Parking space guiding method and system based on guiding robot

Abstract

The invention provides a parking space guiding method and system based on a guiding robot, and the method carries out the parking guiding through the guiding robot, and comprises the steps: carrying out the preprocessing of an obtained initial in-field image, so as to obtain a final in-field image, and selecting a part of virtual parking spaces in the guiding robot as idle parking spaces based on the final in-field image; obtaining a first distance from an entrance of the parking lot to the free parking space, and obtaining a second distance from the free parking space to a target point, so as to determine candidate parking spaces; obtaining a driving path to the candidate parking space, and splitting the driving path into a plurality of path segments; and the road section driving duration of the path section is acquired, then the path driving duration is acquired to determine a target path and a target parking space, and the guiding robot is driven to guide the vehicle to the target parking space through the target path. The robot is guided to replace a fixed detection device, complex circuit layout is avoided, real-time guiding can be achieved, target parking space selection is more intelligent, and the parking experience of a user is optimized.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a parking space guidance method and system based on a guiding robot. Background Technology

[0002] With rapid urbanization and the continuous increase in car ownership, people are increasingly demanding faster and more convenient driving experiences and improved parking management infrastructure. As a result, the problem of parking difficulties in various parking lots has become increasingly prominent.

[0003] Traditional parking lot management relies heavily on manual intervention, only informing drivers of parking space availability upon entry without specifying a clear route. Vehicles still need to find a space themselves after entering. However, with the development of intelligent systems, parking management systems have emerged. These systems use fixed detection devices (such as geomagnetic sensors and ultrasonic probes) within parking spaces to detect vacancy and guide vehicles to available spaces via electronic displays or voice announcements.

[0004] However, this method has several drawbacks. First, the fixed detection device needs to be installed separately for each parking space, and corresponding communication and power supply lines need to be laid, which is complex and has high maintenance costs. Second, since guidance is provided through electronic displays or voice broadcasts, vehicles cannot receive real-time guidance and still need to find parking spaces on their own, which is not timely enough. Third, since users need to choose available parking spaces themselves, it is impossible to determine which available parking space is closest to the user's intention, which affects the user's parking experience. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention aims to provide a parking space guidance method and system based on a guiding robot, which solves the technical problems of complex device deployment, high maintenance costs, insufficient real-time parking guidance, and difficulty in closely matching user intentions in existing parking management systems.

[0006] To achieve the above objectives, in a first aspect, embodiments of this application provide a parking space guidance method based on a guiding robot, wherein the guiding robot is equipped with a parking lot map, and the parking lot map contains a plurality of virtual parking spaces. The parking space guidance method based on the guiding robot includes the following steps: An initial image of the parking lot is acquired through a camera, and the initial image of the parking lot is preprocessed to obtain a final image of the parking lot. Based on the final image of the parking lot, several pre-occupied parking spaces are selected from several virtual parking spaces. A secondary identification is performed on several pre-reserved parking spaces to select occupied parking spaces from the several pre-reserved parking spaces, and the remaining virtual parking spaces are selected as vacant parking spaces; Obtain a first distance from the parking lot entrance to the available parking space, and obtain a second distance from the available parking space to the target point. Based on the first distance and the second distance, select a number of candidate parking spaces from a number of available parking spaces. The driving path from the parking lot entrance to the candidate parking space is obtained based on the parking lot map, and the driving path is divided into several path segments. The travel time of the road segment is obtained, the travel time of several road segments is summarized into a total travel time, the travel path with the shortest travel time is selected as the target path, and the candidate parking space corresponding to the target path is selected as the target parking space. Based on the target path, the driving guide robot guides the vehicle to the target parking space.

[0007] Furthermore, the preprocessing includes distortion correction, illumination compensation, and image enhancement.

[0008] Furthermore, the step of selecting several pre-reserved parking spaces from several virtual parking spaces based on the final in-field image includes: The final field image is aligned to a standard empty field reference image to select parking space areas in the final field image. The parking space areas are associated with virtual parking spaces through parking space codes. A difference map is obtained based on the final in-field image and the standard empty field reference map, and the difference gray value of each difference pixel in the difference map is obtained. The difference gray value is compared with a gray value threshold to distinguish the difference pixels as foreground pixels and background pixels. Determine whether the foreground pixel exists within the parking space area, and mark the virtual parking space corresponding to the parking space area where the foreground pixel exists as a pre-occupied parking space.

