WO2023241595A1 - 车位范围的处理方法及计算设备 - Google Patents

车位范围的处理方法及计算设备 Download PDF

Info

Publication number
WO2023241595A1
WO2023241595A1 PCT/CN2023/100034 CN2023100034W WO2023241595A1 WO 2023241595 A1 WO2023241595 A1 WO 2023241595A1 CN 2023100034 W CN2023100034 W CN 2023100034W WO 2023241595 A1 WO2023241595 A1 WO 2023241595A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking space
line
parking
image
image acquisition
Prior art date
Application number
PCT/CN2023/100034
Other languages
English (en)
French (fr)
Inventor
张玮炜
Original Assignee
阿里云计算有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿里云计算有限公司 filed Critical 阿里云计算有限公司
Publication of WO2023241595A1 publication Critical patent/WO2023241595A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
    • G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
    • G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/147—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is within an open public zone, e.g. city centre

Definitions

  • the present application relates to the field of cloud computing technology, and in particular to a parking space range processing method and computing device.
  • Remote management of parking spaces can be achieved by monitoring parking spaces.
  • it is usually necessary to draw the corresponding lines of the parking space range in the physical world in the collected image area for the next step of the algorithm. deal with.
  • the marking of parking space ranges is based on manual methods. Since parking spaces are usually distributed in a relatively large area and the number of parking spaces involved is relatively large, therefore, the marking of parking space ranges will consume a lot of manpower and time costs. .
  • Embodiments of the present application provide a parking space range processing method and calculation device to realize parking space range calculation and parking space management.
  • embodiments of the present application provide a parking space range processing method, including:
  • a parking space range of the parking space is determined based on the first parking space line and the second parking space line, so that a computing device associated with the parking space detects a relative relationship between a vehicle and the parking space.
  • embodiments of the present application provide a method for processing parking space ranges, which is applied to computing devices deployed near parking spaces.
  • the method includes:
  • the parking space range is determined based on the first parking space line and the second parking space line identified in at least one parking space image.
  • the parking space image is obtained by an image acquisition device near the parking space. Obtained from the shooting, the first parking space line is parallel to the road and determined based on the relative position of the image acquisition device and the parking space, and the second parking space line is the line spaced between two parking spaces;
  • the relative relationship between the vehicle and the parking space in the parking space image newly collected by the image acquisition device is identified.
  • embodiments of the present application provide a computing device, including a memory, a processor, and a computer program stored on the memory.
  • the processor implements the above-mentioned method when executing the computer program.
  • one or more parking space images taken by an image acquisition device near the parking space are obtained, and further based on the relative position of the image acquisition device and the parking space, it is identified from the parking space image that the parking space is parallel to the road.
  • the first parking space line and the second parking space line between the two parking spaces so that the parking space range of the parking space can be determined based on the first parking space line and the second parking space line. It can be seen that this application provides an automatic identification of the parking space range.
  • This solution can improve the identification efficiency of the parking space range, make full use of the images obtained by the image collection equipment used for monitoring, reduce a lot of labor costs, and is suitable for scenarios where there are many parking spaces and are widely distributed, and can
  • the computing device associated with the parking space detects the relative relationship between the vehicle and the parking space, and further realizes practical needs such as automatic parking billing, parking space management, alarm management, camera deflection detection, and camera exposure detection in unmanned monitoring scenarios. It has broad application prospects.
  • Figure 1 is a schematic diagram of an exemplary application scenario for implementing the method of the embodiment of the present application
  • Figure 2 is a flow chart of a parking space range processing method according to an embodiment of the present application.
  • Figure 3 is a flow chart of a parking space range processing method according to another embodiment of the present application.
  • Figure 4 is a structural block diagram of a parking space range processing device according to an embodiment of the present application.
  • Figure 5 is a structural block diagram of a parking space range processing device according to another embodiment of the present application.
  • Figure 6 is a block diagram of a computing device used to implement embodiments of the present application.
  • the embodiment provides a parking space range processing method.
  • an image acquisition device near the parking space in advance, and obtaining one or more parking space images collected by the image acquisition device, two types of parking spaces are identified from the parking space images based on the relative position of the image acquisition device and the parking space. Lines, one is the first parking space line where the parking space is parallel to the road, and the other is the second parking space line that is spaced between parking spaces, and the parking space range can be automatically determined based on the two parking space lines.
  • it can improve the identification efficiency of the parking space range, make full use of the images obtained by the image acquisition equipment used for monitoring, reduce a lot of labor costs, and is suitable for the distribution of more parking spaces and wider distribution. scene.
  • the relative relationship between vehicles and parking spaces can be further detected, the vehicle occupation behavior of parking spaces can be managed, and parking billing, parking space management, alarm management, camera deflection detection, and camera exposure can be realized in unmanned monitoring scenarios.
  • Degree detection and other practical needs have broad application prospects.
  • it can be implemented as a high-level video smart parking system, using image acquisition equipment installed near the parking space to analyze parking space occupancy.
  • the embodiment of the present application is particularly suitable for parking on the road. Compared with parking in a parking lot, parking on the road does not have a set entrance and exit, so you can enter and exit at will, which brings greater management difficulty and is more complicated. What stands out is the difficulty of charging.
  • Existing road toll collection is usually done manually. It requires personnel to squat near the parking space to check the entry and exit of vehicles and record the parking status of vehicles. It is also necessary to quickly collect fees from drivers when exiting the vehicle. The work It is complicated and large in quantity, and the timing accuracy is low.
  • the images collected by the image acquisition device can be combined to further monitor the entry and exit of vehicles, thereby realizing automatic parking billing.
  • the charging results can be sent directly to the mobile terminal corresponding to the vehicle driver.
  • the vehicle owner can be detected based on the monitored license plate number or vehicle characteristics, and the mobile terminal identification corresponding to the vehicle owner can be further determined, and the charging results can be sent in the form of a message or notification. Send it, and the car owner can pay through his or her mobile terminal. There is no need to staff billing and charging, and there is no need for car owners to park and pay.
  • the vehicle can be parked or driven away without any interaction. While improving timing accuracy, it can also improve the efficiency of parking spaces and avoid affecting road traffic.
  • car owners can also connect to cloud servers or computing devices through their mobile terminals to check the status of parking spaces and parking space information in real time, which can improve parking efficiency.
  • the above-mentioned determination of the parking space range can be implemented based on the cloud.
  • Computing equipment can be configured near the parking space for real-time calculation of parking space management. On the one hand, it can share the computing pressure of the cloud. On the other hand, It can realize fast calculation of data and avoid the time delay problem caused by remote transmission. Therefore, the determined parking space range can be sent to the computing device near the parking space, and the computing device is responsible for vehicle entry and exit, billing, and other management.
  • FIG. 1 is a schematic diagram of an exemplary application scenario for implementing the method of the embodiment of the present application.
  • the entire architecture is divided into the cloud and the edge near the parking spaces.
  • One or more image acquisition devices can be deployed as needed.
  • One of the image acquisition devices can capture images of one or more parking spaces. (For example, one image acquisition device corresponds to 3-4 parking spaces).
  • the image acquisition device can specifically be an IPC (IP Camera, network camera) with network communication function, so that the The collected images are uploaded to the cloud server in real time through the router.
  • the cloud can receive the images through the video edge intelligent service platform and further identify the images.
  • the images can be transmitted to the road parking service engine dedicated to road monitoring for management. Specifically, Image algorithms are applied to identify the range of parking spaces.
  • the road parking service engine can obtain event notifications by monitoring messages from the IOT (Internet of Things, Internet of Things) platform in the cloud, or notify the terminal device of the parking space manager.
  • IOT Internet of Things, Internet of Things
  • edge image collection equipment and road parking all-in-one machines can be accessed and managed through the cloud IOT platform.
  • Parking space managers can obtain parking information through terminal equipment connected to the all-in-one machine or through terminal equipment communicating with the cloud platform.
  • the status data of parking spaces can be used to view and manage the status of parking spaces, and the status of image acquisition equipment can also be monitored to repair related problems in a timely manner.
  • FIG. 1 is a parking space according to an embodiment of the present application.
  • Flowchart of range processing method As shown in Figure 2, the method includes:
  • Step S201 Obtain at least one parking space image captured by an image collection device near the parking space.
  • the image collection device described in the embodiments of this application can be a network camera, or any device that can collect images, such as a high-speed dome camera for road monitoring, a video recorder, etc.
  • the collected images can be in the form of images or video frames extracted from the video. .
  • the corresponding network connection function can be configured for the image collection device.
  • the image acquisition equipment can be deployed near the parking space so that images of the parking space area can be collected. Specifically, it can be at a higher position to collect images from a bird's-eye view, or at a lower position from a upward view. Images can also be collected from a head-up perspective.
  • the image collection equipment can be set up at a high place.
  • the image acquisition device usually captures the parking space to the middle of the image to obtain more information content related to the parking space.
  • the parking spaces in the embodiment of the present application may be in the form of adjacent vehicles end to end, or may be arranged side by side.
  • it is usually in the form of adjacent end-to-end parking spaces.
  • the existing monitoring equipment for the parking space such as a high-speed dome camera for road monitoring
  • the parking spaces are monitored.
  • the cloud server can add management of the image acquisition device, that is, register the image acquisition device as an Internet of Things device, and obtain the corresponding computing space.
  • the number of image acquisition devices can be set according to actual needs so that a more complete parking space area can be monitored. For example, one image acquisition device can generally monitor several parking space areas. Of course, the increase in the number of image acquisition devices can Improving the accuracy of monitoring will also increase hardware costs and data calculations. The number of image acquisition devices can be increased or reduced according to actual needs.
  • the image acquisition device may collect images or videos, and the corresponding parking space image may be one or more images or video frames extracted from the video.
  • Step S202 According to the relative position of the image acquisition device and the parking space, select a parking space from the at least one parking space. In the image, it is identified that the parking space is parallel to the first parking space line of the road.
  • the parking space line of the parking space can be identified from the parking space image.
  • the parking space range is usually rectangular.
  • the parking space range of the parking space is composed of four corresponding sides of the rectangle, that is, four parking space lines, and has a certain aspect ratio.
  • the long side of the parking space is close to the road and parallel to the road, which is the first parking space line; the short side of the parking space is the line separating the two parking spaces, which is recorded as the second parking space line.
