Parking calibration method, device, equipment and computer storage medium

Abstract

The present application discloses a parking calibration method, device, equipment and computer storage medium. The parking calibration method includes: obtaining first position information of a vehicle and second position information of a parking area; obtaining relative orientation information between the vehicle and the parking area when it is determined that the overlapping state of the vehicle and the parking area meets a preset overlapping condition based on the first position information and the second position information; outputting a first signal when the relative orientation information meets the preset orientation condition, the first signal indicating that the vehicle meets the preset parking condition. In this embodiment, when the overlapping state of the vehicle and the parking area meets the preset overlapping condition, the relative orientation information is further combined to implement parking calibration, which can effectively reduce the amount of calculation required for parking calibration during parking and save computing resources.

Description

Technical Field

[0001] The present application belongs to the field of parking technology, and in particular, relates to a parking calibration method, device, equipment and computer storage medium. Background Art

[0002] As we all know, there is a need to park a vehicle in a specific area in many situations, for example, the vehicle needs to be parked within the boundary of the parking area when parking normally. During the parking process, the autonomous driving vehicle usually continuously obtains the relative position relationship between the vehicle body and the parking area to perform parking calibration to ensure that the vehicle body can be accurately parked in the parking area.

[0003] However, in the prior art, parking calibration usually runs through the entire parking process, which leads to the problem of high consumption of computing resources. Summary of the invention

[0004] The embodiments of the present application provide a parking calibration method, device, equipment and computer storage medium to solve the problem in the prior art that parking calibration runs through the entire parking process, resulting in high consumption of computing resources.

[0005] In a first aspect, an embodiment of the present application provides a parking calibration method, comprising:

[0006] Acquiring first position information of the vehicle and second position information of the parking area;

[0007] When it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information, obtaining relative position information between the vehicle and the parking area;

[0008] When the relative position information satisfies a preset position condition, a first signal is output, and the first signal indicates that the vehicle satisfies a preset parking condition.

[0009] In a second aspect, an embodiment of the present application provides a parking calibration device, the device comprising:

[0010] A first acquisition module, used to acquire first position information of the vehicle and second position information of the parking area;

[0011] A second acquisition module is used to acquire relative position information between the vehicle and the parking area when it is determined that the overlapping state between the vehicle and the parking area meets a preset overlapping condition according to the first position information and the second position information;

[0012] The output module is used to output a first signal when the relative position information meets a preset position condition, wherein the first signal is used to indicate that the vehicle meets a preset parking condition.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions;

[0014] The processor implements the above parking calibration method when executing the computer program instructions.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned parking calibration method is implemented.

[0016] The parking calibration method, device, equipment and computer storage medium of the embodiment of the present application obtain the first position information of the vehicle and the second position information of the parking area, and obtain the relative orientation information between the vehicle and the parking area when it is determined that the overlapping state of the vehicle and the parking area meets the preset overlapping condition according to the first position information and the second position information, and output a first signal indicating that the vehicle meets the preset parking condition when the relative orientation information meets the preset orientation condition. In this embodiment, when the overlapping state of the vehicle and the parking area meets the preset overlapping condition, the relative orientation information is further combined to implement parking calibration, which can effectively reduce the amount of calculation required for parking calibration during parking and save computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 is a flow chart of a parking calibration method provided in an embodiment of the present application;

[0019] Figure 2a to Figure 2f is an example diagram of a target image in an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of the structure of a parking calibration device provided in an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0023] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0024] In order to solve the problems in the prior art, the embodiments of the present application provide a parking calibration method, device, equipment and computer storage medium. The parking calibration method provided by the embodiments of the present application is first introduced below.

[0025] Figure 1 FIG. 1 is a flow chart of a parking calibration method provided by an embodiment of the present application. Figure 1 As shown, the parking calibration method includes:

[0026] Step 101, obtaining first position information of a vehicle and second position information of a parking area;

[0027] Step 102, when it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information, relative position information between the vehicle and the parking area is obtained;

[0028] Step 103: When the relative position information satisfies a preset position condition, a first signal is output, where the first signal is used to indicate that the vehicle satisfies a preset parking condition.

[0029] In combination with some actual application scenarios, the above-mentioned vehicle may be in the process of driving towards the parking area, or may have arrived in the parking area in whole or in part; in general, the vehicle may be considered to be in a parking state. Accordingly, the parking calibration method provided in this embodiment may be used to calibrate whether the vehicle has parked in the parking area according to the preset parking conditions; for example, whether the vehicle has entered the parking area as a whole, or whether the parking direction of the vehicle is consistent with the extension direction of the parking area, etc., which will be specifically described below.

[0030] It is easy to understand that the vehicle may be an autonomous vehicle, for example, it may automatically park in a parking area without human intervention, or it may be a vehicle that manually triggers the automatic parking function when human intervention occurs. The parking area may be an area with specific boundaries, such as a common rectangular parking space or a parallelogram parking space, which is not specifically limited here.

[0031] Generally speaking, the first position information of the vehicle and the second position information of the parking area can be reflected in the captured image; for example, a surround view of the vehicle is captured using a camera installed on the vehicle, and the surround view can include the first position information and the second position information.

[0032] Of course, in some possible implementations, the above-mentioned captured images may also be image devices installed above the parking area. These image devices may be equipped with communication devices for communicating with the vehicle, and the captured images are sent to the vehicle through the communication devices.

[0033] In some other possible implementations, the first location information and the second location information may be obtained by using, for example, a high-definition map and a vehicle positioning device. For example, the first location information of the vehicle in the map may be determined by a positioning device, and the second location information of the parking area may be directly stored in the high-definition map.

