product, or apparatus. [Example]

[0015] 1 is a flowchart of a parking space recognition method according to a first embodiment of the present application. This embodiment may be applied to the case of recognizing a parking space. The method may be performed by a parking space recognition device. The parking space recognition device may be implemented in the form of hardware and / or software, and the parking space recognition device may be disposed in the parking space recognition equipment. Preferably, the parking space recognition device may be a vehicle, or the parking space recognition device may be integrated into a vehicle. As shown in FIG. 1, the method includes:

[0016] S110, obtain real-time parking information of the target parking lot and past parking information corresponding to the target parking lot.

[0017] In this embodiment, the target parking lot is a parking lot where the vehicle is currently recognizing a parking space. The real-time parking lot information may include information related to the target parking lot recognized by the vehicle at the current time. For example, the real-time parking lot information may include real-time environmental data, real-time parking space data, and real-time positioning data. The real-time environmental data is data related to the environment other than the real-time parking space data and the real-time positioning data. For example, the real-time environmental data may include parking lot signs, entrance security guards, and entrance car gates. The past parking lot information includes information related to the target parking lot recognized by the vehicle at a time before the current time. The past parking lot information includes past environmental data, past parking space data, and past positioning data. The past environmental data is data related to the environment other than the past parking space data and the past positioning data. For example, the content of the real-time environmental data corresponds one-to-one to the real-time environmental data.

[0018] Specifically, real-time parking information can be obtained by the relevant equipment in the vehicle recognizing the current parking lot. For example, real-time environmental data of the target parking lot can be obtained using image recognition equipment such as a surround view camera, and real-time positioning data of the vehicle can be obtained using positioning equipment. The real-time positioning data in the real-time parking information can be used to search for past positioning data of the target parking lot, and once searched, past parking information corresponding to the target parking lot can be determined.

[0019] S120: determining a target parking space certainty factor based on real-time parking space data in the real-time parking information and past parking space data in the past parking information;

[0020] In this embodiment, the real-time parking space data includes information related to the parking space in the target parking lot recognized by the vehicle at the current time, such as the coordinates of the four corner points of the candidate parking space recognized in real time. The past parking space data includes information related to the candidate parking space in the target parking lot recognized by the vehicle at a time before the current time. The target parking space certainty indicates the probability that the recognized candidate parking space is an actual parking space.

[0021] Specifically, the system uses an image recognition device to recognize the environment around the vehicle, acquires candidate parking spaces and related data corresponding to the candidate parking spaces, generates real-time parking space data based on the related data corresponding to the candidate parking spaces, and then determines the target parking space certainty factor by comparing the real-time parking space data with past parking space data.

[0022] Preferably, in order to increase the accuracy of parking space recognition, a visual parking space may be recognized by an image recognition device, and a real-time spatial parking space may be constructed by detecting obstacles around the current vehicle in real time by an ultrasonic sensor, and candidate parking spaces may be determined based on the visual parking space and the spatial parking space.

[0023] S130: determining, as a target parking space, a parking space corresponding to the target parking space certainty degree that satisfies predetermined conditions including that the target parking space certainty degree is equal to or greater than a predetermined threshold value.

[0024] In this embodiment, the predetermined threshold is a predetermined value, and the predetermined condition is a predetermined condition according to the actual situation. The parking spaces corresponding to the target parking space certainty degree include the candidate parking spaces.

[0025] Specifically, the target parking space certainty indicates the probability that the recognized candidate parking space is an actual parking space. If the probability that the recognized candidate parking space is an actual parking space is relatively low, the target parking space certainty is somewhat low. Conversely, if the probability that the recognized candidate parking space is an actual parking space is high, the target parking space certainty is high. Thus, a predetermined condition is set such that the target parking space certainty is equal to or greater than a predetermined threshold, and a parking space that satisfies this condition is determined as the target parking space. This effectively avoids situations where the parking space is erroneously recognized, and prevents a parking space that does not satisfy the predetermined condition from being determined as the target parking space, thereby further improving the accuracy of parking space recognition.

[0026] Preferably, the target parking space may appear on the vehicle's console display so that the user parks based on the target parking space displayed on the console display.