  • the short side of the parking space is close to the road and is the first parking space line; the long side of the parking space is the line separating the two parking spaces and is the second parking space line.
  • the connection between the first parking space line, the image acquisition device and the center of the parking space is vertical. If the image acquisition device is on the side of the parking space, On one side of the second parking space line of the parking space, the first parking space line is parallel to the line connecting the image acquisition device and the center of the parking space. From this, it can be recognized from the parking space image that the parking space is parallel to the first parking space line of the road, that is, if the relative position of the image acquisition device and the parking space is that the image acquisition device is on one side of the first parking space line of the parking space.
  • the line perpendicular to the connection between the center of the parking space and the image acquisition device in the image is regarded as the first parking space line; if the relative position of the image acquisition device and the parking space is on the side of the second parking space line where the image acquisition device is in the parking space , then the line in the image that is parallel to the connection between the center of the parking space and the image acquisition device is regarded as the first parking space line.
  • Step S203 Identify a second parking space line between two parking spaces from the at least one parking space image.
  • the second parking space line there is a vertical relationship between the second parking space line and the first parking space line. Then if the relative position of the image acquisition device and the parking space is that the image acquisition device is on one side of the first parking space line of the parking space, then the image and The parallel line connecting the center of the parking space and the image acquisition device is used as the second parking space line; if the relative position of the image acquisition device and the parking space is on one side of the second parking space line where the image acquisition device is on the parking space, then the image is The vertical line connecting the center of the parking space and the image acquisition device is used as the second parking space line.
  • Step S204 Determine the parking space range of the parking space based on the first parking space line and the second parking space line, so that the computing device associated with the parking space detects the relative relationship between the vehicle and the parking space.
  • the parking space is a rectangle composed of four lines, so the first parking space line and the second parking space line constitute the two sides of the parking space. There is another parking space line parallel to the first parking space line, and the second parking space line includes The line separating vehicles on both sides.
  • the parking space range can be obtained based on the first parking space line and the second parking space line, that is, the first parking space line and its parallel lines and the second parking space line constitute the parking space range.
  • the obtained parking space range can be sent to the computing device associated with the parking space for detecting the relative relationship between the vehicle and the parking space.
  • the relative relationship between the vehicle and the parking space can be identified through the collected images, which can be specifically the relative position in space. Based on whether the vehicle indicated by the relative position partially or fully enters the parking space range, it can be known whether the vehicle In the parking space, through the comparison of multiple consecutive images, it can also be further determined whether the vehicle has entered or exited the parking space, and then parking billing and whether the parking space is free can be carried out based on the time of entering and exiting the parking space. , unpaid alarm management, etc.
  • the computing device here can be a computing device in the cloud or near a parking space. With recent computing equipment, the latter can realize real-time calculation of parking space management, share the computing pressure of the cloud, and avoid the time delay problem caused by remote transmission.
  • the first parking space line of the parking space parallel to the road from at least one parking space image when identifying the first parking space line of the parking space parallel to the road from at least one parking space image, you can first identify the first parking space line in the at least one parking space image.
  • the first set of straight lines included can be realized through straight line detection.
  • the classic Hough transformation algorithm can be used to extract image edges and transform the edge point coordinates into Hough space.
  • Each point in Hough space represents a line.
  • Straight lines Points on the same straight line in the image will have intersection points in the Hough space.
  • the number of pixels contained in the Hough space per unit area is counted. If it is judged to be higher than the set threshold, it is determined that a straight line is included.
  • a second set of straight lines parallel to the road is determined from the first straight line set as the first parking space line of the parking space parallel to the road.
  • the first parking space line can be sorted according to the set threshold or distance from near to far.
  • the length of the straight line can also be used as a reference. If it is connected end to end, it is more likely to be the first parking space line. The longer side is the first parking space line. If they are arranged side by side, the shorter side is the first parking space line. The judgment can be made by setting a threshold or a numerical range.
  • the straight lines in the first straight line set can be grouped according to the degree of similarity.
  • the straight lines can be grouped according to the slope and offset value of the straight lines. The length and distance are compared for each group, and the one with the higher probability of the calculated result is Or multiple groups as the straight line corresponding to the first parking space line.
  • the brightness value of the parking space line can be obtained in advance.
  • the brightness value can be a preset value, or it can be a value input in advance by the manager on the parking space display interface, and is used to assist the parking space line.
  • a brightness value interval can be constructed based on the brightness value of the parking space line. For example, the brightness value of the parking space line is increased by a preset value upwards, and a preset value is subtracted downwards to construct a numerical interval composed of the two results.
  • the brightness value interval is used to filter the content of at least one parking space image, that is, the brightness value of each pixel is compared to see whether it is within the brightness value interval, and pixels that do not meet the brightness value interval are removed, because what is removed is the same as that of the brightness value interval.
  • Content areas with inconsistent parking space line brightness can be considered to have removed image areas that are irrelevant to the parking space lines.
  • the image data corresponding to the parking space image can also be converted to a preset color space including a brightness channel, so that the brightness value of each pixel of the image can be extracted to match the brightness of the parking space image according to the brightness value interval. Filter by the brightness value of the channel.
  • the manager's input on the interface can be used to assist in determining the parking space line, and the brightness value of the parking space line submitted through a selection operation on the parking space image displayed on the display screen can be obtained.
  • it can be a manager who manages road parking services in the cloud, and is responsible for handing over the parking space range to the corresponding parking space management party after the delineation is completed.
  • the parking space management party can participate in the auxiliary determination of parking space lines through terminal equipment.
  • the first straight line set included in at least one parking space image can be collected according to the image.
  • the relative position of the equipment and the parking space is determined from the first set of straight lines, a third set of straight lines perpendicular to the road, as the first parking space line of the parking space parallel to the road.
  • the first set of straight lines is divided into a second set of straight lines including the first parking space lines and a third set of straight lines including the second parking space lines.
  • the first parking space line and the second parking space line can be The relationship between lines excludes some unreasonable lines from the third straight line set. Since the extension lines of the first parking space line and the second parking space line intersect, the distance between the two lines is not too far, so Straight lines whose distance from the first parking space line exceeds the set range can also be deleted from the third straight line set.
  • a quadrilateral can be constructed based on the first parking space line in the second straight line set, and the first parking space line in the second straight line set is included, and then the calculation When the distance between the first parking space line and the second parking space line is calculated, the distance between the second parking space line and the quadrilateral can be calculated.
  • the third set of straight lines after deleting the over-range can also be grouped.
  • the straight lines in the first set of straight lines can be grouped according to the degree of similarity.
  • the straight lines can be grouped according to the slope and offset value of the straight lines.
  • the grouped straight lines can be grouped respectively. Calculate the distance between the quadrilateral and the quadrilateral, and delete straight line groups whose distance exceeds the set range.
  • the parking space range generally has one or several fixed aspect ratios.
  • the parking space range can be determined based on the first parking space line and the second parking space line.
  • the length or width can be supplemented according to the aspect ratio to avoid parking space lines fading or discoloration causing parking spaces.
  • the line collection is incomplete.
  • the intersection point of the first parking space line and the second parking space line may also be determined as the corresponding parking space for the multiple parking spaces.
  • the dividing point of the first parking space line Since the arrangement of multiple parking spaces from the perspective of the image collection device is in a certain proportional relationship from near to far, that is, it conforms to the principle of perspective, then the images that do not conform to the perspective can be deleted.
  • the intersection points corresponding to the first parking space line of the proportional relationship between the parking space lines of multiple parking spaces from the perspective of the device are collected, and the remaining intersection points that conform to the perspective principle are used as the basis for segmentation of the first parking space line.
  • the above method is executed on a cloud server, and the detected parking space range can be further sent to a computing device near the parking space.
  • the computing device detects the vehicle and the vehicle based on the vehicle detection algorithm issued by the cloud server. The relative relationship between the parking spaces.
  • the association between the image acquisition device and the computing device can also be registered on the cloud server, and the corresponding container instance can be added for data calculation by the parking space manager.
  • FIG. 3 is a parking space model according to an embodiment of the present application.
  • a flow chart of the surrounding processing method which includes:
  • Step S301 Obtain the parking space range of the parking space issued by the cloud server.
  • the parking space range is determined based on the first parking space line and the second parking space line identified in at least one parking space image.
  • the parking space image is determined by the parking space near the parking space.
  • the first parking space line is captured by an image acquisition device and is parallel to the road and determined based on the relative position of the image acquisition device and the parking space, and the second parking space line is a line spaced between two parking spaces;
  • Step S302 Based on the obtained parking space range, identify the relative relationship between the vehicle and the parking space in the parking space image newly collected by the image collection device.
  • one or more parking space images taken by an image acquisition device near the parking space are obtained, and further based on the relative position of the image acquisition device and the parking space, it is identified from the parking space image that the parking space is parallel to the road.
  • the first parking space line and the second parking space line between the two parking spaces so that the parking space range of the parking space can be determined based on the first parking space line and the second parking space line. It can be seen that this application provides an automatic identification of the parking space range.
  • This solution can improve the identification efficiency of the parking space range, make full use of the images obtained by the image collection equipment used for monitoring, reduce a lot of labor costs, and is suitable for scenarios where there are many parking spaces and are widely distributed, and can
  • the computing device associated with the parking space detects the relative relationship between the vehicle and the parking space, and further realizes practical needs such as automatic parking billing, parking space management, alarm management, camera deflection detection, and camera exposure detection in unmanned monitoring scenarios. It has broad application prospects.
  • the embodiments of the present application also provide a parking space range processing device.
  • Figure 4 shows the structure of the parking space range processing device according to an embodiment of the present application.