[0009] Furthermore, the step of performing secondary identification on the plurality of pre-reserved parking spaces to select an occupied parking space from the plurality of pre-reserved parking spaces includes: Obtain the area ratio between the foreground pixels and the area of ​​the pre-occupied parking space, and obtain the occupancy time of the foreground pixels in the pre-occupied parking space in the final field image of the continuous time frames; The area percentage is compared with the area threshold, and the occupancy time is compared with the duration threshold. If the area percentage is greater than the area threshold and the occupancy time is greater than the duration threshold, then the pre-occupied parking space is selected as an occupied parking space.

[0010] Furthermore, the step of selecting several candidate parking spaces from several available parking spaces based on the first distance and the second distance includes: A first minimum distance is selected from a plurality of first distances, and a second minimum distance is selected from a plurality of second distances. A first attribute value corresponding to the vacant parking space is obtained based on the first distance and the first minimum distance, and a second attribute value corresponding to the vacant parking space is obtained based on the second distance and the second minimum distance. The final score corresponding to the vacant parking space is determined by the first attribute value and the second attribute value, and the vacant parking spaces with a final score greater than the score threshold are selected as candidate parking spaces.

[0011] Furthermore, the formula for obtaining the first attribute value is: , in, This represents the first attribute value of the i-th available parking space. This represents the first distance from the parking lot entrance to the i-th available parking space. This indicates taking the minimum value; The formula for obtaining the final score is: , in, Let represent the final score for the i-th available parking space. This represents the second attribute value of the i-th available parking space. , Both represent weighting coefficients, and + =1.

[0012] Furthermore, the step of obtaining the travel time of the path segment includes: Obtain the current number of vehicles in the path segment, and obtain the traffic flow density of the road segment based on the current number of vehicles; The average density is obtained by measuring the traffic flow density of the road segment, and the busyness coefficient of the road segment is obtained by measuring the traffic flow density of the road segment and the average density. The predicted driving speed is obtained based on the traffic flow density and the busyness coefficient of the road segment, and the driving time of the road segment is obtained through the predicted driving speed.

[0013] Furthermore, the formula for obtaining the traffic flow density of the aforementioned road segment is: , in, This represents the traffic flow density of the m-th segment within the j-th travel path. This represents the current number of vehicles in the m-th path segment of the j-th travel path. This represents the length of the m-th path segment in the j-th travel path; The formula for obtaining the mean density is: , in, Indicates the mean density. This indicates the total number of path segments in the parking lot map; The formula for obtaining the traffic congestion factor of the road segment is: , in, This represents the traffic congestion coefficient of the m-th route segment in the j-th travel path.

[0014] Furthermore, the formula for obtaining the predicted driving speed is: , in, This represents the predicted speed of the m-th path segment within the j-th driving path. Indicates the permitted driving speed. Indicates the maximum congestion density of the road segment. This represents the traffic flow density of the m-th segment within the j-th travel path. This represents the traffic congestion coefficient of the m-th route segment within the j-th travel path. This represents the correction factor.

[0015] Secondly, embodiments of this application provide a parking space guidance system based on a guide robot, applied to the parking space guidance method based on a guide robot as described in the first aspect above, the system comprising: The first recognition module is used to acquire an initial on-site image through a camera, preprocess the initial on-site image to obtain a final on-site image, and select a number of pre-occupied parking spaces from a number of virtual parking spaces based on the final on-site image. The second identification module is used to perform secondary identification on the several pre-occupied parking spaces, so as to select occupied parking spaces from the several pre-occupied parking spaces, and select the remaining virtual parking spaces as vacant parking spaces. The first selection module is used to obtain a first distance from the parking lot entrance to the vacant parking space and a second distance from the vacant parking space to the target point, and select a number of candidate parking spaces from a number of vacant parking spaces based on the first distance and the second distance; The segmentation module is used to obtain the driving path from the parking lot entrance to the candidate parking space based on the parking lot map, and to divide the driving path into several path segments; The second selection module is used to obtain the travel time of the road segment, summarize the travel time of several road segments into a path travel time, select the travel path with the shortest path travel time as the target path, select the candidate parking space corresponding to the target path as the target parking space, and drive the guiding robot to guide the vehicle to the target parking space based on the target path.