[0027] The technical aspect of Example 1 of the present application involves acquiring real-time parking information for a target parking lot and past parking information corresponding to the target parking lot, determining a target parking space certainty based on the real-time parking space data in the real-time parking lot information and the past parking space data in the past parking lot information, and determining as the target parking space a parking space corresponding to the target parking space certainty that satisfies predetermined conditions, including that the target parking space certainty is equal to or greater than a predetermined threshold. Considering that a poor environment may cause the parking frame lines to become blurred or missing, which may ultimately affect real-time parking space recognition, if a parking space in this parking lot has previously been recognized under relatively good environmental conditions, the past parking space data can be used to assist in real-time parking space recognition. That is, by combining the real-time parking space data from the real-time parking lot information and the past parking space data from the past parking lot information to comprehensively recognize the parking space, the problem of low efficiency and accuracy of parking space recognition due to environmental influences in parking space recognition methods in related technologies can be effectively solved, effectively reducing environmental interference and improving the efficiency and accuracy of parking space recognition.

[0028] In some embodiments, the past parking information is determined by: recognizing the surrounding environment of the target vehicle using a predetermined device of the target vehicle to obtain environmental recognition information; determining whether a parking space exists based on the environmental recognition information; and, if a parking space exists, marking the parking space in the environmental recognition information using a predetermined mark to indicate the unique identity of the parking space; and determining the past parking information based on the environmental recognition information. The above technical aspects make it possible to effectively determine the past parking information.

[0029] In this embodiment, the target vehicle is a vehicle that needs to recognize the surrounding environment. The predetermined device is installed in the target vehicle and is used to recognize the surrounding environment. The predetermined device may include an image recognition device, a positioning device, etc. The environment recognition information includes recognized and processed environment information, and the environment recognition information may include positioning information and visual parking spaces. The predetermined sign includes a pre-set symbol, which may be a number, an alphabet, etc., for example, the predetermined sign is 1, 2, 3, etc., and is used to indicate the unique identity of the parking lot. The historical parking information corresponds one-to-one to the real-time parking information.

[0030] Specifically, environmental recognition information can be obtained by recognizing the surrounding environment of the target vehicle using a predetermined device installed in the target vehicle. For example, environmental information about the surroundings of the target vehicle can be obtained using an image recognition device such as a surround-view camera, and positioning information about the target vehicle can be obtained using a positioning device. The environmental recognition information may include parking space information, environmental information, and positioning information, where the environmental information may be information other than parking space information and positioning information. Based on the environmental recognition information, it can be determined whether a parking space exists around the target vehicle. If a parking space exists and is proven to be a parking space, the parking space is marked in the environmental recognition information using a predetermined sign. If there are previously marked parking spaces, they can be marked in order. For example, if there is a parking space marked 3, the currently recognized parking space should be marked 4. Furthermore, past parking lot information is determined based on the environmental recognition information. For example, the positioning information in the environmental recognition information is determined as past positioning data, the parking space information in the environmental recognition information is determined as past parking space data, and the environmental information in the environmental recognition information is determined as past environment data.

[0031] Preferably, in order to increase the accuracy of parking space recognition, in addition to recognizing the visual parking space by the image recognition equipment, a real-time spatial parking space may be constructed by combining with an ultrasonic sensor to sense obstacles around the current vehicle in real time, and then parking space information in the environment recognition information may be generated based on the visual parking space and the spatial parking space.

[0032] In some embodiments, the historical parking information is stored locally on the current vehicle and / or on a cloud server corresponding to the current vehicle.

[0033] Specifically, the acquired past parking information may be stored locally in the current vehicle, which is advantageous to improving the efficiency of the vehicle acquiring past parking information. The past parking information may be stored in a cloud server corresponding to the current vehicle. Storing the past parking information in the cloud server allows the current vehicle and other vehicles to share the past parking information at different times, which effectively reduces storage costs for the current vehicle and allows other vehicles to directly acquire past parking information from the cloud, effectively saving time and cost and facilitating vehicles' recognition of parking spaces. In this embodiment, the current vehicle may be a target vehicle or a vehicle different from the target vehicle. [Example]

[0034] 2 is a flowchart of a parking space recognition method according to a second embodiment of the present invention, which is an optimization and extension of the above-mentioned preferred embodiments. This embodiment describes in detail how to determine a target parking space certainty factor based on real-time parking space data in real-time parking information and past parking space data in past parking information, where the real-time parking space data includes real-time parking space coordinates and real-time parking space certainty factor, and the past parking space data includes past parking space coordinates and past parking space certainty factor. As shown in FIG. 2, the method includes:

[0035] S210, real-time parking information of the target parking lot and historical parking information corresponding to the target parking lot are obtained.