  • Block diagram, the device may include:
  • the image acquisition module 401 is used to acquire at least one parking space image captured by an image acquisition device near the parking space;
  • the first identification module 402 is used to identify the first parking space line of the parking space parallel to the road from the at least one parking space image based on the relative position of the image collection device and the parking space;
  • the second identification module 403 is used to identify the second parking space line between two parking spaces from the at least one parking space image
  • the parking space range determination module 404 is used to determine the parking space range of the parking space based on the first parking space line and the second parking space line, so that the computing device associated with the parking space detects the relative position between the vehicle and the parking space. relation.
  • the first identification module includes:
  • a straight line identification submodule used to identify the first set of straight lines included in the at least one parking space image
  • a straight line determination submodule configured to determine a second straight line set parallel to the road from the first straight line set based on the relative position of the image acquisition device and the parking space, as the parking space parallel to the road. First parking space line.
  • the straight line determination sub-module is specifically configured to select the first parking space line as the parking space parallel to the road according to the length of the straight line in the second straight line set and the distance from the center point of the image.
  • One or more straight lines, the relative position of the image acquisition device and the parking space is set such that the captured one or more parking spaces Located in the middle of the parking space image.
  • the device further includes:
  • the content screening module is used to construct a brightness value interval according to the brightness value of the parking space line, use the brightness value interval to perform content screening on the at least one parking space image, and remove image areas that are not related to the parking space line.
  • the device further includes:
  • the image conversion module is used to convert the image data corresponding to the at least one parking space image into a preset color space including a brightness channel, so as to correspond to the brightness of the at least one parking space image according to the brightness value interval. Filter by the brightness value of the channel.
  • the device further includes:
  • the brightness acquisition module is used to acquire the brightness value of the parking space line submitted by performing a selection operation on the parking space image displayed on the display screen.
  • the second identification module is specifically configured to identify, from the first set of straight lines included in the at least one parking space image, the relative position between the image acquisition device and the parking space. Position, determine a third set of straight lines perpendicular to the road from the first set of straight lines as the second parking space line of the parking space parallel to the road.
  • the second identification module further includes:
  • a straight line deletion sub-module configured to delete straight lines whose distance from the first parking space line exceeds a set range from the third straight line set.
  • the parking space range determination module includes:
  • the parking space range construction sub-module is used to construct the parking space range of the parking space based on the first parking space line and the second parking space line and the aspect ratio data of the parking space range.
  • the parking space range determination module further includes:
  • An intersection determination sub-module is used to determine the intersection point of the first parking space line and the second parking space line as the dividing point of the first parking space lines corresponding to multiple parking spaces;
  • intersection deletion submodule is used to delete the intersection point corresponding to the first parking space line that does not conform to the proportional relationship between the parking space lines of multiple parking spaces from the perspective of the image acquisition device.
  • the device is executed on a cloud server, and the device further includes:
  • a parking space range delivery module is used to deliver the detected parking space range to a computing device near the parking space.
  • the computing device detects the distance between the vehicle and the parking space based on the vehicle detection algorithm issued by the cloud server. relative relationship.
  • the device further includes:
  • a device registration module is used to register the association between the image acquisition device and the computing device on the cloud server, and add a corresponding container instance for data calculation by the manager of the parking space.
  • one or more parking space images taken by an image acquisition device near the parking space are obtained, and further based on the relative position of the image acquisition device and the parking space, it is identified from the parking space image that the parking space is parallel to the road.
  • the first parking space line and the second parking space line between the two parking spaces can be based on the first parking space line and the second parking space line.
  • the space line determines the parking space range of the parking space.
  • the computing device associated with the parking spaces can be used to detect the relative relationship between vehicles and parking spaces, further realizing parking in unmanned monitoring scenarios. It has broad application prospects for practical needs such as automatic billing, parking space management, alarm management, camera deflection detection, and camera exposure detection.
  • the embodiments of the present application also provide a parking space range processing device, which can be deployed in computing devices deployed near the parking spaces, as shown in Figure 5.
  • a parking space range processing device which can be deployed in computing devices deployed near the parking spaces, as shown in Figure 5.
  • the device may include:
  • the parking space range acquisition module 501 is used to obtain the parking space range of the parking space issued by the cloud server.
  • the parking space range is determined based on the first parking space line and the second parking space line identified in at least one parking space image.
  • the parking space image It is captured by an image acquisition device near a parking space.
  • the first parking space line is parallel to the road and determined based on the relative position of the image acquisition device and the parking space.
  • the second parking space line is between two parking spaces. spaced lines;
  • the behavior recognition module 502 is configured to identify the relative relationship between the vehicle and the parking space in the parking space image newly collected by the image collection device based on the obtained parking space range.
  • one or more parking space images taken by an image acquisition device near the parking space are obtained, and further based on the relative position of the image acquisition device and the parking space, it is identified from the parking space image that the parking space is parallel to the road.
  • the first parking space line and the second parking space line between the two parking spaces so that the parking space range of the parking space can be determined based on the first parking space line and the second parking space line. It can be seen that this application provides an automatic identification of the parking space range.
  • This solution can improve the identification efficiency of the parking space range, make full use of the images obtained by the image collection equipment used for monitoring, reduce a lot of labor costs, and is suitable for scenarios where there are many parking spaces and are widely distributed, and can
  • the computing device associated with the parking space detects the relative relationship between the vehicle and the parking space, and further realizes practical needs such as automatic parking billing, parking space management, alarm management, camera deflection detection, and camera exposure detection in unmanned monitoring scenarios. It has broad application prospects.
  • each module in each device of the embodiment of the present application can be found in the corresponding description in the above method, and have corresponding beneficial effects, which will not be described again here.
  • Figure 6 is a block diagram of a computing device used to implement embodiments of the present application.
  • the computing device includes: a memory 610 and a processor 620 .
  • the memory 610 stores a computer program that can run on the processor 620 .
  • the processor 620 executes the computer program, the method in the above embodiment is implemented.
  • the number of memory 610 and processor 620 may be one or more.
  • the computing device also includes:
  • the communication interface 630 is used to communicate with external devices and perform data interactive transmission.
  • the bus may be an Industry Standard Architecture (Industry Standard Architecture, ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus, etc.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one thick line is used in Figure 6, but it does not mean that there is only one bus or one type of bus.
  • the memory 610, the processor 620 and the communication interface 630 are integrated on one chip, the memory 610, the processor 620 and the communication interface 630 can communicate with each other through the internal interface.
  • Embodiments of the present application provide a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, the method provided in the embodiment of the present application is implemented.
  • An embodiment of the present application also provides a chip, which includes a processor for calling and running instructions stored in the memory, so that the communication device installed with the chip executes the method provided by the embodiment of the present application.
  • Embodiments of the present application also provide a chip, including: an input interface, an output interface, a processor and a memory.
  • the input interface, the output interface, the processor and the memory are connected through an internal connection path, and the processor is used to execute the code in the memory. , when the code is executed, the processor is used to execute the method provided by the application embodiment.
  • processor can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • CPU Central Processing Unit
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • a general-purpose processor can be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports Advanced RISC Machines (ARM) architecture.
  • ARM Advanced RISC Machines
  • the above-mentioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory.
  • the memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • non-volatile memory can include read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically removable memory. Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may include random access memory (RAM), which is used as an external cache.
  • RAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • DDR SDRAM double data rate synchronous dynamic random access Memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synchlink DRAM, SLDRAM synchronous link dynamic random access memory
  • Direct Rambus RAM Direct Rambus RAM
  • a computer program product includes one or more computer instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • references to the terms “one embodiment,” “some embodiments,” “an example,” “specific examples,” or “some examples” or the like means that specific features are described in connection with the embodiment or example.
  • structures, materials or features are included in at least one embodiment or example of the present application.
  • the specific features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
  • those skilled in the art may combine and combine different embodiments or examples and features of different embodiments or examples described in this specification unless they are inconsistent with each other.
  • first and second are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Thus, features defined as “first” and “second” may explicitly or implicitly include at least one of these features. In the description of this application, “plurality” means two or more than two, unless otherwise explicitly and specifically limited.
  • logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered a sequenced list of executable instructions for implementing the logical functions, and may be embodied in any computer-readable medium, For use by, or in combination with, instruction execution systems, devices or devices (such as computer-based systems, systems including processors or other systems that can fetch instructions from and execute instructions from the instruction execution system, device or device) or equipment.
  • various parts of the present application may be implemented in hardware, software, firmware, or a combination thereof.
  • various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the method in the above embodiment can be completed by instructing relevant hardware through a program.
  • the program can be stored in a computer-readable storage medium. When executed, the program includes one of the steps of the method embodiment or other steps. combination.
  • each functional unit in various embodiments of the present application can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or software function modules.
  • the above integrated modules can also be stored if they are implemented in the form of software function modules and sold or used as independent products. in a computer-readable storage medium.
  • the storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请提供了一种车位范围的处理方法及计算设备，涉及云计算技术领域。本申请实施例通过获取停车位附近的图像采集设备拍摄的一张或多张停车位图像，进一步根据该图像采集设备与停车位的相对位置，从停车位图像中识别停车位平行于道路的第一车位线以及两个停车位间隔的第二车位线，进一步确定停车位的车位范围，由此可见，可以提高车位范围的识别效率，可以对用于监测的图像采集设备获得的图像进行充分利用，减少大量的人力成本，适合于较多停车位分布且分布较广的场景，可以实现无人监测场景下的停车自动计费、停车位管理、告警管理、摄像头偏转检测、摄像头曝光度检测等现实需求，具有较广阔的应用前景。