[0016] Thirdly, embodiments of this application provide a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the parking space guidance method based on the guided robot as described in the first aspect above.

[0017] Fourthly, embodiments of this application provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the parking space guidance method based on a guided robot as described in the first aspect above.

[0018] Compared with existing technologies, the beneficial effects of this invention are as follows: By employing the guiding robot, which internally houses the parking lot map and virtual parking spaces, and through the combination of the guiding robot and the camera, the guiding robot achieves real-time monitoring of available parking spaces, thereby replacing fixed detection devices, avoiding complex wiring layouts, and reducing maintenance costs; based on the real-time monitoring of available parking spaces by the guiding robot, vehicles can be guided in real-time and continuously after entering the parking lot, solving the problem of insufficient real-time performance of static guidance; by obtaining the formal path between the parking lot and the candidate parking spaces, and using the first distance and the second distance together as the screening criteria for the candidate parking spaces, the user's intentions are fully considered, and personalized parking space guidance is implemented, avoiding indiscriminate allocation that reduces the user's parking experience; by introducing the predicted driving speed, the traffic conditions in the driving path are comprehensively considered, making the determination of the target parking space more intelligent and further optimizing the user's parking experience. Attached Figure Description

[0019] Figure 1 This is a flowchart of the parking space guidance method based on a guide robot in the first embodiment of the present invention; Figure 2 This is a structural block diagram of the parking space guidance system based on a guide robot in the second embodiment of the present invention; The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0020] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0021] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] Please see Figure 1 The first embodiment of the present invention provides a parking space guidance method based on a guiding robot, which guides parking through a guiding robot. The guiding robot is equipped with a parking lot map, and the parking lot map contains a plurality of virtual parking spaces. The parking space guidance method based on the guiding robot includes the following steps: S10: Acquire an initial on-site image through a camera, preprocess the initial on-site image to obtain a final on-site image, and select a number of pre-occupied parking spaces from a number of virtual parking spaces based on the final on-site image; The preprocessing includes distortion correction, illumination compensation, and image enhancement. Specifically, by acquiring the intrinsic parameters and distortion coefficients of the camera, the initial in-field image is corrected to eliminate lens distortion, and a corrected image is acquired. The corrected image is then subjected to grayscale processing to obtain a grayscale image. The number of grayscale pixels at each grayscale level in the grayscale image is obtained. The grayscale level probability is obtained based on the product of the number of grayscale pixels and the total number of pixels. Based on the grayscale level probability, the cumulative probability of the corresponding grayscale level is obtained. Based on the cumulative probability of the grayscale level, an updated grayscale value corresponding to the grayscale level is obtained. The updated grayscale value is assigned to the grayscale pixels in the grayscale level to complete illumination compensation, enhance the contrast of the corrected image, reduce the impact of uneven lighting in the parking lot, and acquire a compensated image. The compensated image is then denoised using a Gaussian filter to complete image enhancement, and the final in-field image is acquired. This preprocessing improves the accuracy of vacant parking space identification, facilitating the precise control of vacant parking spaces by the guiding robot.

[0024] Step S10 includes: S110: Align the final field image to the standard empty field reference image to select the parking space area in the final field image, and the parking space area is associated with the virtual parking space through the parking space code; Understandably, the parking space code is a preset value of encoding information, and each parking space corresponds to a unique parking space code. The standard empty parking reference map is obtained based on the same processing flow as the final parking lot image. The only difference is that the standard empty parking reference map is obtained when the parking lot is empty. After obtaining the standard empty parking reference map, the empty parking space area can be formed by edge detection algorithm or by manual labeling. It should be noted that each of the standard empty parking reference maps can correspond to a part of the parking lot map.

[0025] S120: Obtain a difference map based on the final in-field image and the standard empty field reference map, and obtain the difference gray value of each difference pixel in the difference map. Compare the difference gray value with a gray value threshold to distinguish the difference pixel into foreground pixels and background pixels. Understandably, the camera has been calibrated and its installation position is fixed. Therefore, the final in-field image and the standard empty-field reference image are essentially consistent. In some embodiments, further alignment can be performed by selecting corresponding registration point pairs in the final in-field image and the standard empty-field reference image, respectively, based on the registration point pairs. After alignment is completed, the grayscale values ​​at corresponding pixels are subtracted to form the difference image.