[0036] S220: If the coordinate value corresponding to the real-time parking space coordinate is within the threshold range corresponding to the past parking space coordinate, determine whether the past parking space certainty factor is greater than the real-time parking space certainty factor. If it is greater, execute S230; if it is equal to or less than, execute S240.

[0037] In this embodiment, the threshold range is set according to the actual situation. For example, the threshold range may be set as follows: Formula 1, where x may be a coordinate value corresponding to the previous parking space coordinate.

[0038]

number

[0039] Specifically, when the coordinate value corresponding to the real-time parking space coordinate is within a threshold range corresponding to the past parking space coordinate, it can be determined that there is a relatively high possibility that a parking space exists at that position, and by determining whether the past parking space certainty is greater than the real-time parking space certainty, it is further determined whether to determine the candidate parking space corresponding to the real-time parking space certainty as the target parking space.

[0040] S230: The past parking space certainty factor is set as the target parking space certainty factor.

[0041] Specifically, if the past parking space certainty factor is greater than the real-time parking space certainty factor, it means that when parking space recognition is performed at the current time, the outline of the parking space is recognized, but due to the influence of the environment, the parking frame line of the parking space may be blurred or difficult to distinguish, which may result in a slightly lower real-time parking space certainty factor. In this case, in order to better determine the parking space and avoid erroneous recognition situations, the past parking space certainty factor is set as the target parking space certainty factor, thereby increasing the probability of recognizing the parking space.

[0042] S240, determining a target parking space confidence level based on the real-time parking space confidence level;

[0043] Specifically, if the past parking space certainty is smaller than the real-time parking space certainty, it indicates that there is no environmental influence or is not influenced by the environment when recognizing the parking space at the current time, and the recognized candidate parking space is closer to the actual parking space, and at this time, the target parking space certainty can be determined based on the real-time parking space certainty. Also, if the past parking space certainty is equal to the real-time parking space certainty, the probability that the candidate parking space recognized twice is the same as the actual parking space can be determined as the target parking space certainty based on the real-time parking space certainty or the past parking space certainty.

[0044] At S250, a parking space corresponding to a target parking space certainty factor that satisfies predetermined conditions, including the target parking space certainty factor being equal to or greater than a predetermined threshold, is determined as the target parking space.

[0045] The technical aspect of Example 2 of the present application acquires real-time parking information of a target parking lot and past parking information corresponding to the target parking lot, and when the coordinate value corresponding to the real-time parking space coordinate is within a threshold range corresponding to the past parking space coordinate, determines whether the past parking space certainty factor is greater than the real-time parking space certainty factor, and if it is greater, sets the past parking space certainty factor as the target parking space certainty factor, and if it is equal to or less than that, sets the real-time parking space certainty factor as the target parking space certainty factor. The above technical aspect can effectively avoid the influence of poor environmental conditions on parking space recognition, and further effectively improve the efficiency and accuracy of parking space recognition.

[0046] In some embodiments, the real-time parking space data further includes a real-time environmental score, and the historical parking space data further includes a historical environmental score, and the method further includes, when the historical parking space confidence is equal to the real-time parking space confidence, determining whether the real-time environmental score is greater than the historical environmental score, and if greater, updating the historical parking space data based on the real-time parking space data corresponding to the real-time environmental score.

[0047] In this embodiment, the environmental score is used to determine the parking space based on the parking frame lines and the background corresponding to the parking frame lines. Generally, the more obvious the parking frame lines are and the more distinct the parking frame lines are from the background corresponding to the parking frame lines, the higher the environmental score will be. Conversely, the less obvious the parking frame lines are and the less distinct the parking frame lines are from the background corresponding to the parking frame lines, the lower the environmental score will be.

[0048] Specifically, when the past parking space certainty factor and the real-time parking space certainty factor are equal, the target parking space can be determined using either the past parking space certainty factor or the real-time parking space certainty factor. However, in order to ensure the quality of the past parking space information, it is necessary to further determine whether the real-time environmental score is greater than the past environmental score. If it is greater, the past parking space data is updated based on the real-time parking space data corresponding to the real-time environmental score, thereby ensuring the quality of the past parking space information.

