WO2021051621A1 - Parking space determination method, terminal device and computer readable storage medium - Google Patents

Abstract

A parking space determination method, a terminal device and a medium, which are applicable to the technical field of artificial intelligence, wherein the method comprises: acquiring a monitoring video collected by each preset monitoring device, detecting whether a moving object is contained in the monitoring video according to a preset moving object detection strategy, determining the monitoring video containing the moving object as an initial monitoring video, and selecting a target area occupied by the moving object contained in the initial monitoring video in each frame of video image (S1); if the target area in at least a first preset number of consecutive frames of video images in the initial monitoring video completely overlaps, determining the initial monitoring video as a monitoring video to be screened, and performing target recognition on the target area in the first preset number of consecutive frames of video images contained in the monitoring video to be screened (S2); if the recognized moving object in the target area of the first preset number of consecutive frames of video images contained in the monitoring video to be screened is a vehicle, determining the monitoring video to be screened as a target monitoring video, determining the target area in the first preset number of consecutive frames of video images contained in the target monitoring video as a parking area, and determining coordinate information of the parking area in the first preset number of consecutive frames of video images (S3); acquiring information of a preset monitoring area of a target monitoring device corresponding to the target monitoring video, and determining information of an actual parking space corresponding to the parking area contained in the target monitoring video according to the information of the preset monitoring area and the coordinate information of the parking area contained in the target monitoring video in the first preset number of consecutive frames of video images (S4). By determining the information of the corresponding actual parking space according to the parking area, a parking management system is convenient to perform statistics and scheduling on the scattered parking spaces in an actual scene, which reduces the parking difficulty, and improves the parking efficiency.

Description

Method for determining parking space, terminal equipment and computer readable storage medium

This application affirms the priority of the Chinese patent application filed on September 16, 2019 with the application number 201910872304.X, titled "A method for determining parking spaces, terminal equipment and computer-readable storage media", the Chinese patent application The overall content of is incorporated in this application by reference.

Technical field

This application belongs to the field of artificial intelligence technology, and in particular relates to a method for determining a parking space, a terminal device, and a computer non-volatile readable storage medium.

Background technique

With the rapid development of the automobile industry and the continuous improvement of people's living standards, cars have become an essential means of transportation for most people. With the increase of car users, the demand for parking spaces in most cities has greatly increased. In order to relieve the parking pressure of parking lots, many cities will set up parking spaces on some outdoor streets. However, due to the dispersion and uncertainty of these outdoor parking spaces, it is difficult for the existing parking management system to know the scattered parking spaces. In addition, it is impossible to archive and record the information of these scattered parking spaces in a unified manner. As a result, when parking spaces in the parking lot are in short supply, these scattered outdoor parking spaces cannot be urgently dispatched, which increases the difficulty of parking and reduces the parking efficiency.

technical problem

The embodiments of the present application provide a method, terminal equipment, and computer non-volatile readable storage medium for determining parking spaces, so as to solve the problem that the existing parking management system cannot obtain information about scattered outdoor parking spaces, resulting in a shortage of indoor parking spaces. It is impossible to make emergency dispatch to the scattered outdoor parking spaces at times, the difficulty of parking is high, and the parking efficiency is low.

Technical solutions

In the first aspect, a method for determining parking spaces is provided, including:

Obtain the surveillance videos collected by each preset surveillance device, detect whether the surveillance video contains moving objects based on the preset moving object detection strategy, determine the surveillance video containing the moving objects as the initial surveillance video, and select the initial surveillance video. The target area occupied by the moving objects contained in the surveillance video in each frame of the video image;

If at least the target area in the video image of the first preset number of consecutive frames completely overlaps in the initial surveillance video, the initial surveillance video is determined to be the surveillance video to be screened, and the surveillance video to be screened includes Performing target recognition on the target area in the first preset number of consecutive frames of video images;

If it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames contained in the surveillance video to be screened is a vehicle, the surveillance video to be screened is determined as the target surveillance video, and the target surveillance video The target area included in the video images of the first preset number of consecutive frames is determined to be a parking area, and the coordinate information of the parking area in the video images of the first consecutive preset number of frames is determined;

Obtain the information of the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first preset number of frames of video images The coordinate information in, determines the actual parking space information corresponding to the parkingable area contained in the target surveillance video.