[0026] S130: Determine whether the foreground pixel exists within the parking space area, and mark the virtual parking space corresponding to the parking space area where the foreground pixel exists as a pre-occupied parking space.

[0027] S20: Perform secondary identification on the plurality of pre-occupied parking spaces to select occupied parking spaces from the plurality of pre-occupied parking spaces, and select the remaining virtual parking spaces as vacant parking spaces; After obtaining the reserved parking space, further identification is required to avoid errors in parking space status recognition caused by partial obstruction of the parking space due to vehicles passing by. Specifically, step S20 includes: S210: Obtain the area ratio between the foreground pixels and the area of ​​the pre-occupied parking space, and obtain the occupancy time of the foreground pixels in the pre-occupied parking space in the final field image of the continuous time frame. S220: Compare the area percentage with the area threshold and the occupancy time with the duration threshold. If the area percentage is greater than the area threshold and the occupancy time is greater than the duration threshold, then the pre-occupied parking space is selected as an occupied parking space.

[0028] In some embodiments, the parking space status is determined by inputting the final in-field image into a pre-trained neural network recognition model.

[0029] S30: Obtain a first distance from the parking lot entrance to the available parking space, and obtain a second distance from the available parking space to the target point; select a number of candidate parking spaces from a number of available parking spaces based on the first distance and the second distance. Both the first distance and the second distance refer to straight-line distances, in order to quickly determine the candidate parking space through the shortest path.

[0030] Step S30 includes: S310: Select a first minimum distance from a plurality of first distances, and select a second minimum distance from a plurality of second distances; obtain a first attribute value corresponding to the vacant parking space based on the first distance and the first minimum distance, and obtain a second attribute value corresponding to the vacant parking space based on the second distance and the second minimum distance; The formula for obtaining the first attribute value is: , in, This represents the first attribute value of the i-th available parking space. This represents the first distance from the parking lot entrance to the i-th available parking space. This indicates that the minimum value is taken. The second attribute value is obtained in the same way, so it will not be described again here.

[0031] S320: Determine the final score corresponding to the vacant parking space using the first attribute value and the second attribute value, and select vacant parking spaces with a final score greater than the score threshold as candidate parking spaces; The formula for obtaining the final score is: , in, Let represent the final score for the i-th available parking space. This represents the second attribute value of the i-th available parking space. , Both represent weighting coefficients, and + =1. After combining the first distance and the second distance, since both are straight-line distances and only the distance factor is considered, it is also necessary to consider whether the driving path of the vehicle from the parking lot entrance to the candidate parking space is optimal. Therefore, the vacant parking space with the highest final score cannot be directly selected as the target parking space.

[0032] S40: Obtain the driving path from the parking lot entrance to the candidate parking space based on the parking lot map, and divide the driving path into several path segments; Specifically, the driving path is divided based on the intersections in the driving path. Assuming that a driving path contains two intersections, it is divided into three path segments: path segment 1 (parking lot entrance - intersection 1) - path segment 2 (intersection 1 - intersection 2) - path segment 3 (intersection 2 - candidate parking space).

[0033] S50: Obtain the travel time of the road segment, summarize the travel time of several road segments into a total travel time, select the travel path with the shortest travel time as the target path, select the candidate parking space corresponding to the target path as the target parking space, and drive the guiding robot to guide the vehicle to the target parking space based on the target path. Step S50 includes: S510: Obtain the current number of vehicles in the path segment, and obtain the traffic flow density of the road segment based on the current number of vehicles; Understandably, the current number of vehicles in the path segment can be determined by acquiring real-time images from the camera and using a pre-trained recognition neural network model, or by detecting them using sensors installed on the guiding robot in the guiding state.

[0034] The formula for obtaining the traffic flow density of the aforementioned road section is: , in, This represents the traffic flow density of the m-th segment within the j-th travel path. This represents the current number of vehicles in the m-th path segment of the j-th travel path. This represents the length of the m-th path segment in the j-th travel path.