[0049] Preferably, if the past parking space certainty factor is less than the real-time parking space certainty factor, no environmental scoring determination is made and the past parking space data can be updated directly based on the real-time parking space data corresponding to the real-time environmental certainty factor.

[0050] In some embodiments, the environmental score is determined by: converting a parking space image, which is acquired by an image recognition device and includes a parking frame line determined from the parking space coordinates and a parking frame line background corresponding to the parking frame line, into a parking space gradation map; calculating a parking frame line average gray value and a parking frame line gray standard deviation corresponding to the parking frame line in the parking space gradation map, and a background average gray value and a background gray standard deviation corresponding to the parking frame line background; calculating a contrast between the parking frame line and the parking frame line background based on the parking frame line average gray value, the parking frame line gray standard deviation, the background average gray value, and the background gray standard deviation; and determining an environmental score based on the contrast.

[0051] In this embodiment, the parking space image is acquired by an image recognition device, which may be a surround view camera, and the parking space image includes parking lines and a parking line background corresponding to the parking lines. The parking space gradient map includes an image in which each pixel has only one sampled color. The environmental scoring includes past environmental scoring and real-time environmental scoring.

[0052] Specifically, Fig. 3 is a schematic diagram of a parking space gradation map according to an embodiment of the present application. A parking space image is acquired by an image recognition device, for example, by a surround view camera, and converted into a parking space gradation map, thereby reducing the interference of other colors. As shown in Fig. 3, the parking space gradation map includes a parking frame line 01 and a parking frame line background 02 corresponding to the parking frame line, among which the parking frame line is determined according to the parking space coordinates.

[0053] A parking frame line average gradation value l1 and a parking frame line gradation standard deviation σ1 corresponding to the parking frame line in the parking space gradation map, and a background average gradation value l2 and a background gradation standard deviation σ2 corresponding to the parking frame line background are calculated. Then, the contrast between the parking frame line and the parking frame line background is calculated based on the parking frame line average gradation value l1, the parking frame line gradation standard deviation σ1, the background average gradation value l2, and the background gradation standard deviation σ2 as shown in the following formula.

[0054]

number

[0055] Among them, the contrast indicates the contrast between the parking frame line and the background of the parking frame line.

[0056] In turn, the contrast between the parking frame line and the background of the parking frame line is used as the environmental score.

[0057] Similarly, for real-time environment scoring, a real-time parking space image is obtained by an image recognition device, and the real-time parking space image is captured by, for example, a surround view camera, and the real-time parking space image is converted into a real-time parking space gradation map, thereby reducing the interference of other colors, and the real-time parking space gradation map includes a real-time parking frame line and a real-time parking frame line background corresponding to the real-time parking frame line, among which the real-time parking frame line is determined according to the real-time parking space coordinates.

[0058] A real-time parking frame line average gradation value l1 dot and a real-time parking frame line gradation standard deviation σ1 dot corresponding to the real-time parking frame line in the real-time parking space gradation map, and a real-time background average gradation value l2 dot and a real-time background gradation standard deviation σ2 dot corresponding to the real-time parking frame line background are calculated. Then, a real-time contrast between the real-time parking frame line and the real-time parking frame line background is calculated based on the real-time parking frame line average gradation value l1 dot, the real-time parking frame line gradation standard deviation σ1 dot, the real-time background average gradation value l2 dot, and the real-time background gradation standard deviation σ2 dot according to the following formula:

[0059]

number

[0060] Among them, the contrast dot indicates the real-time contrast between the real-time parking frame line and the real-time parking frame line background.

[0061] Furthermore, the real-time contrast between the real-time parking frame line and the real-time parking frame line background is used as the real-time environment scoring.

[0062] Similarly, for the past environment scoring, a past parking space image is obtained by an image recognition device, and the past parking space image is photographed by, for example, a surround view camera, and the past parking space image is converted into a past parking space gradation map, thereby reducing the interference of other colors, and the past parking space gradation map includes a past parking frame line and a past parking frame line background corresponding to the past parking frame line, among which the past parking frame line is determined based on the past parking space coordinates.