Description

车位范围的处理方法及计算设备
本申请要求于2022年06月16日提交中国专利局、申请号为202210686320.1、申请名称为“车位范围的处理方法及计算设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及云计算技术领域，尤其涉及一种车位范围的处理方法及计算设备。
背景技术
通过对车位进行监测可以实现对车位的远程管理，在基于采集到的图像进行识别时，通常需要绘制出物理世界的车位范围在采集的画面区域中对应的划线，以用于算法下一步的处理。
目前，车位范围的划线是基于人工方式实现的，由于车位的分布通常是比较大的区域，涉及到的车位个数也比较多，因此，车位范围的划线会耗费大量的人力和时间成本。
发明内容
本申请实施例提供一种车位范围的处理方法及计算设备，以实现对停车位的车位范围计算和停车位的管理。
第一方面，本申请实施例提供了一种车位范围的处理方法，包括：
获取停车位附近的图像采集设备拍摄的至少一张停车位图像；
根据所述图像采集设备与所述停车位的相对位置，从所述至少一张停车位图像中识别所述停车位平行于道路的第一车位线；
从所述至少一张停车位图像中识别两个停车位间隔的第二车位线；
基于所述第一车位线和第二车位线确定所述停车位的车位范围，以用于与所述停车位关联的计算设备检测车辆与所述停车位的相对关系。
第二方面，本申请实施例提供了一种车位范围的处理方法，应用于停车位附近位置部署的计算设备，所述方法包括：
获取云端服务器下发的停车位的车位范围，所述车位范围基于至少一张停车位图像中识别的第一车位线和第二车位线确定，所述停车位图像由停车位附近的图像采集设备拍摄获得，所述第一车位线平行于道路并根据所述图像采集设备与所述停车位的相对位置确定，所述第二车位线为两个停车位之间间隔的线；
基于所获取的车位范围，识别所述图像采集设备新采集的停车位图像中车辆与所述停车位的相对关系。
第三方面，本申请实施例提供了一种计算设备，包括存储器、处理器及存储在存储器上的计算机程序，所述处理器在执行所述计算机程序时实现上述所述的方法。
与现有技术相比，本申请具有如下优点：
依据本申请实施例，通过获取停车位附近的图像采集设备拍摄的一张或多张停车位图像，进一步根据该图像采集设备与停车位的相对位置，从停车位图像中识别停车位平行于道路的第一车位线以及两个停车位间隔的第二车位线，从而可以基于第一车位线和第二车位线确定停车位的车位范围，由此可见，本申请提供了一种车位范围自动识别的方案，可以提高车位范围的识别效率，可以对用于监测的图像采集设备获得的图像进行充分利用，减少大量的人力成本，适合于较多停车位分布且分布较广的场景，并且，可以用于与停车位关联的计算设备检测车辆与停车位的相对关系，进一步实现无人监测场景下的停车自动计费、停车位管理、告警管理、摄像头偏转检测、摄像头曝光度检测等现实需求，具有较广阔的应用前景。
上述概述仅仅是为了说明书的目的，并不意图以任何方式进行限制。除上述描述的示意性的方面、实施方式和特征之外，通过参考附图和以下的详细描述，本申请进一步的方面、实施方式和特征将会是容易明白的。
附图说明
在附图中，除非另外规定，否则贯穿多个附图相同的附图标记表示相同或相似的部件或元素。这些附图不一定是按照比例绘制的。应该理解，这些附图仅描绘了根据本申请公开的一些实施方式，而不应将其视为是对本申请范围的限制。
图1为示例性的用于实现本申请实施例的方法的一个应用场景的示意图；
图2为本申请一实施例的车位范围的处理方法的流程图；
图3是本申请另一实施例的车位范围的处理方法的流程图；
图4是本申请一实施例的车位范围的处理装置的结构框图；
图5是本申请另一实施例的车位范围的处理装置的结构框图；
图6为用来实现本申请实施例的计算设备的框图。
具体实施方式
在下文中，仅简单地描述了某些示例性实施例。正如本领域技术人员可认识到的那样，在不脱离本申请的精神或范围的情况下，可通过各种不同方式修改所描述的实施例。因此，附图和描述被认为本质上是示例性的而非限制性的。
为便于理解本申请实施例的技术方案，以下对本申请实施例的相关技术进行说明，以下相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合，其均属于本申请实施例的保护范围。
针对现有的车位范围(也即是车位框)划线采用人工实现带来的高成本问题，本申请 实施例提供了一种车位范围的处理方法。通过预先在停车位附近设置图像采集设备，通过获取图像采集设备采集的一张或多张停车位图像，根据图像采集设备与停车位的相对位置，从停车位图像中识别停车位的两种车位线，一种是停车位平行于道路的第一车位线，一种是停车位之间间隔的第二车位线，进而可以基于两种车位线实现对车位范围的自动确定。相比于人工划线的方案，可以提高车位范围的识别效率，可以对用于监测的图像采集设备获得的图像进行充分利用，减少大量的人力成本，适合于较多停车位分布且分布较广的场景。
依据上述确定的车位范围可以进一步检测车辆与停车位的相对关系，管理车辆对停车位的占用行为，实现无人监测场景下的停车计费、停车位管理、告警管理、摄像头偏转检测、摄像头曝光度检测等现实需求，具有较广阔的应用前景。具体可以实现为高位视频智慧停车系统，利用安装在停车位附近的图像采集设备进行停车位占用的分析。
本申请实施例特别适合于道路停车的情况下，相比于停车场停车，道路停车由于没有设定好的进口和出口，可以随意进入和驶出，从而带来了较大的管理难度，较为突出的是收费困难的问题，现有的道路收费通常是人工完成的，需要配备人员蹲守在车位附近查看车辆进出情况并记录车辆停靠情况，还需要再驶出车辆时快速向司机收取费用，工作繁杂且量大，且计时准确性较低。依据本申请实施例的方案，可以结合图像采集设备采集到的图像进一步进行车辆驶入和驶出的监测，从而实现自动的停车计费。可以将计费结果直接发送到车辆司机对应的移动终端，例如，可以根据监测到的车牌号或车辆特征进行车主检测，进一步确定车主对应的移动终端标识，将计费结果以消息或通知的形式进行发送，车主通过自己的移动终端即可实现缴费。既无需配备人员计费和收费，也无需车主停车缴费，车辆停放后或是驶离都可以无需任何交互操作，提高计时准确性的同时，还可以提高停车位使用效率，避免影响道路交通。并且，车主还可以通过自己的移动终端连接云端服务器或是连接计算设备，实时查看停车位状态，实时查看到停车位信息，可以提高停车的效率。
一种可选的实现方式中，上述对车位范围的确定可以基于云端实现，可以在停车位附近配置计算设备，用于进行车位管理的实时计算，一方面可以分担云端的计算压力，另一方面可以实现数据的快速运算，避免远程传输带来的时间延迟问题。因此，可以将确定的车位范围下发到停车位附近的计算设备，由计算设备负责车辆驶入和驶出、计费等等各项管理。
本申请实施例的方案还可以结合云端服务器实现，可以在云端的道路停车服务中增加对图像采集设备的管理，并向停车位的管理方提供专用的容器实例，对图像采集设备采集并传送到云端服务器的停车位图像进行相应的数据运算。图1为示例性的用于实现本申请实施例的方法的一个应用场景的示意图。将整个架构划分为云端和停车位附近的边缘端，停车位一般会有多个，可以根据需要部署一个或多个图像采集设备，其中一个图像采集设备可以对应拍摄一个或多个停车位的图像(例如一个图像采集设备对应3-4个停车位)。图像采集设备具体可以是带有网络通信功能的IPC(IP Camera，网络摄像机)，从而可以将 采集到的图像通过路由器实时上传到云端服务器，云端可以通过视频边缘智能服务平台接收图像，进一步对图像进行识别，如图可以将图像传输到专用于道路监测的道路停车服务引擎进行管理，具体采用图像算法应用进行车位范围的识别。在识别到车位范围之后可以下发到边缘的计算设备，也即是图中的道路停车一体机，用于后续根据采集到的图像进行车辆驶入驶出或计费等功能，并生成对应的事件通知，道路停车服务引擎可以通过监听云端的IOT(Internet of Things，物联网设备)平台的消息获取到事件通知，或是通知到停车位的管理方的终端设备。
其中，边缘的图像采集设备和道路停车一体机可以通过云端的IOT平台进行接入和管理，停车位的管理方可以通过与一体机连接的终端设备或是通过与云端平台通信的终端设备获取停车位的状态数据，实现对停车位状态的查看管理，还可以监测图像采集设备状态以便及时维修相关问题。
如下给出本申请具体的实施例方案，本申请实施例提供了一种车位范围的处理方法，该方法可以应用于云端服务器或停车位附近的计算设备，图2是本申请一实施例的车位范围的处理方法的流程图。如图2所示，该方法包括：
步骤S201，获取停车位附近的图像采集设备拍摄的至少一张停车位图像。
本申请实施例所述的图像采集设备可以是网络摄像机，也可以是道路监测的高速球摄像机、录像机等任意可以采集图像的设备，采集的图像可以为图像形式或是视频中提取的视频帧形式。为实现采集的图像向云端的传输，可以为图像采集设备配置相应的网络连接功能。图像采集设备可以部署在停车位附近的位置，以便于可以采集到停车位区域的图像，具体可以是在较高的位置，以俯视的视角采集图像，或是在较低的位置以仰视的视角采集图像，还可以是平视视角，为了使得采集的图像更完整避免遮挡物或是低处容易损坏的问题，可以将图像采集设备设置于高处。图像采集设备通常会将停车位拍摄到图像的中间位置，以获得与停车位更多相关的信息内容。
本申请实施例的停车位可以是车辆首尾相邻的形式，也可以是并列排布的形式。当本申请实施例应用于道路停车位场景下时，通常是首尾相邻的形式，为提高设备利用率，可以采用停车位现有的监测设备(例如道路监测的高速球摄像机)，在实现道路监测的同时，对停车位进行监测。
本实施例由云端服务器完成时，可以在云端服务器增加对图像采集设备的管理，也即是注册图像采集设备作为一个物联网设备，并获得相应的计算空间。
图像采集设备的个数可以根据实际需要设定，以便于可以监测到较完整的停车位区域，例如一般可以是一个图像采集设备对应监测几个停车位区域，当然，图像采集设备数量的增加可以提高监测的准确性，同时也会提高硬件成本和数据计算量，可以根据实际需要增加或减少图像采集设备的个数。图像采集设备采集到的可以是图像或是视频，则对应停车位图像可以是一张或多张图像或是提取于视频的视频帧。