[0035] S520: Obtain the average density value through the traffic flow density of the road segment, and obtain the road segment busyness coefficient through the traffic flow density of the road segment and the average density value; The formula for obtaining the mean density is: , in, Indicates the mean density. This indicates the total number of path segments in the parking lot map; The formula for obtaining the traffic congestion factor of the road segment is: , in, This represents the traffic congestion coefficient of the m-th route segment in the j-th travel path.

[0036] S530: Obtain the predicted driving speed based on the traffic flow density and the busyness coefficient of the road segment, and obtain the driving time of the road segment through the predicted driving speed; The formula for obtaining the predicted driving speed is: , in, This represents the predicted speed of the m-th path segment within the j-th driving path. Indicates the permitted driving speed. Indicates the maximum congestion density of the road segment. This represents the traffic flow density of the m-th segment within the j-th travel path. This represents the traffic congestion coefficient of the m-th route segment within the j-th travel path. This represents a correction coefficient. After obtaining the predicted driving speed, the travel time of the road segment is obtained by dividing the length of the road segment by the predicted driving speed. It should be noted that the maximum congestion density of the road segment is obtained by dividing the number of vehicles in the road segment when it is in a completely congested state by the length of the road segment. The predicted driving speed is not zero when the traffic density of the road segment is the same as the maximum congestion density of the road segment. By introducing a correction coefficient, an approximate simulation of the completely congested state is completed. The value of the correction coefficient can be adaptively adjusted by the value of the traffic density of the road segment. In this embodiment, the value of the correction coefficient is 0.5~3.0. When the value of the traffic density of the road segment is larger, the value of the correction coefficient is higher.

[0037] By employing the guiding robot, which internally displays the parking lot map and virtual parking spaces, and combining the guiding robot with the camera, real-time monitoring of available parking spaces is achieved. This replaces fixed detection devices, avoids complex wiring, and reduces maintenance costs. Based on the real-time monitoring of available parking spaces, the guiding robot can provide real-time and continuous guidance after a vehicle enters the parking lot, solving the problem of insufficient real-time performance of static guidance. By obtaining the formal path from the parking lot to the candidate parking spaces, and using the first distance and the second distance together as the selection criteria for candidate parking spaces, user intent is fully considered, and personalized parking space guidance is implemented, avoiding indiscriminate allocation that reduces the user's parking experience. By introducing predicted driving speed and comprehensively considering traffic conditions along the driving path, the determination of the target parking space becomes more intelligent, further optimizing the user's parking experience. Please see Figure 2 The second embodiment of the present invention provides a parking space guidance system based on a guided robot. This system is applied to the parking space guidance method based on a guided robot described in the above embodiments, and will not be repeated hereafter. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0038] The system includes: The first identification module 10 is used to acquire an initial on-site image through a camera, preprocess the initial on-site image to obtain a final on-site image, and select a number of pre-occupied parking spaces from a number of virtual parking spaces based on the final on-site image. The first identification module 10 includes: The first unit is used to align the final field image to a standard empty field reference image, so as to select a parking space area in the final field image, and the parking space area is associated with a virtual parking space through a parking space code; The second unit is used to obtain a difference map based on the final in-field image and the standard empty field reference map, and to obtain the difference gray value of each difference pixel in the difference map, and to compare the difference gray value with a gray value threshold to distinguish the difference pixel into foreground pixels and background pixels. The third unit is used to determine whether the foreground pixel exists in the parking space area, and to mark the virtual parking space corresponding to the parking space area where the foreground pixel exists as a pre-occupied parking space. The second identification module 20 is used to perform secondary identification on the several pre-occupied parking spaces, so as to select occupied parking spaces from the several pre-occupied parking spaces and select the remaining virtual parking spaces as vacant parking spaces. The second identification module 20 includes: The fourth unit is used to obtain the area ratio between the foreground pixels and the area of ​​the pre-occupied parking space, and to obtain the occupancy time of the foreground pixels in the pre-occupied parking space in the final field image of the continuous time frames. The fifth unit is used to compare the area ratio with the area threshold and the occupancy time with the duration threshold. If the area ratio is greater than the area threshold and the occupancy time is greater than the duration threshold, then the pre-occupied parking space is selected as an occupied parking space. The first selection module 30 is used to obtain a first distance from the parking lot entrance to the vacant parking space and a second distance from the vacant parking space to the target point, and select a number of candidate parking spaces from a number of vacant parking spaces based on the first distance and the second distance; The first selection module 30 includes: The sixth unit is used to select a first minimum distance from a plurality of first distances and a second minimum distance from a plurality of second distances, obtain a first attribute value corresponding to the vacant parking space based on the first distance and the first minimum distance, and obtain a second attribute value corresponding to the vacant parking space based on the second distance and the second minimum distance; The seventh unit is used to determine the final score corresponding to the vacant parking space through the first attribute value and the second attribute value, and to select vacant parking spaces with a final score greater than the score threshold as candidate parking spaces; The segmentation module 40 is used to obtain the driving path from the parking lot entrance to the candidate parking space based on the parking lot map, and to divide the driving path into several path segments. The second selection module 50 is used to obtain the travel time of the road segment, summarize the travel time of several road segments into a path travel time, select the travel path with the shortest path travel time as the target path, select the candidate parking space corresponding to the target path as the target parking space, and drive the guiding robot to guide the vehicle to the target parking space based on the target path. The second selection module 50 includes: The eighth unit is used to obtain the current number of vehicles in the path segment and obtain the traffic flow density of the road segment based on the current number of vehicles; The ninth unit is used to obtain the average density value through the traffic flow density of the road segment, and to obtain the road segment busyness coefficient through the traffic flow density of the road segment and the average density value. The tenth unit is used to obtain the predicted driving speed based on the traffic flow density and the busyness coefficient of the road segment, and to obtain the driving time of the road segment through the predicted driving speed.