[0063] A past parking frame line average gradation value l1 bar and a past parking frame line gradation standard deviation σ1 bar corresponding to the past parking frame line in the past parking space gradation map, and a past background average gradation value l2 bar and a past background gradation standard deviation σ2 bar corresponding to the past parking frame line background are calculated. Then, according to the following formula, a past contrast between the past parking frame line and the past parking frame line background is calculated based on the past parking frame line average gradation value l1 bar, the past parking frame line gradation standard deviation σ1 bar, the past background average gradation value l2 bar, and the past background gradation standard deviation σ2 bar.

[0064]

number

[0065] Among them, the contrast bar indicates the contrast between the past parking frame line and the background of the past parking frame line.

[0066] Furthermore, the past contrast between the past parking frame line and the background of the past parking frame line is used as the past environment score.

[0067] In some embodiments, the parking space coordinates include four parking space corner point coordinates, and the coordinate values ​​corresponding to the real-time parking space coordinates being within a threshold range corresponding to the past parking space coordinates include the coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates all being within a threshold range corresponding to the four parking space corner point coordinates corresponding to the past parking space coordinates.The above technical aspects can effectively ensure that the parking space recognized in real time and the parking space stored in the past are the same parking space.

[0068] In this embodiment, the four parking space corner point coordinates include coordinates of the four corners of the parking space, and the four parking space corner point coordinates include a first corner point coordinate, a second corner point coordinate, a third corner point coordinate, and a fourth corner point coordinate. Similarly, the real-time parking space coordinates include a real-time first corner point coordinate, a real-time second corner point coordinate, a real-time third corner point coordinate, and a real-time fourth corner point coordinate. Similarly, the past parking space coordinates include a past first corner point coordinate, a past second corner point coordinate, a past third corner point coordinate, and a past fourth corner point coordinate. The threshold range includes a first threshold range, a second threshold range, a third threshold range, and a fourth threshold range.

[0069] Specifically, when the coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates are all within the threshold range corresponding to the four parking space corner point coordinates corresponding to the past parking space coordinates, it includes the coordinate value of the real-time first corner point coordinate being within the first threshold range corresponding to the past first corner point coordinate, and the coordinate value of the real-time second corner point coordinate being within the second threshold range corresponding to the past second corner point coordinate, and the coordinate value of the real-time third corner point coordinate being within the third threshold range corresponding to the past third corner point coordinate, and the coordinate value of the real-time fourth corner point coordinate being within the fourth threshold range corresponding to the past fourth corner point coordinate.

[0070] In some embodiments, determining the target parking space certainty based on the real-time parking space data in the real-time parking information and the past parking space data in the past parking information further includes: when the coordinate value corresponding to the real-time parking space coordinate is not within a threshold range corresponding to the past parking space coordinate, setting the past parking space certainty as the target parking space certainty. The above-mentioned aspect can effectively avoid the situation of erroneous parking space recognition and effectively improve the accuracy rate of parking space recognition by utilizing the past parking information.

[0071] 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 past parking space coordinates, it indicates that the parking space recognized in real time may be inaccurate. However, since past parking space data exists, and the stored past parking space information is relatively high quality data, the past parking space certainty can be directly used as the target parking space certainty at this time.

[0072] Preferably, during real-time parking space recognition, if there is an interfering line with the parking frame line, two real-time parking space coordinates will be recognized, which will be denoted as first real-time parking space coordinates and second real-time parking space coordinates, among which the first real-time parking space coordinates are recognized based on the interfering line, and the given first real-time parking space certainty is greater than the second real-time parking space certainty, when the first real-time parking space coordinates and the second parking space coordinates are both within a threshold range corresponding to the previous parking space coordinates, and the first real-time parking space certainty and the second real-time parking space certainty are both greater than the previous parking space certainty, then the target parking space certainty may be determined by the following manner:

[0073]

number

[0074] Wherein, ∂ indicates the target parking space confidence level, the contrast bar indicates the past environment score, ∂ bar indicates the past parking space confidence level, and ∂2 indicates the second real-time parking space confidence level. The above method further improves the accuracy of parking space recognition.