步骤S202，根据所述图像采集设备与所述停车位的相对位置，从所述至少一张停车 位图像中识别所述停车位平行于道路的第一车位线。
图像采集设备与停车位之间存在距离，根据图像采集设备与停车位的相对位置，可以从停车位图像中识别到停车位的车位线。基于目前大多数车辆的形状，车位范围通常都是长方形的，停车位的车位范围由长方形对应的四条边，也即是四条车位线构成，且具有一定的长宽比。
以首尾相邻的车位为例，车位长边的一侧靠近道路，且平行于道路，为第一车位线；车位短边的一侧是两个车位的间隔的线，记为第二车位线，通常是两个车位共用的车位线。以并列排布的车位为例，车位的短边的一侧靠近道路，为第一车位线；车位长边的一侧是两个车位的间隔的线，为第二车位线。
针对上述两种排布方式，若图像采集设备在停车位的第一车位线的一侧，则第一车位线与图像采集设备和停车位中心的连线是垂直的，若图像采集设备在停车位的第二车位线的一侧，则第一车位线与图像采集设备和停车位中心的连线是平行的。由此可以从停车位图像中识别到停车位平行于道路的第一车位线，也即是，若图像采集设备与停车位的相对位置是图像采集设备在停车位的第一车位线的一侧，则将图像中与停车位中心与图像采集设备的连线垂直的线作为第一车位线；若图像采集设备与停车位的相对位置是图像采集设备在停车位的第二车位线的一侧，则将图像中与停车位中心与图像采集设备的连线平行的线作为第一车位线。
步骤S203，从所述至少一张停车位图像中识别两个停车位间隔的第二车位线。
相应的，第二车位线与第一车位线之间是垂直关系，那么若图像采集设备与停车位的相对位置是图像采集设备在停车位的第一车位线的一侧，则将图像中与停车位中心与图像采集设备的连线平行的线作为第二车位线；若图像采集设备与停车位的相对位置是图像采集设备在停车位的第二车位线的一侧，则将图像中与停车位中心与图像采集设备的连线垂直的线作为第二车位线。
步骤S204，基于所述第一车位线和第二车位线确定所述停车位的车位范围，以用于与所述停车位关联的计算设备检测车辆与所述停车位的相对关系。
停车位是由四条线构成的长方形，那么第一车位线和第二车位线构成了停车位的两种边，与第一车位线平行的还有另外一条车位线，第二车位线则是包括了两边车辆间隔的线。根据第一车位线和第二车位线就可以得到车位范围，也即是将第一车位线及其平行的线和第二车位线构成车位范围。
获得的车位范围可以下发到停车位关联的计算设备以用于检测车辆与停车位的相对关系。在划定车位范围之后，可以通过采集到的图像识别车辆与停车位的相对关系，具体可以是空间上的相对位置，根据相对位置指示的车辆是否部分或全部进入了车位范围，可以获知车辆是否在停车位，通过连续多张图像的对比，还可以进步确定车辆驶入了停车位还是驶出了停车位，进而可以根据驶入和驶出停车位的时间进行停车计费、停车位是否空闲、未缴费的告警管理等等。此处的计算设备可以是云端的计算设备，也可以是停车位附 近的计算设备，后者可以实现车位管理的实时计算，分担云端的计算压力，避免远程传输带来的时间延迟问题。
一种可能的实现方式中，根据图像采集设备与停车位的相对位置，从至少一张停车位图像中识别停车位平行于道路的第一车位线时，可以先识别至少一张停车位图像中包括的第一直线集合，通过直线检测可以实现，例如可以采用经典的霍夫变换算法，通过提取图像边缘，并将边缘点坐标变换到霍夫空间，霍夫空间中每个点都代表一条直线，图像中同一直线上的点在霍夫空间会产生交点，在单位面积的霍夫空间中进行包含的像素点数统计，若判断为高于设定阈值，则确定包含一条直线。或是，还可以采用其他算法，例如Wireframe(基于网格线的直线检测)算法、LCNN(Lookup-based Convolutional Neural Network，基于查找的卷积神经网络)等等。
进一步根据图像采集设备与所述停车位的相对位置，从第一直线集合中确定与道路平行的第二直线集合，作为停车位平行于道路的第一车位线。根据图像采集设备采集的停车位图像会将停车位置于图像中心位置的思路，也即是说图像采集设备与所述停车位的相对位置设置为使得采集的一个或多个停车位位于停车位图像的中间位置上，可以按照第二直线集合中直线的长度和距离图像中心点的距离，选取作为停车位平行于道路的第一车位线的一条或多条直线，距离图像中心点距离近直线，则为第一车位线的概率较高，可以根据设定的阈值或是距离由近到远排序靠前的为第一车位线，直线的长度也可以作为参考，若是首尾相连的情况，则较长的边为第一车位线，若并列排布的情况，则较短的边为第一车位线，可以通过设定一个阈值或是数值范围来进行判断。
其中，可以对第一直线集合中的直线按照相近程度进行分组，例如可以按照直线的斜率和偏移值进行分组，针对每个分组进行长度和距离的比较，将计算结果概率较高的一个或多个组作为第一车位线对应的直线。
一种可能的实现方式中，可以预先获取车位线的亮度值，该亮度值可以是预先设定的值，也可以是预先根据管理人员在停车位显示界面输入的值，用于辅助车位线的确定。根据车位线的亮度值可以构建亮度数值区间，例如取车位线的亮度值向上增加一个预设值，向下减去一个预设值，构建由两个结果构成的数值区间。进一步，采用亮度数值区间对至少一张停车位图像进行内容筛选，也即是，比对各像素的亮度值是否再亮度数值区间内，将不符合亮度数值区间的像素去除，由于去除的是与车位线亮度不一致的内容区域，则可以认为去除了与车位线不相关的图像区域。
在上述比对之前，还可以将停车位图像对应的图像数据转换至包括亮度通道的预设色彩空间下，从而可以提取图像各像素的亮度值，以根据亮度数值区间对停车位图像对应在亮度通道的亮度值进行筛选。
一种可能的实现方式中，可以借助管理人员在界面的输入来辅助确定车位线，获取通过对显示屏上展示的停车位图像执行的选取操作提交的车位线的亮度值。例如可以是云端管理道路停车服务的管理人员，负责将车位范围划线完成之后交接给对应的停车位管理方， 或是由停车位管理方通过终端设备参与到车位线的辅助确定中。
一种可能的实现方式中，相应的，从停车位图像中识别两个停车位间隔的第二车位线时，可以从至少一张停车位图像中包括的第一直线集合中，根据图像采集设备与所述停车位的相对位置，从第一直线集合中确定与道路垂直的第三直线集合，作为停车位平行于道路的第一车位线。从而将第一直线集合划分为包括第一车位线的第二直线集合和包括第二车位线的第三直线集合。
一种可能的实现方式中，为提高第二车位线查找的准确率，从至少一张停车位图像中识别两个停车位间隔的第二车位线时，可以根据第一车位线和第二车位线之间的关系从第三直线集合中排除一部分不合理的线，由于第一车位线和第二车位线的延长线是有交集的，两条线之间的距离并不会太远，因此还可以从第三直线集合中删除与第一车位线距离超出设定范围的直线。
具体的，由于车位线准确来说是有宽度的四边形，因此，可以先根据第二直线集合中的第一车位线构建四边形，把第二直线集合中的第一车位线包括进去，进而在计算第一车位线和第二车位线之间的距离时，可以计算第二车位线和四边形之间的距离。
还可以对删除超范围后的第三直线集合，进行分组，可以对第一直线集合中的直线按照相近程度进行分组，例如可以按照直线的斜率和偏移值进行分组，分组后的直线分别计算和四边形之间的距离，删除距离超出设定范围的直线分组。
一种可能的实现方式中，车位范围一般是有一种或几种固定的长宽比，基于第一车位线和第二车位线确定停车位的车位范围时，可以根据第一车位线和第二车位线以及车位范围的长宽比数据，构建停车位的车位范围，针对两条线，确定车位范围时，可以根据长宽比进行长度或宽度的补充，以避免车位线褪色或是掉色导致车位线采集不完整的情况。
一种可能的实现方式中，上述基于第一车位线和第二车位线确定停车位的车位范围时，还可以确定第一车位线与第二车位线的交点，作为多个停车位分别对应的第一车位线的分界点，由于多个停车位在图像采集设备视角下的排布按照由近及远的位置是呈一定的比例关系的，也即是符合透视原理，则可以删除不符合图像采集设备视角下多个停车位的车位线比例关系的第一车位线对应的交点，剩余的符合透视原理的交点作为第一车位线的分割依据。
一种可能的实现方式中，上述方法在云端服务器执行，可以进一步将所检测到的车位范围下发至所述停车位附近的计算设备，计算设备基于云端服务器下发的车辆检测算法检测车辆与所述停车位的相对关系。
一种可能的实现方式中，在上述方案执行之前，还可以在云端服务器注册图像采集设备与计算设备的关联关系，并添加对应的容器实例以用于停车位的管理方的数据运算。
上述实施例给出了车位范围的确定过程，如下基于确定的车位范围提供其相关的处理方案，可以应用于停车位附近位置部署的计算设备。图3是本申请一实施例的一种车位范 围的处理方法的流程图，该方法包括：
步骤S301，获取云端服务器下发的停车位的车位范围，所述车位范围基于至少一张停车位图像中识别的第一车位线和第二车位线确定，所述停车位图像由停车位附近的图像采集设备拍摄获得，所述第一车位线平行于道路并根据所述图像采集设备与所述停车位的相对位置确定，所述第二车位线为两个停车位之间间隔的线；
步骤S302，基于所获取的车位范围，识别所述图像采集设备新采集的停车位图像中车辆与所述停车位的相对关系。
上述内容可以参考上个实施例所述，此处不再赘述。
依据本申请实施例，通过获取停车位附近的图像采集设备拍摄的一张或多张停车位图像，进一步根据该图像采集设备与停车位的相对位置，从停车位图像中识别停车位平行于道路的第一车位线以及两个停车位间隔的第二车位线，从而可以基于第一车位线和第二车位线确定停车位的车位范围，由此可见，本申请提供了一种车位范围自动识别的方案，可以提高车位范围的识别效率，可以对用于监测的图像采集设备获得的图像进行充分利用，减少大量的人力成本，适合于较多停车位分布且分布较广的场景，并且，可以用于与停车位关联的计算设备检测车辆与停车位的相对关系，进一步实现无人监测场景下的停车自动计费、停车位管理、告警管理、摄像头偏转检测、摄像头曝光度检测等现实需求，具有较广阔的应用前景。