[0034] Based on the first position information and the second position information, the overlapping state between the vehicle and the parking area can be obtained. The overlapping state here can refer to whether the vehicle and the parking area overlap, or the overlapping degree between the vehicle and the parking area.

[0035] It is easy to understand that when the first position information and the second position information are reflected on the image, the image areas of the vehicle and the parking area in the image can be obtained through deep learning or semantic segmentation, and the overlapping state can be obtained based on the image areas corresponding to the two.

[0036] When the first position information and the second position information are reflected on the map, the geographical area of ​​the vehicle in the map can be determined based on the vehicle's position, posture and inherent size. The geographical area of ​​the parking area is usually fixed in the map. Based on the geographical areas of the two, or the geographical coordinate information, the above-mentioned overlapping state can be obtained.

[0037] Before step 102, it may be determined whether the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition. The preset overlapping condition may mean that the vehicle and the parking area overlap, or that the degree of overlap between the vehicle and the parking area is greater than a preset overlap threshold, etc.

[0038] In step 102, when the overlapping state of the vehicle and the parking area meets the preset overlapping condition, the relative position information between the vehicle and the parking area can be further obtained. The relative position information here can refer to the relative distance information and relative angle information between the vehicle and the parking area.

[0039] For example, corresponding center points may be defined for vehicles and parking areas, for example, for a parking area of ​​a regular shape, the center point may be the geometric center; for a vehicle, the center point may be the centroid, etc. The relative distance information may be the distance between the center points of the corresponding vehicle and the parking area.

[0040] For the vehicle and the parking area, corresponding directions can usually be defined respectively, for example, the defined direction can refer to the extension direction of the long side of the vehicle and the parking area, etc. The relative angle information of the vehicle and the parking area can correspond to the angle between the defined directions.

[0041] Before step 103, it may be determined whether the relative position information meets a preset position condition. The preset position condition here may refer to the relative distance information being less than a distance threshold, and / or the relative angle information being less than an angle threshold.

[0042] Comparing the relative orientation information with the preset orientation conditions can be considered as the main parking calibration process to a certain extent. For example, when the relative distance information indicates that the distance is too large, it means that the vehicle may not have driven normally into the parking area, and when the relative angle information indicates that the angle is too large, it means that the vehicle may be parked crookedly. By comparing the relative orientation information with the preset orientation conditions, some unsuccessful parking situations can be effectively discovered.

[0043] In step 103, when the relative position information meets the preset position condition, a first signal may be output, and the first signal may indicate that the vehicle meets the preset parking condition. In combination with some actual application scenarios, the output first signal may be used to end the automatic parking function; or to prompt the completion of parking on some vehicle terminals; or may be sent to a remote server through a vehicle communication device; or may be stored as a driving log, etc.

[0044] It is easy to understand that, in this embodiment, the acquisition of the relative position information between the vehicle and the parking area, and the determination of whether the relative position information satisfies the preset position condition, can be performed when the overlapping state of the vehicle and the parking area satisfies the preset overlapping condition. That is, before the overlapping state satisfies the preset overlapping condition, that is, when the parking state has a large deviation between the vehicle and the parking area, the main parking calibration calculation process can be skipped to reduce the amount of calculation.

[0045] It can be seen that the parking calibration method provided in the embodiment of the present application obtains the first position information of the vehicle and the second position information of the parking area, and when it is determined that the overlapping state of the vehicle and the parking area meets the preset overlapping condition according to the first position information and the second position information, obtains the relative orientation information between the vehicle and the parking area, and when the relative orientation information meets the preset orientation condition, outputs a first signal indicating that the vehicle meets the preset parking condition. In this embodiment, when the overlapping state of the vehicle and the parking area meets the preset overlapping condition, the relative orientation information is further combined to implement parking calibration, which can effectively reduce the amount of calculation required for parking calibration during the parking process and save computing resources.

[0046] Optionally, the above step 101, obtaining the first position information of the vehicle and the second position information of the parking area, includes:

[0047] Acquire a target image, wherein the target image includes an image of the vehicle and an image of the parking area;

[0048] According to the target image, first position information and second position information are obtained.

[0049] In this embodiment, the first position information and the second position information may be obtained from an image obtained based on shooting. For simplicity, the image from which the first position information and the second position information are obtained may be defined as a target image.

[0050] It is easy to understand that the target image may include images of the vehicle and the parking area. For example, as shown above, the surrounding view of the vehicle can be obtained by using an imaging device installed on the vehicle, which includes the image of the vehicle and the image of the parking area; for another example, the target image can be obtained by photographing the vehicle and the parking area with a camera located above the parking area, and then further sent to the vehicle.

[0051] Generally speaking, the position of the vehicle and the parking area in the target image can be obtained through deep learning or semantic segmentation, and the position can be reflected by coordinates in the image coordinate system. In other words, the first position information and the second position information can be reflected by the coordinates of the images of the vehicle and the parking area in the target image.

[0052] In this embodiment, the first position information and the second position information are obtained based on the target image, so that the position information of the vehicle and the parking area can be obtained more accurately, which also helps to make subsequent parking calibration more accurate.

[0053] In one example, the step of acquiring the target image specifically includes:

[0054] Acquire multiple initial images, where the multiple initial images are acquired by imaging devices installed around the vehicle;

[0055] Multiple initial images are stitched together to obtain the target image.

[0056] In this example, the target image may be obtained by stitching together initial images captured by multiple imaging devices. For ease of understanding, the process of acquiring the target image is described below in conjunction with an actual application scenario.

[0057] In this application scenario, the target image can be called a surround view. The surround view can be a bird's-eye view generated by stitching technology using four fisheye cameras installed around the vehicle to obtain information about the environment in which the vehicle is located, and then performing distortion correction and inverse perspective transformation on the images captured by the cameras.