In a second aspect, a terminal device is provided, including:

The frame selection unit is used to obtain the surveillance video collected by each preset monitoring device, detect whether the surveillance video contains a moving object based on the preset moving object detection strategy, and determine the surveillance video containing the moving object as the initial surveillance video , Box select the target area occupied by the moving objects contained in the initial surveillance video in each frame of the video image;

The target recognition unit is configured to determine that the initial surveillance video is the surveillance video to be screened if at least the target area in the first preset number of consecutive frames of video images completely overlap Performing target recognition on the target area in the first preset number of consecutive frames of video images included in the surveillance video to be screened;

The first determining unit is configured to determine that the surveillance video to be screened is the target surveillance video if it is identified that the moving object in the target area of the video image of the first preset number of consecutive frames included in the surveillance video to be screened is a vehicle. , Determining the target area in the continuous first preset number of frames of video images included in the target surveillance video as a parkingable area, and determining that the parkingable area is in the first continuous preset number of frames of video images Coordinate information;

The second determining unit is configured to obtain information about the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first The coordinate information in the video image of a preset number of frames determines the information of the actual parking space corresponding to the parking area included in the target surveillance video.

In a third aspect, a terminal device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions The steps of the method for determining a parking space described above.

In a fourth aspect, a computer non-volatile readable storage medium is provided, and the computer non-volatile readable storage medium stores computer readable instructions, which when executed by a processor, realize the above Steps of the method of determining parking spaces.

Beneficial effect

An embodiment of the application provides a method for determining a parking space, which detects the moving objects in the surveillance video collected by the preset surveillance equipment, and selects the target area occupied by the moving object in each frame of the surveillance video. , When there are at least a first preset number of consecutive frames in a surveillance video where the target area in the video image completely overlaps, the surveillance video is determined to be the surveillance video to be screened, and the surveillance video to be screened contains the continuous first preset number of frames of video Target recognition is performed on the target area in the image. When it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames contained in a surveillance video to be screened is a vehicle, the surveillance video to be screened is determined as the target surveillance video , The target area in the video image of the first preset number of consecutive frames contained in the target surveillance video is determined as the parking area, based on the information of the preset surveillance area of the target surveillance equipment corresponding to the target surveillance video and the parking area in the first consecutively The coordinate information in the preset number of frames of video images determines the information of the actual parking space corresponding to the parking area. The embodiment of the application can automatically determine the parking space information in the actual scene corresponding to the monitoring screen of the target monitoring device based on the monitoring video collected by the target monitoring device, so that the parking management system can easily determine the actual scene corresponding to the monitoring screen of the target monitoring device. Statistics on the scattered parking spaces is beneficial to the parking management system to dispatch the scattered parking spaces when the indoor parking spaces are in short supply, which reduces the difficulty of parking and improves the parking efficiency.

Description of the drawings

Fig. 1 is an implementation flowchart of a method for determining a parking space provided by an embodiment of the present application;

FIG. 2 is a specific implementation flowchart of S3 in a method for determining a parking space provided by an embodiment of the present application;

FIG. 3 is a specific implementation flowchart of S32 in a method for determining a parking space provided by an embodiment of the present application;

FIG. 4 is a structural block diagram of a terminal device provided by an embodiment of the present application;

Fig. 5 is a structural block diagram of a terminal device provided by another embodiment of the present application.

Embodiments of the present invention

In order to make the purpose, technical solutions, and advantages of this application clearer, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

Please refer to FIG. 1. FIG. 1 is an implementation flowchart of a method for determining a parking space provided by an embodiment of the present application. In this embodiment, the execution subject of the method for determining a parking space is a terminal device. Terminal devices include but are not limited to smart phones, tablets or desktop computers. The method for determining a parking space as shown in Figure 1 includes the following steps:

S1: Obtain surveillance videos collected by each preset monitoring device, detect whether the surveillance video contains moving objects based on the preset moving object detection strategy, determine the surveillance video containing the moving objects as the initial surveillance video, and select all The target area occupied by the moving objects contained in the initial surveillance video in each frame of the video image.

In the embodiment of the present application, the preset monitoring device is a monitoring device used to monitor outdoor streets. Each preset monitoring device has a unique identity, and each preset monitoring device has its corresponding preset monitoring area. In practical applications, the unique identification of the preset monitoring device may be the number of the preset monitoring device, or the device identification code of the preset monitoring device, etc., and there is no restriction here. The number of the preset monitoring device can be composed of the identification of the street monitored by the preset monitoring device and the position number of the preset monitoring device on the street monitored by the preset monitoring device; the information of the preset monitoring area of the preset monitoring device can be preset The name of the street monitored by the monitoring device, the location information of the preset monitoring device on the street it monitors, and the description of the field of view of the preset monitoring device. The field of view of the preset monitoring device refers to the range of the area that the preset monitoring device can monitor in the actual scene, and the field of view of the preset monitoring device corresponds to the monitoring screen monitored by the preset monitoring device.