与本申请实施例提供的方法的应用场景以及方法相对应地，本申请实施例还提供一种车位范围的处理装置，如图4所示为本申请一实施例的车位范围的处理装置的结构框图，该装置可以包括：
图像获取模块401，用于获取停车位附近的图像采集设备拍摄的至少一张停车位图像；
第一识别模块402，用于根据所述图像采集设备与所述停车位的相对位置，从所述至少一张停车位图像中识别所述停车位平行于道路的第一车位线；
第二识别模块403，用于从所述至少一张停车位图像中识别两个停车位间隔的第二车位线；
车位范围确定模块404，用于基于所述第一车位线和第二车位线确定所述停车位的车位范围，以用于与所述停车位关联的计算设备检测车辆与所述停车位的相对关系。
一种可能的实现方式中，所述第一识别模块包括：
直线识别子模块，用于识别所述至少一张停车位图像中包括的第一直线集合；
直线确定子模块，用于根据所述图像采集设备与所述停车位的相对位置，从所述第一直线集合中确定与道路平行的第二直线集合，作为所述停车位平行于道路的第一车位线。
一种可能的实现方式中，所述直线确定子模块，具体用于按照所述第二直线集合中直线的长度和距离图像中心点的距离，选取作为停车位平行于道路的第一车位线的一条或多条直线，所述图像采集设备与所述停车位的相对位置设置为使得采集的一个或多个停车位 位于所述停车位图像的中间位置上。
一种可能的实现方式中，所述装置还包括：
内容筛选模块，用于根据车位线的亮度值构建亮度数值区间，采用所述亮度数值区间对所述至少一张停车位图像进行内容筛选，去除与车位线不相关的图像区域。
一种可能的实现方式中，所述装置还包括：
图像转换模块，用于将所述至少一张停车位图像对应的图像数据转换至包括亮度通道的预设色彩空间下，以根据所述亮度数值区间对所述至少一张停车位图像对应在亮度通道的亮度值进行筛选。
一种可能的实现方式中，所述装置还包括：
亮度获取模块，用于获取通过对显示屏上展示的停车位图像执行的选取操作提交的车位线的亮度值。
一种可能的实现方式中，所述第二识别模块，具体用于从所述至少一张停车位图像中包括的第一直线集合中，根据所述图像采集设备与所述停车位的相对位置，从所述第一直线集合中确定与道路垂直的第三直线集合，作为所述停车位平行于道路的第二车位线。
一种可能的实现方式中，所述第二识别模块还包括：
直线删除子模块，用于从所述第三直线集合中删除与所述第一车位线距离超出设定范围的直线。
一种可能的实现方式中，所述车位范围确定模块包括：
车位范围构建子模块，用于根据所述第一车位线和第二车位线以及车位范围的长宽比数据，构建所述停车位的车位范围。
一种可能的实现方式中，所述车位范围确定模块还包括：
交点确定子模块，用于确定所述第一车位线与所述第二车位线的交点，作为多个停车位分别对应的第一车位线的分界点；
交点删除子模块，用于删除不符合图像采集设备视角下多个停车位的车位线比例关系的第一车位线对应的交点
一种可能的实现方式中，所述装置在云端服务器执行，所述装置还包括：
车位范围下发模块，用于将所检测到的车位范围下发至所述停车位附近的计算设备，所述计算设备基于所述云端服务器下发的车辆检测算法检测车辆与所述停车位的相对关系。
一种可能的实现方式中，所述装置还包括：
设备注册模块，用于在云端服务器注册所述图像采集设备与计算设备的关联关系，并添加对应的容器实例以用于所述停车位的管理方的数据运算。
依据本申请实施例，通过获取停车位附近的图像采集设备拍摄的一张或多张停车位图像，进一步根据该图像采集设备与停车位的相对位置，从停车位图像中识别停车位平行于道路的第一车位线以及两个停车位间隔的第二车位线，从而可以基于第一车位线和第二车 位线确定停车位的车位范围，由此可见，本申请提供了一种车位范围自动识别的方案，可以提高车位范围的识别效率，可以对用于监测的图像采集设备获得的图像进行充分利用，减少大量的人力成本，适合于较多停车位分布且分布较广的场景，并且，可以用于与停车位关联的计算设备检测车辆与停车位的相对关系，进一步实现无人监测场景下的停车自动计费、停车位管理、告警管理、摄像头偏转检测、摄像头曝光度检测等现实需求，具有较广阔的应用前景。
与本申请实施例提供的方法的应用场景以及方法相对应地，本申请实施例还提供一种车位范围的处理装置，可以部署于停车位附近位置部署的计算设备，如图5所示为本申请另一实施例的车位范围的处理装置的结构框图，该装置可以包括：
车位范围获取模块501，用于获取云端服务器下发的停车位的车位范围，所述车位范围基于至少一张停车位图像中识别的第一车位线和第二车位线确定，所述停车位图像由停车位附近的图像采集设备拍摄获得，所述第一车位线平行于道路并根据所述图像采集设备与所述停车位的相对位置确定，所述第二车位线为两个停车位之间间隔的线；
行为识别模块502，用于基于所获取的车位范围，识别所述图像采集设备新采集的停车位图像中车辆与所述停车位的相对关系。
依据本申请实施例，通过获取停车位附近的图像采集设备拍摄的一张或多张停车位图像，进一步根据该图像采集设备与停车位的相对位置，从停车位图像中识别停车位平行于道路的第一车位线以及两个停车位间隔的第二车位线，从而可以基于第一车位线和第二车位线确定停车位的车位范围，由此可见，本申请提供了一种车位范围自动识别的方案，可以提高车位范围的识别效率，可以对用于监测的图像采集设备获得的图像进行充分利用，减少大量的人力成本，适合于较多停车位分布且分布较广的场景，并且，可以用于与停车位关联的计算设备检测车辆与停车位的相对关系，进一步实现无人监测场景下的停车自动计费、停车位管理、告警管理、摄像头偏转检测、摄像头曝光度检测等现实需求，具有较广阔的应用前景。
本申请实施例各装置中的各模块的功能可以参见上述方法中的对应描述，并具备相应的有益效果，在此不再赘述。
图6为用来实现本申请实施例的计算设备的框图。如图6所示，该计算设备包括：存储器610和处理器620，存储器610内存储有可在处理器620上运行的计算机程序。处理器620执行该计算机程序时实现上述实施例中的方法。存储器610和处理器620的数量可以为一个或多个。
该计算设备还包括：
通信接口630，用于与外界设备进行通信，进行数据交互传输。
如果存储器610、处理器620和通信接口630独立实现，则存储器610、处理器 620和通信接口630可以通过总线相互连接并完成相互间的通信。该总线可以是工业标准体系结构(Industry Standard Architecture，ISA)总线、外部设备互连(Peripheral Component Interconnect，PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture，EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
可选的，在具体实现上，如果存储器610、处理器620及通信接口630集成在一块芯片上，则存储器610、处理器620及通信接口630可以通过内部接口完成相互间的通信。
本申请实施例提供了一种计算机可读存储介质，其存储有计算机程序，该程序被处理器执行时实现本申请实施例中提供的方法。
本申请实施例还提供了一种芯片，该芯片包括，包括处理器，用于从存储器中调用并运行存储器中存储的指令，使得安装有芯片的通信设备执行本申请实施例提供的方法。
本申请实施例还提供了一种芯片，包括：输入接口、输出接口、处理器和存储器，输入接口、输出接口、处理器以及存储器之间通过内部连接通路相连，处理器用于执行存储器中的代码，当代码被执行时，处理器用于执行申请实施例提供的方法。
应理解的是，上述处理器可以是中央处理器(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。值得说明的是，处理器可以是支持进阶精简指令集机器(Advanced RISC Machines，ARM)架构的处理器。
进一步地，可选的，上述存储器可以包括只读存储器和随机存取存储器，还可以包括非易失性随机存取存储器。该存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以包括只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以包括随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用。例如，静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic Random Access Memory，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总 线随机存取存储器(Direct Rambus RAM，DR RAM)。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包括于本申请的至少一个实施例或示例中。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或隐含地包括至少一个该特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分。并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。
应理解的是，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。上述实施例方法的全部或部分步骤是可以通过程序来指令相关的硬件完成，该程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。上述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储 在一个计算机可读存储介质中。该存储介质可以是只读存储器，磁盘或光盘等。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到其各种变化或替换，这些都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (14)