[0058] Since the relative positions of the camera and the vehicle are fixed, generally speaking, the vehicle can be in the center of the surround view, and the aspect ratio of the vehicle image is generally fixed.

[0059] Of course, it is worth noting that the specific type of imaging equipment installed on the vehicle can be selected according to actual needs, and the number of imaging equipment can also be adjusted according to factors such as the length of the vehicle, and examples are not given here one by one.

[0060] By acquiring multiple initial images through imaging devices installed around the vehicle, and stitching the multiple initial images to obtain the target image, the first position information of the vehicle can be relatively fixed, reducing the amount of calculation required to obtain the first position information. At the same time, in this example, the acquisition of the target image is less affected by environmental factors, and the first position information and the second position information can be reliably acquired in various parking scenarios.

[0061] Optionally, in the above step 102, when it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information, before obtaining the relative position information between the vehicle and the parking area, the method further includes:

[0062] Determine an overlapping area of ​​the vehicle and the parking area in the target image and a first area of ​​the vehicle in the target image according to the first position information and the second position information;

[0063] When the ratio of the overlapping area to the first area is greater than or equal to the first ratio threshold, it is determined that the overlapping state of the vehicle and the parking area meets the preset overlapping condition.

[0064] In combination with the description of the above embodiment, the first position information and the second position information may correspond to the image of the vehicle and the image of the parking area, respectively, that is, the vehicle and the parking area may have corresponding image areas in the target image, respectively. In the image coordinate system of the target image, the area of ​​the image area can usually be obtained.

[0065] In other words, the first area corresponding to the vehicle is obtained according to the first position information; and the intersection of the image of the vehicle and the image of the parking area is obtained to obtain the overlapping area, which can also be achieved based on the first position information and the second position information.

[0066] In this embodiment, the ratio of the overlapping area to the first area can be calculated, that is, the first area is used as the denominator of the ratio operation, and the overlapping area is used as the numerator, which is usually not greater than the first area. Therefore, the value of the ratio of the overlapping area to the first area can be [0,1].

[0067] For ease of explanation, the ratio of the overlapping area to the first area can be represented by the Intersection over Union (IOU). In one example, the first ratio threshold of the IOU can be set to a value less than 1, for example, 3 / 4. When the IOU is less than the first ratio threshold, it can be considered that the vehicle is a certain distance away from successful parking. At this time, there is no need to further calculate the relative position of the vehicle and the parking area, which greatly reduces the amount of redundant calculations.

[0068] Of course, the specific value of the first ratio threshold can also be selected according to actual needs.

[0069] Generally speaking, for a certain vehicle, its corresponding first area is often relatively fixed. When performing the above ratio operation to determine the overlapping state of the vehicle and the parking area, the influence of various factors on the operation results can be effectively reduced (for example, when half of the parking space is blocked or there is only a part of the parking space in the target image, the accuracy of the denominator of the ratio operation can still be guaranteed); and using the relatively fixed first area as the denominator, a relatively fixed first ratio threshold can be further set for different types of vehicles and different types of parking areas. In summary, using the first area as the denominator of the ratio operation helps to simplify the judgment process of whether the overlapping state meets the preset overlapping conditions and improve the accuracy of the judgment result.

[0070] In addition, in some possible implementations, the overlapping state of the vehicle and the parking area is also characterized by other methods. For example, the intersection area and the union area of ​​the vehicle and the parking area in the target image are obtained, and the ratio of the intersection area to the union area is used to characterize the overlapping state, and the ratio is further compared with a preset ratio to determine whether the overlapping state meets the preset overlapping condition.

[0071] It is easy to understand that, in general, there will be a complete vehicle image in the target image, and the first area of ​​the vehicle in the target image is often easy to obtain. For example, when the target image is spliced ​​based on the initial image obtained by the camera installed on the vehicle, the first area of ​​the vehicle can usually be fixed. The following will mainly explain the process of obtaining the above overlapping area.

[0072] Optionally, determining the overlapping area between the vehicle and the parking area in the target image and the first area of ​​the vehicle in the target image based on the first position information and the second position information includes:

[0073] Determining a first area of ​​the vehicle in the target image according to the first position information;

[0074] Determining a target contour of the parking area in the target image according to the second position information, wherein the target contour matches the parking area;

[0075] An overlapping area between the vehicle and the parking area in the target image is determined according to the target contour and the first position information.

[0076] As shown above, based on deep learning or semantic segmentation, the images corresponding to the vehicle and the parking area can be identified from the target image. And according to the first position information corresponding to the vehicle image, the first area of ​​the vehicle in the target image can be determined.

[0077] Compared with the vehicle, the parking area in the target image may have various forms. For example, the shape of the parking area may be a rectangle or a parallelogram. During the parking process, the vehicle may block the parking area in the target image.

[0078] Therefore, in this embodiment, the target contour of the parking area in the target image can be determined according to the second position information. Specifically, the parking area usually has actual contour lines, but these actual contour lines may not be closed and may be blocked by vehicles, making it difficult to directly obtain an image of the complete parking area.

[0079] In this embodiment, a target contour of the parking area may be determined in the target image based on the second position information. The target contour may be closed, and the enclosed area may be considered as the area of ​​the complete parking area in most cases.

[0080] In other words, the matching relationship between the parking area and the target contour can, to a certain extent, be considered that the target contour can indicate the actual contour of the complete parking area. Of course, in some actual application scenarios, there may be slight differences between the target contour and the actual contour, and the matching relationship can be further described as the target contour can approximately indicate the actual contour of the complete parking area.