[0039] The present invention also provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the parking space guidance method based on the guided robot as described in the above technical solutions.

[0040] The present invention also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the parking space guidance method based on a guided robot as described in the above technical solution.

[0041] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0042] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A parking space guidance method based on a guiding robot, wherein a parking map is installed within the guiding robot, and the parking map contains a plurality of virtual parking spaces, characterized in that, The parking space guidance method based on the guided robot includes the following steps: An initial image of the parking lot is acquired through a camera, and the initial image of the parking lot is preprocessed to obtain a final image of the parking lot. Based on the final image of the parking lot, several pre-occupied parking spaces are selected from several virtual parking spaces. A secondary identification is performed on several pre-reserved parking spaces to select occupied parking spaces from the several pre-reserved parking spaces, and the remaining virtual parking spaces are selected as vacant parking spaces; Obtain a first distance from the parking lot entrance to the available parking space, and obtain a second distance from the available parking space to the target point. Based on the first distance and the second distance, select a number of candidate parking spaces from a number of available parking spaces. The driving path from the parking lot entrance to the candidate parking space is obtained based on the parking lot map, and the driving path is divided into several path segments. The travel time of the road segment is obtained, the travel time of several road segments is summarized into a total travel time, the travel path with the shortest travel time is selected as the target path, and the candidate parking space corresponding to the target path is selected as the target parking space. Based on the target path, the driving guide robot guides the vehicle to the target parking space.

2. The parking space guidance method based on a guided robot according to claim 1, characterized in that, The preprocessing includes distortion correction, illumination compensation, and image enhancement.

3. The parking space guidance method based on a guided robot according to claim 1, characterized in that, The step of selecting several pre-reserved parking spaces from several virtual parking spaces based on the final in-field image includes: The final field image is aligned to a standard empty field reference image to select parking space areas in the final field image. The parking space areas are associated with virtual parking spaces through parking space codes. A difference map is obtained based on the final in-field image and the standard empty field reference map, and the difference gray value of each difference pixel in the difference map is obtained. The difference gray value is compared with a gray value threshold to distinguish the difference pixels as foreground pixels and background pixels. Determine whether the foreground pixel exists within the parking space area, and mark the virtual parking space corresponding to the parking space area where the foreground pixel exists as a pre-occupied parking space.