[0075] Preferably, in all the above embodiments, the real-time parking space data may further include a real-time parking space type, and the past parking space data may further include a past parking space type, of which 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 past parking space type includes a past vertical type, a past horizontal type, and a past diagonal type. If the real-time parking space type and the past parking space type are the same, the target parking space certainty factor may be determined based on other information in the real-time parking space data and other information in the past parking space data. If the real-time parking space type and the past parking space type are different, the past parking space certainty factor may be directly used as the target parking space certainty factor. This effectively reduces the amount of calculation by recognizing the parking space type, and improves the efficiency of parking space determination. [Example]

[0076] Fig. 4 is a structural schematic diagram of a parking space recognition device according to a third embodiment of the present invention. As shown in Fig. 4, the device includes: an information acquisition module 31 used to acquire real-time parking information of a target parking lot and past parking information corresponding to the target parking lot; a certainty determination module 32 used to determine a target parking space certainty based on real-time parking space data in the real-time parking lot information and past parking space data in the past parking lot information; and a parking space determination module 33 used to determine, as a target parking space, a parking space corresponding to a target parking space certainty that satisfies predetermined conditions, including that the target parking space certainty is equal to or greater than a predetermined threshold.

[0077] The technical aspect of Example 3 of the present application effectively solves the problem that the efficiency and accuracy of parking space recognition are low due to environmental influences in the parking space recognition method in the related art, and can effectively reduce environmental interference and improve the efficiency and accuracy of parking space recognition.

[0078] Preferably, the real-time parking space data includes real-time parking space coordinates and real-time parking space confidence levels, and the past parking space data includes past parking space coordinates and past parking space confidence levels.

[0079] Preferably, the confidence determination module 32 includes: a confidence determination unit used for determining whether the past parking space confidence is greater than the real-time parking space confidence when the coordinate value corresponding to the real-time parking space coordinate is within a threshold range corresponding to the past parking space coordinate; a first confidence determination unit used for taking the past parking space confidence as the target parking space confidence when the past parking space confidence is greater than the real-time parking space confidence; and a second confidence determination unit used for determining the target parking space confidence based on the real-time parking space confidence when the past parking space confidence is less than or equal to the real-time parking space confidence.

[0080] Preferably, the real-time parking space data further includes a real-time environmental score, and the historical parking space data further includes a historical environmental score.

[0081] Preferably, the parking space recognition device includes: a scoring determination module, used for determining whether the real-time environmental scoring is greater than the past environmental scoring when the past parking space certainty is equal to the real-time parking space certainty; and a data updating module, used for updating the past parking space data based on the real-time parking space data corresponding to the real-time environmental scoring when the real-time environmental scoring is greater than the past parking space certainty.

[0082] Preferably, the environmental score is determined by: converting a parking space image, which is acquired by an image recognition device and includes a parking frame line determined from the parking space coordinates and a parking frame line background corresponding to the parking frame line, into a parking space gradation map; calculating a parking frame line average gradation value and a parking frame line gradation standard deviation corresponding to the parking frame line in the parking space gradation map, and a background average gradation value and a background gradation standard deviation corresponding to the parking frame line background; calculating a contrast between the parking frame line and the parking frame line background based on the parking frame line average gradation value, the parking frame line gradation standard deviation, the background average gradation value, and the background gradation standard deviation; and determining the environmental score based on the contrast.

[0083] Preferably, the parking space coordinates include four parking space corner point coordinates.

[0084] Preferably, the coordinate values ​​corresponding to the real-time parking space coordinates being within a threshold range corresponding to the past parking space coordinates includes that the coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates are all within a threshold range corresponding to the four parking space corner point coordinates corresponding to the past parking space coordinates.

[0085] Preferably, the past parking information is determined by: recognizing the surrounding environment of the target vehicle using a predetermined device of the target vehicle to obtain environmental recognition information; determining whether a parking space exists based on the environmental recognition information; and if a parking space exists, marking the parking space in the environmental recognition information using a predetermined mark to indicate the unique identity of the parking space; and determining the past parking information based on the environmental recognition information.

[0086] Preferably, the past parking information is stored locally in the current vehicle and / or in a cloud server corresponding to the current vehicle.

[0087] Preferably, the confidence determination module 32 further includes a fourth confidence determination unit, which is used for setting the previous parking space confidence as the target parking space confidence when the coordinate value corresponding to the real-time parking space coordinate is not within the threshold range corresponding to the previous parking space coordinate.

[0088] Preferably, the second certainty determination unit is specifically used for determining a target parking space certainty based on the past environment score, the past parking space certainty, and the second real-time parking space certainty when the first real-time parking space certainty and the second real-time parking space certainty are both greater than the past parking space certainty, wherein the first real-time parking space certainty is greater than the second real-time parking space certainty, and the first parking space coordinate corresponding to the first real-time parking space certainty and the second parking space coordinate corresponding to the second real-time parking space certainty are both within a threshold range corresponding to the past parking space coordinate.