  1. 一种车位范围的处理方法，其特征在于，包括：
    获取停车位附近的图像采集设备拍摄的至少一张停车位图像；
    根据所述图像采集设备与所述停车位的相对位置，从所述至少一张停车位图像中识别所述停车位平行于道路的第一车位线；
    从所述至少一张停车位图像中识别两个停车位间隔的第二车位线；
    基于所述第一车位线和第二车位线确定所述停车位的车位范围，以用于与所述停车位关联的计算设备检测车辆与所述停车位的相对关系。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述图像采集设备与所述停车位的相对位置，从所述至少一张停车位图像中识别所述停车位平行于道路的第一车位线包括：
    识别所述至少一张停车位图像中包括的第一直线集合；
    根据所述图像采集设备与所述停车位的相对位置，从所述第一直线集合中确定与道路平行的第二直线集合，作为所述停车位平行于道路的第一车位线。
  3. 根据权利要求2所述的方法，其特征在于，所述从所述第一直线集合中确定与道路平行的第二直线集合，作为所述停车位平行于道路的第一车位线包括：
    按照所述第二直线集合中直线的长度和距离图像中心点的距离，选取作为停车位平行于道路的第一车位线的一条或多条直线，所述图像采集设备与所述停车位的相对位置设置为使得采集的一个或多个停车位位于所述停车位图像的中间位置上。
  4. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据车位线的亮度值构建亮度数值区间，采用所述亮度数值区间对所述至少一张停车位图像进行内容筛选，去除与车位线不相关的图像区域。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    将所述至少一张停车位图像对应的图像数据转换至包括亮度通道的预设色彩空间下，以根据所述亮度数值区间对所述至少一张停车位图像对应在亮度通道的亮度值进行筛选。
  6. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    获取通过对显示屏上展示的停车位图像执行的选取操作提交的车位线的亮度值。
  7. 根据权利要求1所述的方法，其特征在于，所述从所述至少一张停车位图像中识别两个停车位间隔的第二车位线包括：
    从所述至少一张停车位图像中包括的第一直线集合中，根据所述图像采集设备与所述停车位的相对位置，从所述第一直线集合中确定与道路垂直的第三直线集合，作为所述停车位平行于道路的第二车位线。
  8. 根据权利要求7所述的方法，其特征在于，所述从所述至少一张停车位图像中识别两个停车位间隔的第二车位线还包括：
    从所述第三直线集合中删除与所述第一车位线距离超出设定范围的直线。
  9. 根据权利要求1所述的方法，其特征在于，所述基于所述第一车位线和第二车位线确定所述停车位的车位范围包括：
    根据所述第一车位线和第二车位线以及车位范围的长宽比数据，构建所述停车位的车位范围。
  10. 根据权利要求9所述的方法，其特征在于，所述基于所述第一车位线和第二车位线确定所述停车位的车位范围还包括：
    确定所述第一车位线与所述第二车位线的交点，作为多个停车位分别对应的第一车位线的分界点；
    删除不符合图像采集设备视角下多个停车位的车位线比例关系的第一车位线对应的交点。
  11. 根据权利要求1所述的方法，其特征在于，所述方法在云端服务器执行，所述方法还包括：
    将所检测到的车位范围下发至所述停车位附近的计算设备，所述计算设备基于所述云端服务器下发的车辆检测算法检测车辆与所述停车位的相对关系。
  12. 根据权利要求1所述的方法，其特征在于，还包括：
    在云端服务器注册所述图像采集设备与计算设备的关联关系，并添加对应的容器实例以用于所述停车位的管理方的数据运算。
  13. 一种车位范围的处理方法，其特征在于，应用于停车位附近位置部署的计算设备，所述方法包括：
    获取云端服务器下发的停车位的车位范围，所述车位范围基于至少一张停车位图像中识别的第一车位线和第二车位线确定，所述停车位图像由停车位附近的图像采集设备拍摄获得，所述第一车位线平行于道路并根据所述图像采集设备与所述停车位的相对位置确定，所述第二车位线为两个停车位之间间隔的线；
    基于所获取的车位范围，识别所述图像采集设备新采集的停车位图像中车辆与所述停车位的相对关系。
  14. 一种计算设备，包括存储器、处理器及存储在存储器上的计算机程序，所述处理器在执行所述计算机程序时实现权利要求1-13中任一项所述的方法。
PCT/CN2023/100034 2022-06-16 2023-06-13 车位范围的处理方法及计算设备 WO2023241595A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210686320.1 2022-06-16
CN202210686320.1A CN115116033A (zh) 2022-06-16 2022-06-16 车位范围的处理方法及计算设备