[0081] Of course, in some possible implementations, the actual contour lines in the target image may be identified by, for example, Hough transform straight line detection, and the target contour may be obtained based on the actual contour lines.

[0082] Determining the overlapping area between the vehicle and the parking area in the target image according to the target contour and the first position information can be achieved in the following manner:

[0083] A binary mask matrix is ​​established for the vehicle and parking area, respectively, and is denoted as M c and M s Among them, in M c In M, the pixel value of the area where the vehicle image is located can be 1, and the pixel value of the area other than the area where the vehicle image is located can be 0. s In the example, the pixel value in the area enclosed by the target outline can be 1, while the pixel value outside the area enclosed by the target outline can be 0.

[0084] Calculate the intersection of the parking area and the vehicle, that is, the M corresponding to the parking area s M corresponding to the vehicle c Multiply them, and then directly add the pixels whose product is 1 to get the intersection area S (M s ∩Mc ), which corresponds to the above-mentioned overlapping area.

[0085] Accordingly, S(M s ∩M c ) and the ratio of the first area is taken as the value of the above-mentioned IOU.

[0086] It can be seen that in this embodiment, the target contour corresponding to the parking area is obtained through the second position information, and the overlapping area between the parking area and the vehicle in the target image is obtained based on the target contour and the first position information, which helps to obtain the overlapping area more conveniently and accurately.

[0087] As shown above, in the target image, the parking area may be blocked by the vehicle, making it difficult to directly acquire an image of the complete parking area.

[0088] For example, combined with Figure 2a to Figure 2f , Figure 2a to Figure 2f shows several possible positional relationships between the parking area and the vehicle in the target image. Specifically, the parking area may be a parking space, and the shape of the parking space may be a rectangle, with four endpoints D1, D2, D3 and D4, respectively; wherein the line connecting D3 and D4 may be considered as the front of the parking space.

[0089] exist Figure 2a In the figure, the vehicle has just entered the parking space and is parallel to the parking space; the vehicle blocks the line connecting D3 and D4, but the four endpoints all appear in the target image;

[0090] exist Figure 2b In the figure, the vehicle crosses the line and enters the parking space, blocking part of the parking space. There is a certain angle between the vehicle and the parking space, and the endpoint D3 is blocked. At the same time, there are two intersection points between the outline of the parking space and the outline of the vehicle, namely F1 and F2.

[0091] exist Figure 2c The positional relationship between the vehicle and the parking space is Figure 2b Similarly, the vehicle blocks the endpoint D4. At the same time, there are two intersection points F1 and F2 between the outline of the parking space and the outline of the vehicle.

[0092] exist Figure 2d In the figure, the vehicle blocks both endpoints D3 and D4. At the same time, there are two intersection points F1 and F2 between the outline of the parking space and the outline of the vehicle.

[0093] exist Figure 2e In the figure, the vehicle is located within the outline of the parking space, but there is a certain angle between the vehicle and the parking space;

[0094] exist Figure 2fIn the figure, the entire vehicle is located within the outline of the parking space, and the vehicle and the parking space are parallel, so it can be considered that the vehicle has been successfully parked in the parking space.

[0095] Based on the above examples, it can be seen that in the target image, the actual outline of the vehicle can usually be presented relatively completely in the target image; however, the actual outline of the parking space may be obscured, and the specific forms of the obscuration may exist in various forms.

[0096] In order to obtain the target contour of a parking area such as a parking space, in an exemplary embodiment, determining the target contour of the parking area in the target image according to the second position information includes:

[0097] Determine a first image contour of the vehicle in the target image and a second image contour of the parking area in the target image according to the first position information and the second position information;

[0098] Determining a target point associated with the parking area according to the first image contour and the second image contour;

[0099] According to the target point and the preset shape information corresponding to the parking area, the target contour of the parking area in the target image is determined.

[0100] In this embodiment, the first image contour may refer to the contour of the vehicle that can be directly presented in the target image. As shown above, the actual contour of the vehicle can usually be relatively completely presented in the target image, so generally speaking, the first image contour may be the actual contour of the corresponding vehicle.

[0101] Similarly, the second image contour may refer to the contour of the parking area that can be directly presented in the target image. Figure 2a to Figure 2d , the second image contour may not correspond to the actual contour of the parking area.

[0102] However, based on the first image contour and the second image contour, some key points can be obtained, such as D1, D2, D3, D4, F1 and F2 mentioned above, and these key points can be considered as target points associated with the parking area.

[0103] It is easy to understand that the second image contour obtained based on the second position information may have some angular inflection points, which may be one or more of the above D1, D2, D3 and D4. In addition, the inflection points can be obtained by feature screening, and the specific feature screening method is not limited here.

[0104] Similarly, the intersection points of the first image contour and the second image contour can also be obtained by feature screening and other methods, which will not be described in detail here. These intersection points may be one or more of the above-mentioned F1 and F2.

[0105] In addition, in this embodiment, the parking area may correspond to preset shape information. For example, the shape of the parking area may be preset as a quadrilateral. Accordingly, the parking area may have four endpoints. Based on the above target point, the four endpoints of the parking area may be obtained. To simplify the description, the endpoints of the parking area may be referred to as target endpoints below.

[0106] The following examples illustrate the process of determining the target endpoint by combining some specific scenarios:

[0107] See also Figure 2a In the scenario shown in the figure, D1, D2, D3 and D4 can be determined as four target endpoints.

[0108] See also Figure 2b In the scenario shown in the figure, D1, D2 and D4 can be first determined as three target endpoints; then, the intersection of the straight line D1F1 and the straight line D4F2 can be used as the fourth target endpoint. Figure 2c In the scenario shown, four target endpoints can also be obtained in this way.