[0089] The parking space recognition device according to the embodiments of the present application can execute the parking space recognition method according to any embodiment of the present application, and has functional modules and effects corresponding to the execution of the method. [Example]

[0090] 5 is a structural schematic diagram of a parking space recognition device 10 according to an embodiment of the present application. The parking space recognition device may be an electronic device, which is intended to represent various types of digital computers, such as laptops, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various types of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components, their connections and relationships, and their functions shown herein are merely exemplary and are not intended to limit the implementation of the present application as described and / or claimed herein.

[0091] 5, electronic device 10 includes at least one processor 11 and memory communicatively coupled to at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., in which computer programs executable by at least one processor are stored in the memory, and processor 11 can perform various appropriate operations and processes based on the computer programs stored in read-only memory (ROM) 12 or loaded from storage unit 18 into random access memory (RAM) 13. RAM 13 may store various programs and data necessary for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are connected to one another via bus 14. Input / output (I / O) interface 15 is also connected to bus 14.

[0092] Several components in electronic device 10 are connected to I / O interface 15, including input units 16 such as a keyboard, mouse, etc., output units 17 such as various types of displays, speakers, etc., storage units 18 such as a magnetic disk, optical disk, etc., and communication units 19 such as a network card, modem, wireless communication transceiver, etc. The communication units 19 enable electronic device 10 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks.

[0093] The processor 11 may be any of a variety of general-purpose and / or specialized processing assemblies having processing and computing capabilities. Some examples of the processor 11 may 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 that execute machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the methods and processes described above, such as the parking space recognition method.

[0094] In some embodiments, the parking space recognition method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, some or all of the computer program may be loaded and / or installed into 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, it may perform one or more steps of the parking space recognition method described above. Alternatively, in other embodiments, processor 11 may be configured to perform the parking space recognition method in any other suitable manner (e.g., by firmware).

[0095] Various embodiments of the systems and techniques described herein above may be realized in digital electronic circuitry systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being embodied in one or more computer programs that can be executed and / or interpreted by a programmable system that includes at least one programmable processor, which may be a special-purpose or general-purpose programmable processor, and that can receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0096] Computer programs for implementing the methods of the present application can be coded in any combination of one or more programming languages. These computer programs can be provided to a processor in a general purpose computer, a special purpose computer, or other programmable data processing apparatus, so that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are performed. The computer program can be executed entirely on the machine, partially on the machine, as a separate software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of this application, a computer-readable storage medium may be a tangible medium that can contain or store a computer program for use with, or in connection with, an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. Further specific examples of machine-readable storage media include an electrical connection of one or more wires, 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.

[0098] To provide for user interaction, the systems and techniques described herein can be implemented in an electronic device having a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to a user, and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the electronic device. Other types of devices can be used to provide for user interaction; for example, feedback provided to the user can be any form of sensing feedback (e.g., visual feedback, auditory feedback, or haptic feedback), and input from the user can be received in any form (including sound input, speech input, or tactile input).

[0099] The systems and techniques described herein may be implemented in a computing system that includes background components (e.g., as a data server), or middleware components (e.g., an application server), or front-end components (e.g., a user computer having a graphical user interface or network browser through which a user can interact with embodiments of the systems and techniques described herein), or any combination of such background, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0100] A computing system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship is established by computer programs running on corresponding computers and having a client-server relationship. To address the drawbacks of traditional physical hosts and VPS services, such as difficult management and poor business scalability, the server may be called a cloud computing server or cloud host, and may be a cloud server, a host product in a cloud computing service system.

[0101] It should be understood that steps can be rearranged, added, or deleted using the various types of flows shown above. For example, the steps described herein may be performed in parallel, sequentially, or in a different order, and are not limited herein as long as the expected results of the technical aspects of the present application are achieved.

Claims

1. Obtaining real-time parking information of a target parking lot and historical parking information corresponding to the target parking lot; determining a target parking space certainty factor based on real-time parking space data in the real-time parking space information and past parking space data in the past parking space information; determining, as the target parking space, a parking space corresponding to the target parking space certainty degree that satisfies a predetermined condition including that the target parking space certainty degree is equal to or greater than a predetermined threshold value; Parking space recognition method.