Publications (1)

Publication Number Publication Date
WO2023241595A1 true WO2023241595A1 (zh) 2023-12-21

Family

ID=83328775

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/100034 WO2023241595A1 (zh) 2022-06-16 2023-06-13 车位范围的处理方法及计算设备

Country Status (2)

Country Link
CN (1) CN115116033A (zh)
WO (1) WO2023241595A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115116033A (zh) * 2022-06-16 2022-09-27 阿里云计算有限公司 车位范围的处理方法及计算设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110414355A (zh) * 2019-06-27 2019-11-05 沈阳工业大学 基于视觉的右方位空停车位与泊车过程中车位线检测方法
US20190370572A1 (en) * 2018-05-31 2019-12-05 Kpit Technologies Limited System and method for detection of free parking space for a vehicle
CN113525337A (zh) * 2020-03-31 2021-10-22 本田技研工业株式会社 驻车位辨识系统及包括该驻车位辨识系统的驻车辅助系统
WO2022088900A1 (zh) * 2020-11-02 2022-05-05 亿咖通(湖北)技术有限公司 停车区域的车位线检测方法和计算机设备
CN115116033A (zh) * 2022-06-16 2022-09-27 阿里云计算有限公司 车位范围的处理方法及计算设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190370572A1 (en) * 2018-05-31 2019-12-05 Kpit Technologies Limited System and method for detection of free parking space for a vehicle
CN110414355A (zh) * 2019-06-27 2019-11-05 沈阳工业大学 基于视觉的右方位空停车位与泊车过程中车位线检测方法
CN113525337A (zh) * 2020-03-31 2021-10-22 本田技研工业株式会社 驻车位辨识系统及包括该驻车位辨识系统的驻车辅助系统
WO2022088900A1 (zh) * 2020-11-02 2022-05-05 亿咖通(湖北)技术有限公司 停车区域的车位线检测方法和计算机设备
CN115116033A (zh) * 2022-06-16 2022-09-27 阿里云计算有限公司 车位范围的处理方法及计算设备

Also Published As

Publication number Publication date
CN115116033A (zh) 2022-09-27

Similar Documents

Publication Publication Date Title
CN106373426B (zh) 基于计算机视觉的停车位及违规占道停车监控方法
US11455805B2 (en) Method and apparatus for detecting parking space usage condition, electronic device, and storage medium
CN110047319B (zh) 停车场车位导航方法、电子装置及存储介质
CN108765975B (zh) 路侧垂直停车场管理系统及方法
CN112820137B (zh) 一种停车场的管理方法及装置
WO2023241595A1 (zh) 车位范围的处理方法及计算设备
CN110853391A (zh) 智能共享停车系统
CN108399782A (zh) 室外反向导车的方法、装置、系统、设备及存储介质
CN112347814A (zh) 客流估计与展示方法、系统及计算机可读存储介质
CN112598925A (zh) 停车管理方法、装置、计算机设备及存储介质
CN117237854B (zh) 基于视频识别的停车位分配方法、系统、设备及存储介质
CN115909240A (zh) 一种基于车道线和车辆识别的道路拥堵检测方法
CN110880205A (zh) 一种停车收费方法及装置
WO2023246720A1 (zh) 路侧停车检测方法、系统及电子设备
CN111709286B (zh) 车辆排序及etc交易方法、存储介质、工控机设备及etc系统
KR101236266B1 (ko) 주차공간정보 관리시스템
CN102280028B (zh) 基于动态背景分析和监控带扫描的车辆监测方法
CN108847052B (zh) 停车位置确定方法、装置、系统及计算机可读介质
CN113421452B (zh) 一种基于视觉分析的露天停车场推荐系统
CN113158728B (zh) 一种基于灰度共生矩阵的车位状态检测方法
CN112115792B (zh) 一种出入口信息统计系统、方法及计算机设备
CN112633062A (zh) 一种基于嵌入式终端的深度学习占用公交车道检测方法
KR102556036B1 (ko) Ai 딥러닝 영상 분석 기술 및 라이다 센서를 활용한 야외 주차장 관리 시스템
CN114842650B (zh) 一种车辆超时违停判断方法及装置、图像采集设备
CN115691147A (zh) 数据处理方法、泊车管理系统及计算机存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23823163

Country of ref document: EP

Kind code of ref document: A1