[0109] See also Figure 2d In the scenario shown in the figure, D1 and D2 can be first determined as two target endpoints, and then the endpoint of the longer contour line between D1F1 and D2F2, that is, F2, can be used as the third target endpoint; assuming that the parking area is a parallelogram or a rectangle, the fourth target endpoint can be determined based on the characteristics of these shapes and the coordinates of D1, D2 and F2.

[0110] It is easy to understand that in the image coordinate system of the target image, the coordinates of the above key points can all be obtained. Based on these coordinates, a straight line function can be fitted in the image coordinate system to obtain the coordinates of a specific target endpoint, which is usually easy to achieve.

[0111] When each target endpoint of the parking area is determined, each target endpoint is connected in sequence according to a specific order, so that the target contour of the parking area in the target image can be obtained.

[0112] It can be seen that this embodiment can determine the target contour of the parking area relatively accurately in various parking scenarios, thereby helping to improve the accuracy of subsequent calculations of parameters such as the overlapping area.

[0113] In one example, the target point associated with the parking area includes: an intersection point of any two contour lines in the first image contour whose included angle is greater than a preset angle, and an intersection point of the first image contour and the second image contour;

[0114] The preset shape information is used to indicate that the parking area is a rectangle or a parallelogram.

[0115] In combination with the description of the previous embodiment, the parking area can be preset to a specific shape, such as a rectangle or a parallelogram. These preset shapes can exist in the form of preset shape information. When determining the target contour of the parking area, based on the preset shape information, it is helpful to more conveniently obtain the obscured target endpoint of the parking area.

[0116] Specifically, for rectangles and parallelograms, opposite sides are usually parallel and of equal length. In the image coordinate system, based on these characteristics, the coordinates of the target endpoints can be calculated more conveniently.

[0117] In addition, in this example, the intersection of any two contour lines in the first image contour whose angle is greater than the preset angle can be considered as the inflection point in the second image contour mentioned above; as for the extraction of each intersection point, it can be performed by feature recognition or feature screening, which will not be described here. This example further limits the composition of the target point, avoids introducing too many meaningless endpoints (such as the inflection point in the first image contour, etc.), and reduces the difficulty of determining the target point.

[0118] To further understand the process of determining the target contour, a specific application scenario is used as an example below.

[0119] In this application scenario, the parking area may be a parking space, and parking space information is obtained based on the surround view, and the parking space information may include coordinates of key points of the parking space.

[0120] According to the parking space key points, it can be determined whether the outline of the parking space in the target image (specifically corresponding to the second image outline) needs to be completed. It is worth noting that the purpose of completion here can be to complete the parking space as much as possible into a rectangle or parallelogram, not necessarily to restore the parking space.

[0121] If only three target endpoints of the parking space are detected, the coordinates of the blocked target endpoint need to be completed based on the coordinates of the other three target endpoints; if only two target endpoints are detected, the endpoint of the longer side of the parking space is used as one of the target endpoints, and the fourth target endpoint is completed based on the coordinates of the three target endpoints. Figure 2a to Figure 2d Explained.

[0122] Here we will use Figure 2cIn the scenario, the process of obtaining the four target endpoints of the parking space is described as an example, where the parking space can be a parallelogram or a rectangle by default.

[0123] Given the coordinates of D1 (x1, y1), D2 (x2, y2), and D3 (x3, y3), if the parking space is horizontal (specifically, it can be horizontal in the image coordinate system) and the parking space is a rectangular frame, the coordinate of D4 is (x3, y2);

[0124] For the case where the parking space is tilted and not horizontal, that is, x2≠x1 or x3≠x1, respectively find the straight line y=k1*x+b1 parallel to D1D2 and the straight line y=k2*x+b2 parallel to D1D3, and finally find the coordinates of the intersection point D4 of the two straight lines. The specific calculation process is as follows:

[0125]

[0126] b1=y3-k1*x3 b2=y2-k2*x2

[0127] Substituting the above k1, k2, b1 and b2 into y=k1*x+b1 and y=k2*x+b2, we can get the coordinates of the intersection of the two lines. In general scenarios, the coordinates of the intersection can be recorded as:

[0128]

[0129] When the parking spaces are completed, the above IOU can be further calculated. Specifically, the following is also explained in conjunction with an actual application scenario:

[0130] Step 1: Create binary mask matrices for parking spaces and vehicles. The binary mask matrix for parking spaces refers to the pixel values ​​of the parking space rectangle being 1 and the pixel values ​​of the other parts being 0. Similarly, the binary mask matrix for vehicles refers to the pixel values ​​of the vehicle being 1 and the pixel values ​​of the other parts being 0. The binary mask matrices for parking spaces and vehicles obtained here are denoted as M s and M c ;

[0131] Step 2: Calculate the intersection of parking spaces and vehicles, that is, the parking space binary mask matrix M s and the vehicle binary mask matrix M c Multiply them, and then add up the pixels whose product is 1 to get the intersection area S (M s ∩M c );

[0132] Step 3: Calculate the intersection area and the vehicle rectangular frame area S cThe ratio IOU is calculated as follows:

[0133]

[0134] Here, the vehicle rectangular frame area Sc can be used as the denominator. Generally speaking, in the surround view obtained based on the camera installed on the vehicle, the vehicle body information is fixed, while the parking space rectangular frame may be unstable during detection. For example, in the case where half of the parking space is blocked or only a part of the parking space is in the picture, the IOU calculated with the vehicle rectangular frame as a reference can accurately express whether most of the vehicle body is in the parking space. In other words, using the vehicle rectangular frame area Sc as the denominator can avoid the instability of the IOU denominator caused by changes in the detected parking space rectangle to a certain extent, which helps to accurately characterize the proportion of the vehicle body inside the parking space;

[0135] As shown above, in some possible implementations, the surround view may be replaced by an image captured by a camera installed above the parking space. In this case, the denominator may be the area of ​​the parking space, or the union area of ​​the parking space and the vehicle.