2. The real-time parking space data includes real-time parking space coordinates and real-time parking space certainty, and the past parking space data includes past parking space coordinates and past parking space certainty; Determining a target parking space certainty degree based on real-time parking space data in the real-time parking space information and past parking space data in the past parking space information includes: When a coordinate value corresponding to the real-time parking space coordinate is within a threshold range corresponding to the past parking space coordinate, determining whether the past parking space certainty factor is greater than the real-time parking space certainty factor; When the past parking space certainty factor is greater than the real-time parking space certainty factor, the past parking space certainty factor is set as the target parking space certainty factor; and if the past parking space certainty factor is less than or equal to the real-time parking space certainty factor, determining a target parking space certainty factor based on the real-time parking space certainty factor. The method of claim 1.

3. The real-time parking space data further includes a real-time environmental score, and the historical parking space data further includes a historical environmental score; If the past parking space certainty factor is equal to the real-time parking space certainty factor, determining whether the real-time environmental score is greater than the past environmental score; if so, updating the historical parking space data based on the real-time parking space data corresponding to the real-time environmental score. The method of claim 2.

4. The environmental rating is Converting a parking space image, which is acquired by an image recognition device and includes a parking frame line determined from the parking space coordinates and a parking frame line background corresponding to the parking frame line, into a parking space gradation map; Calculating a parking frame line average gradation value and a parking frame line gradation standard deviation corresponding to the parking frame line in the parking space gradation map, and a background average gradation value and a background gradation standard deviation corresponding to the parking frame line background; Calculating a contrast between the parking frame line and the parking frame line background based on the parking frame line average gray scale value, the parking frame line gray scale standard deviation, the background average gray scale value, and the background gray scale standard deviation; and determining the environmental score based on the contrast. The method of claim 2.

5. The parking space coordinates include four parking space corner point coordinates; The coordinate value corresponding to the real-time parking space coordinate is within a threshold range corresponding to the past parking space coordinate, The coordinate values ​​of the four parking space corner point coordinates corresponding to the real-time parking space coordinates are all within a threshold range corresponding to the four parking space corner point coordinates corresponding to the past parking space coordinates. The method of claim 2.

6. The past parking information is Recognizing the surrounding environment of the target vehicle by utilizing a predetermined device of the target vehicle, and obtaining environmental recognition information; determining whether a parking space exists based on the environmental recognition information; If present, marking the parking lot in the environment recognition information with a predetermined indicator to indicate the unique identity of the parking lot, and determining past parking information based on the environment recognition information. The method of claim 1.

7. The past parking information is stored locally in the current vehicle and / or in a cloud server corresponding to the current vehicle. The method of claim 1.

8. Determining a target parking space certainty degree based on real-time parking space data in the real-time parking space information and past parking space data in the past parking space information includes: and when a coordinate value corresponding to the real-time parking space coordinate is not within a threshold range corresponding to the past parking space coordinate, setting the past parking space certainty factor as the target parking space certainty factor. The method of claim 2.

9. determining a target parking space certainty based on the real-time parking space certainty when the past parking space certainty is smaller than the real-time parking space certainty; determining a target parking space certainty based on the past environment score, the past parking space certainty, and the second real-time parking space certainty when the first real-time parking space certainty and the second real-time parking space certainty are both greater than the past parking space certainty, wherein the first real-time parking space certainty is greater than the second real-time parking space certainty, and the first parking space coordinates corresponding to the first real-time parking space certainty and the second parking space coordinates corresponding to the second real-time parking space certainty are both within a threshold range corresponding to the past parking space coordinates; The method of claim 2.

10. an information acquisition module configured to acquire real-time parking information of a target parking lot and historical parking information corresponding to the target parking lot; a certainty determination module configured to determine a target parking space certainty based on real-time parking space data in the real-time parking information and historical parking space data in the historical parking information; a parking space determination module configured to determine, as a target parking space, a parking space corresponding to the target parking space certainty degree that satisfies a predetermined condition including that the target parking space certainty degree is equal to or greater than a predetermined threshold value; Parking space recognition device.

11. at least one processor; a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor can execute the parking space recognition method according to any one of claims 1 to 9. Parking space recognition equipment.

12. a computer program storing computer instructions for implementing the parking space recognition method according to any one of claims 1 to 9 when executed by a processor; A computer-readable storage medium.

Images