4. The parking space guidance method based on a guided robot according to claim 3, characterized in that, The step of performing secondary identification on the plurality of pre-reserved parking spaces to select an occupied parking space from the plurality of pre-reserved parking spaces includes: Obtain the area ratio between the foreground pixels and the area of ​​the pre-occupied parking space, and obtain the occupancy time of the foreground pixels in the pre-occupied parking space in the final field image of the continuous time frames; The area percentage is compared with the area threshold, and the occupancy time is compared with the duration threshold. If the area percentage is greater than the area threshold and the occupancy time is greater than the duration threshold, then the pre-occupied parking space is selected as an occupied parking space.

5. The parking space guidance method based on a guided robot according to claim 1, characterized in that, The step of selecting several candidate parking spaces from several available parking spaces based on the first distance and the second distance includes: A first minimum distance is selected from a plurality of first distances, and a second minimum distance is selected from a plurality of second distances. A first attribute value corresponding to the vacant parking space is obtained based on the first distance and the first minimum distance, and a second attribute value corresponding to the vacant parking space is obtained based on the second distance and the second minimum distance. The final score corresponding to the vacant parking space is determined by the first attribute value and the second attribute value, and the vacant parking spaces with a final score greater than the score threshold are selected as candidate parking spaces.

6. The parking space guidance method based on a guided robot according to claim 5, characterized in that, The formula for obtaining the first attribute value is: ， in, This represents the first attribute value of the i-th available parking space. This represents the first distance from the parking lot entrance to the i-th available parking space. This indicates taking the minimum value; The formula for obtaining the final score is: ， in, Let represent the final score for the i-th available parking space. This represents the second attribute value of the i-th available parking space. , Both represent weighting coefficients, and + =1.

7. The parking space guidance method based on a guided robot according to claim 1, characterized in that, The step of obtaining the travel time of the route segment includes: Obtain the current number of vehicles in the path segment, and obtain the traffic flow density of the road segment based on the current number of vehicles; The average density is obtained by measuring the traffic flow density of the road segment, and the busyness coefficient of the road segment is obtained by measuring the traffic flow density of the road segment and the average density. The predicted driving speed is obtained based on the traffic flow density and the busyness coefficient of the road segment, and the driving time of the road segment is obtained through the predicted driving speed.

8. The parking space guidance method based on a guided robot according to claim 7, characterized in that, The formula for obtaining the traffic flow density of the aforementioned road section is: ， in, This represents the traffic flow density of the m-th segment within the j-th travel path. This represents the current number of vehicles in the m-th path segment of the j-th travel path. This represents the length of the m-th path segment in the j-th travel path; The formula for obtaining the mean density is: ， in, Indicates the mean density. This indicates the total number of path segments in the parking lot map; The formula for obtaining the traffic congestion factor of the road segment is: ， in, This represents the traffic congestion coefficient of the m-th route segment in the j-th travel path.

9. The parking space guidance method based on a guided robot according to claim 7, characterized in that, The formula for obtaining the predicted driving speed is: ， in, This represents the predicted speed of the m-th path segment within the j-th driving path. Indicates the permitted driving speed. Indicates the maximum congestion density of the road segment. This represents the traffic flow density of the m-th segment within the j-th travel path. This represents the traffic congestion coefficient of the m-th route segment within the j-th travel path. This represents the correction factor.

10. A parking space guidance system based on a guide robot, applied to the parking space guidance method based on a guide robot as described in any one of claims 1 to 9, characterized in that, The system includes: The first recognition module is used to acquire an initial on-site image through a camera, preprocess the initial on-site image to obtain a final on-site image, and select a number of pre-occupied parking spaces from a number of virtual parking spaces based on the final on-site image. The second identification module is used to perform secondary identification on the several pre-occupied parking spaces, so as to select occupied parking spaces from the several pre-occupied parking spaces, and select the remaining virtual parking spaces as vacant parking spaces. The first selection module is used to obtain a first distance from the parking lot entrance to the vacant parking space and a second distance from the vacant parking space to the target point, and select a number of candidate parking spaces from a number of vacant parking spaces based on the first distance and the second distance; The segmentation module is used to obtain the driving path from the parking lot entrance to the candidate parking space based on the parking lot map, and to divide the driving path into several path segments; The second selection module is used to obtain the travel time of the road segment, summarize the travel time of several road segments into a path travel time, select the travel path with the shortest path travel time as the target path, select the candidate parking space corresponding to the target path as the target parking space, and drive the guiding robot to guide the vehicle to the target parking space based on the target path.

Images