[0136] Step 4: Use IOU to eliminate the situation where most of the car body is not in the parking space. Based on the IOU obtained in Step 3, the value range is generally [0,1], and the IOU can accurately describe how much area of ​​the car body is in the parking space. Set a threshold T less than 1 (for example, 3 / 4). When the IOU is less than the threshold, it can be directly determined that the car has not been parked; this helps to eliminate most of the non-overlapping parking states, greatly reducing the amount of redundant calculations.

[0137] Optionally, the relative orientation information includes relative distance information and relative angle information in the target image;

[0138] Accordingly, the above step 102, obtaining the relative position information between the vehicle and the parking area, may include:

[0139] Determine a first centroid of the vehicle in the target image according to the first position information, determine a second centroid of the parking area in the target image according to the second position information, and determine relative distance information between the vehicle and the parking area according to the first centroid and the second centroid;

[0140] The relative angle information between the vehicle and the parking area is determined based on the inclination angle of the target contour line in the target coordinate system; wherein the target contour line is a contour line associated with the vehicle determined in the target image based on the first position information, or a contour line associated with the parking area determined in the target image based on the second position information; and the target coordinate system is an image coordinate system of the target image.

[0141] The following is a collection of a specific application scenario to illustrate this embodiment.

[0142] In this application scenario, the target image can be a surround view obtained by stitching images collected by cameras installed on the vehicle. The surround bird's-eye view generated by the stitching technology, so the vehicle can be in a fixed position in the surround view (for example, the center of the surround view), and its aspect ratio is usually fixed. The vehicle position is represented by a rectangular box Rect(x c ,y c ,w,h) form, where (x c ,y c ) is the coordinate of the center point of the vehicle, w and h are the length and width of the vehicle in the surround view, respectively.

[0143] It is easy to understand that (x c ,y c ) can also be considered as the coordinates of the first center of mass of the vehicle in the target image.

[0144] For a parking space, if it is a parallelogram or a rectangle, there may be four target endpoints in the target image. The specific method for determining these target endpoints has been described in the above embodiments and will not be repeated here.

[0145] The four target endpoints can be recorded as D1(x1,y1), D2(x2,y2), D3(x3,y3), and D4(x4,y4) coordinates respectively, and the center of mass coordinate of the parking space is marked as O(x s ,y s ); then the following relationship can exist:

[0146] x s =(x1+x2+x3+x4) / 4

[0147] y s =(y1+y2+y3+y4) / 4

[0148] The relative distance information can be represented by d, and the specific calculation formula of d is:

[0149]

[0150] As shown above, the position of the vehicle in the surround view is usually fixed. Figure 2a to Figure 2f The vehicle may be horizontal in the surround view. In this case, it is only necessary to analyze whether the parking space is horizontal in the surround view, that is, it is possible to determine whether the vehicle and the parking space are parallel.

[0151] The analysis of whether the parking space is horizontal in the surround view can be achieved by calculating the slope of the parking space contour in the image coordinate system, or the offset angle relative to the horizontal direction (or vertical direction). It is easy to understand that the offset angle here can correspond to the above-mentioned tilt angle.

[0152] Specifically, combined Figure 2a to Figure 2f , the parking space line D1D3 can be taken to calculate the offset angle ω as follows;

[0153]

[0154] If a parking space is blocked, another edge line parallel to D1D3 can be selected for calculation, or the offset angle between D1D2, D3D4 and the vertical direction can be calculated.

[0155] Of course, in some application scenarios, the position of the parking space in the target image may remain fixed, for example, when the camera is installed above the parking space, etc. In this case, the contour line of the vehicle may be selected to calculate the above-mentioned offset angle.

[0156] In order to adapt to more application scenarios, the relative angle information can correspond to the offset angle obtained in the following manner: obtain the first slope (or first inclination angle) corresponding to the contour line corresponding to the long side of the vehicle, and the second slope (or second inclination angle) corresponding to the contour line corresponding to the long side of the parking space (or parking area), and obtain the offset angle between the vehicle and the parking space according to the first slope and the second slope (or the first inclination angle and the second inclination angle).

[0157] Based on the previous embodiment, in this embodiment, in the above step 103, when the relative position information meets the preset position condition, before outputting the first signal, the parking calibration method may further include:

[0158] Determining a distance ratio according to the relative distance information and the first distance, the first distance being the distance between a first point and a second point in the target image, the first point being any end point of the parking area on a side away from the vehicle, and the second point being an end point on the vehicle farthest from the first point;

[0159] When the distance ratio is less than or equal to the second ratio threshold, and the angle between the vehicle and the parking area indicated by the relative angle information is less than or equal to the angle threshold, it is determined that the relative orientation information meets the preset orientation condition.

[0160] For the first point, it can be any end point of the parking area away from the vehicle. Figure 2aWhen the vehicle is parking, generally speaking, it can be considered that it is moving from the right to the left. Accordingly, during the parking process, the left side of the parking area can be considered as the side away from the vehicle. The first point can be an end point on the left side of the parking area (such as D1 or D2).

[0161] When the first point is determined, the second point can be determined based on the distance relationship. For example, when the first point is D1, the second point can be the lower right corner of the vehicle; when the first point is D2, the second point can be the upper right corner of the vehicle.

[0162] As can be seen from the above examples, in this embodiment, the first distance can be considered to be the diagonal line of the union area of ​​the parking area and the vehicle to a certain extent.

[0163] For example, in a specific application example, the coordinates of the upper left corner of the parking space are D1(x1,y1), and the coordinates of the lower right corner of the vehicle body are (x c +w / 2,y c -h / 2), these two points correspond to the first point and the second point respectively, and the distance between them also corresponds to the first distance.

[0164] The calculation formula of the first distance d0 can be:

[0165]

[0166] The distance ratio can be recorded as ψ, and the calculation formula is as follows:

[0167]

[0168] Since the center of mass distance between the vehicle and the parking space is always smaller than the diagonal distance, when the center of mass distance between the vehicle and the parking space is very far, the ψ value approaches 1; when the center of mass of the parking space and the center of mass of the vehicle basically coincide, the ψ value is 0. Therefore, taking a threshold value that satisfies the condition and is close to 0 can determine whether the center of mass of the parking space is close to the center of mass of the vehicle body.

[0169] In other words, by calculating the ratio of the distance between the center of mass of the vehicle body and the center of mass of the parking space to the distance between the diagonals of the two rectangular frames, the second ratio threshold can be limited to the value range of [0,1), which makes it easier to set an accurate center of mass deviation range in engineering.

[0170] On the basis that the distance ratio is less than or equal to the second ratio threshold, if there is further a relationship that the angle (or offset angle) between the vehicle and the parking area is less than a threshold close to 0, it means that the vehicle's center of mass basically coincides with the parking center of mass, and it can be considered that the vehicle has been parked.

[0171] Optionally, in the above step 102, when it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information, after obtaining the relative position information between the vehicle and the parking area, the method further includes:

[0172] When the relative position information does not satisfy the preset position condition, parking planning information is generated according to the relative position information.

[0173] When the relative position information does not meet the preset position condition, it may be considered that the vehicle is close to the parking area but is not parked properly, and further parking path planning is required.

[0174] Therefore, in this embodiment, the acquired relative position information can be applied to parking planning. For example, the relative position information can include the offset vector of the center of mass between the vehicle and the parking area, and the offset angle between the vehicle and the parking area. Such relative position information can be used for subsequent vehicle parking planning and control, and the specific planning and control methods can be implemented by existing technologies, which will not be described in detail here.

[0175] It can be seen that in this embodiment, the first position information and the second position information can not only be used for parking calibration, but can also be further applied to autonomous parking, thereby enriching the uses of these position information.

[0176] like Figure 3 As shown, the embodiment of the present application also provides a parking calibration device, the device comprising:

[0177] A first acquisition module 301 is used to acquire first position information of the vehicle and second position information of the parking area;

[0178] The second acquisition module 302 is used to acquire relative position information between the vehicle and the parking area when it is determined that the overlapping state between the vehicle and the parking area meets a preset overlapping condition according to the first position information and the second position information;

[0179] The output module 303 is used to output a first signal when the relative position information meets a preset position condition, where the first signal is used to indicate that the vehicle meets a preset parking condition.

[0180] Optionally, the first acquisition module 301 may include:

[0181] A first acquisition unit, used to acquire a target image, wherein the target image includes an image of the vehicle and an image of the parking area;

[0182] The second acquisition unit is used to acquire the first position information and the second position information according to the target image.

[0183] Optionally, the first acquiring unit may include:

[0184] An acquisition subunit, used for acquiring a plurality of initial images, wherein the plurality of initial images are acquired by imaging devices installed around the vehicle;

[0185] The stitching subunit is used to stitch multiple initial images to obtain a target image.

[0186] Optionally, the parking calibration device may further include:

[0187] A first determination module, configured to determine an overlapping area between the vehicle and the parking area in the target image and a first area of ​​the vehicle in the target image according to the first position information and the second position information;

[0188] The first determination module is used to determine whether the overlapping state of the vehicle and the parking area meets a preset overlapping condition when the ratio of the overlapping area to the first area is greater than or equal to a first ratio threshold.

[0189] Optionally, the first determining module may include:

[0190] A first determining unit, configured to determine a first area of ​​the vehicle in the target image according to the first position information;

[0191] A second determining unit is used to determine a target contour of the parking area in the target image according to the second position information, wherein the target contour matches the parking area;

[0192] The third determining unit is used to determine the overlapping area between the vehicle and the parking area in the target image according to the target contour and the first position information.

[0193] Optionally, the second determining unit may include:

[0194] A first determining subunit, configured to determine a first image contour of the vehicle in the target image and a second image contour of the parking area in the target image, respectively, according to the first position information and the second position information;

[0195] A second determining subunit, configured to determine a target point associated with the parking area according to the first image contour and the second image contour;

[0196] The third determining subunit is used to determine the target contour of the parking area in the target image according to the target point and the preset shape information corresponding to the parking area.

[0197] Optionally, the target point associated with the parking area includes: an intersection point of any two contour lines in the first image contour whose included angle is greater than a preset angle, and an intersection point of the first image contour and the second image contour;

[0198] The preset shape information is used to indicate that the parking area is a rectangle or a parallelogram.

[0199] Optionally, the relative orientation information includes relative distance information and relative angle information in the target image;

[0200] Accordingly, the second acquisition module 302 may include:

[0201] a fourth determining unit, configured to determine a first centroid of the vehicle in the target image according to the first position information, determine a second centroid of the parking area in the target image according to the second position information, and determine relative distance information between the vehicle and the parking area according to the first centroid and the second centroid;

[0202] a fifth determination unit, for determining relative angle information between the vehicle and the parking area according to an inclination angle of a target contour line in a target coordinate system; wherein the target contour line is a contour line associated with the vehicle determined in a target image according to first position information, or a contour line associated with the parking area determined in a target image according to second position information; and the target coordinate system is an image coordinate system of the target image.

[0203] Optionally, the parking calibration device may further include:

[0204] a second determination module, configured to determine a distance ratio according to the relative distance information and a first distance, wherein the first distance is a distance between a first point and a second point in the target image, the first point being any end point of the parking area on a side away from the vehicle, and the second point being an end point on the vehicle farthest from the first point;

[0205] The second determination module is used to determine that the relative orientation information satisfies a preset orientation condition when the distance ratio is less than or equal to a second ratio threshold and the angle between the vehicle and the parking area indicated by the relative angle information is less than or equal to an angle threshold.

[0206] Optionally, the parking calibration device may further include:

[0207] The generating module is used to generate parking planning information according to the relative position information when the relative position information does not meet the preset position condition.

[0208] It should be noted that the parking calibration device is a device corresponding to the above-mentioned parking calibration method, and all implementation methods in the above-mentioned method embodiment are applicable to the embodiment of the device and can achieve the same technical effect.

[0209] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0210] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0211] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0212] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

[0213] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to the present disclosure.

[0214] The processor 401 implements any one of the parking calibration methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .

[0215] In one example, the electronic device may further include a communication interface 403 and a bus 404. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 404 and communicate with each other.

[0216] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0217] Bus 404 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 404 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0218] In addition, in combination with the parking calibration method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the parking calibration methods in the above embodiment is implemented.

[0219] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0220] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0221] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0222] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0223] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A parking calibration method, characterized in that: include: Acquiring first position information of the vehicle and second position information of the parking area, which includes: acquiring a target image, wherein the target image includes an image of the vehicle and an image of the parking area; acquiring the first position information and the second position information according to the target image; Determine, according to the first position information and the second position information, an overlapping area between the vehicle and the parking area in the target image, and a first area of ​​the vehicle in the target image; When the ratio of the overlapping area to the first area is greater than a first ratio threshold, determining that the overlapping state of the vehicle and the parking area meets a preset overlapping condition; When it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information, obtaining relative position information between the vehicle and the parking area; When the relative position information satisfies a preset position condition, a first signal is output, wherein the first signal indicates that the vehicle satisfies a preset parking condition.

2. The method according to claim 1, characterized in that The acquiring of the target image comprises: Acquire a plurality of initial images, wherein the plurality of initial images are acquired by imaging devices installed around the vehicle; The multiple initial images are spliced ​​to obtain the target image.

3. The method according to claim 1, characterized in that The determining, based on the first position information and the second position information, an overlapping area of ​​the vehicle and the parking area in the target image, and a first area of ​​the vehicle in the target image includes: Determining a first area of ​​the vehicle in the target image according to the first position information; determining, according to the second position information, a target contour of the parking area in the target image, wherein the target contour matches the parking area; An overlapping area between the vehicle and the parking area in the target image is determined according to the target contour and the first position information.

4. The method according to claim 3, characterized in that The step of determining a target contour of the parking area in the target image according to the second position information includes: Determine, according to the first position information and the second position information, a first image contour of the vehicle in the target image and a second image contour of the parking area in the target image; determining a target point associated with the parking area according to the first image contour and the second image contour; According to the target point and preset shape information corresponding to the parking area, a target contour of the parking area in the target image is determined.

5. The method according to claim 4, characterized in that The target point associated with the parking area includes: an intersection point of any two contour lines in the first image contour whose included angle is greater than a preset angle, and an intersection point of the first image contour and the second image contour; The preset shape information is used to indicate that the parking area is a rectangle or a parallelogram.

6. The method according to claim 1, characterized in that The relative orientation information includes relative distance information and relative angle information in the target image; The obtaining of relative position information between the vehicle and the parking area includes: Determine a first centroid of the vehicle in the target image according to the first position information, determine a second centroid of the parking area in the target image according to the second position information, and determine relative distance information between the vehicle and the parking area according to the first centroid and the second centroid; The relative angle information between the vehicle and the parking area is determined according to the inclination angle of the target contour line in the target coordinate system; wherein the target contour line is a contour line associated with the vehicle determined in the target image according to the first position information, or a contour line associated with the parking area determined in the target image according to the second position information; and the target coordinate system is an image coordinate system of the target image.

7. The method according to claim 6, characterized in that When the relative position information satisfies a preset position condition, before outputting the first signal, the method further includes: determining a distance ratio according to the relative distance information and a first distance, wherein the first distance is a distance between a first point and a second point in the target image, the first point being any endpoint of the parking area on a side away from the vehicle, and the second point being an endpoint on the vehicle farthest from the first point; When the distance ratio is less than or equal to a second ratio threshold, and the angle between the vehicle and the parking area indicated by the relative angle information is less than or equal to an angle threshold, it is determined that the relative orientation information meets a preset orientation condition.

8. The method according to claim 1, characterized in that After obtaining relative position information between the vehicle and the parking area, if it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information, the method further includes: When the relative position information does not satisfy a preset position condition, parking planning information is generated according to the relative position information.

9. A parking calibration device, applied to the parking calibration method according to claim 1, characterized in that: The device comprises: A first acquisition module, used to acquire first position information of the vehicle and second position information of the parking area; a second acquisition module, configured to acquire relative position information between the vehicle and the parking area when it is determined that the overlapping state between the vehicle and the parking area satisfies a preset overlapping condition according to the first position information and the second position information; The output module is used to output a first signal when the relative position information meets a preset position condition, wherein the first signal is used to indicate that the vehicle meets a preset parking condition.

10. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the parking calibration method according to any one of claims 1 to 8 is implemented.

11. A computer storage medium, characterized in that: The computer storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the parking calibration method according to any one of claims 1 to 8 is implemented.

Images