In order to count the parking areas (i.e., parking spaces) on outdoor streets, the embodiments of this application need to detect and analyze the surveillance videos collected by the preset monitoring equipment, by detecting whether there is a vehicle in a certain part of the monitoring screen of the preset monitoring equipment. The location stays for a long time to determine whether there is a parking area on the street monitored by the preset monitoring device and to determine the specific location of the parking area. Generally, when there is a vehicle entering/exiting the monitoring screen of the monitoring device and a vehicle can stay in a certain position on the monitoring screen for a period of time, it means that there is a parking area in the area monitored by the monitoring device; when a vehicle passes by the monitoring device When the monitoring screen but no vehicle stays in the monitoring screen of the monitoring device, it means that there is no parking area in the area monitored by the monitoring device.

Specifically, the terminal device may obtain the surveillance video collected by each preset surveillance device, and detect whether the surveillance video collected by the preset surveillance device contains a moving object based on the preset moving object detection strategy. If the terminal equipment detects that a surveillance video contains a moving object, the surveillance video containing the moving object is determined as the initial surveillance video, and the preset surveillance equipment corresponding to the surveillance video containing the moving object is determined as the initial surveillance equipment, and the terminal equipment frame Select the target area occupied by the moving objects in the initial surveillance video in each frame of the video image. The purpose of the terminal device to detect whether there are moving objects in the surveillance video is to prevent the subsequent target recognition from mistakenly judging the objects that occupy a certain space but cannot move in the area monitored by the preset surveillance equipment as vehicles, and the moving objects are monitored at the initial stage. The purpose of frame selection for the target area occupied in each frame of the video image of the video is to subsequently identify whether the framed moving object is a vehicle. It is understandable that if the terminal device does not detect a moving object in a surveillance video, it will not perform frame selection operations on the surveillance video.

It is understandable that since the surveillance video collected by the preset surveillance equipment is usually stored in the surveillance database of the relevant city department, in practical applications, after being authorized by the relevant city department, the terminal equipment can be monitored from the relevant city department. Obtain the surveillance video collected by the preset surveillance equipment from the database. It should be noted that the monitoring database usually uses the unique identification of the preset monitoring device as an index to store the monitoring video collected by the preset monitoring device.

As a preferred embodiment of the present application, the terminal device can obtain the surveillance video collected by each preset surveillance device within the preset time period from the surveillance database. Among them, the preset time period can be set according to actual needs. For example, the preset time period can be the peak time when the parking action occurs. For example, people usually need to park during the working hours in the morning and the off-duty hours in the evening. The preset monitoring equipment with a parking area in the monitoring area can capture the process of the vehicle entering the monitoring screen and staying in the monitoring screen with a greater probability. Therefore, only the monitoring video collected during the preset time period can be detected and analyzed. Efficiently and accurately detect whether there is a parking area in the area monitored by the preset monitoring equipment.

As an embodiment of the present application, the terminal device detects whether the surveillance video contains a moving object based on a preset moving object detection strategy, which may specifically include the following steps:

Reading each frame of video images included in the surveillance video;

Performing smoothing processing and gray-scale processing on each frame of the video image included in the surveillance video to obtain a gray-scale image of the video image of each frame;

Performing differential processing on the grayscale images of each two adjacent frames of the video image to obtain a grayscale difference image corresponding to each two adjacent frames of the video image;

Performing binarization processing on each of the gray-level difference images based on a preset gray-level value threshold to obtain a binarized image corresponding to each two adjacent frames of the video image;

Determine whether the surveillance video contains a moving object based on each of the binarized images.

In this embodiment, the terminal device performing differential processing on the grayscale images of every two adjacent frames of video images is specifically: calculating the difference in grayscale values between corresponding pixels in the grayscale images of every two adjacent frames of video images.

The terminal device performs binarization processing on each of the gray-scale difference images based on the preset gray value threshold to obtain the binarized image corresponding to each two adjacent frames of the video image, which may specifically include: The pixel value of the pixel whose gray value is greater than or equal to the preset gray value threshold is determined as the first preset value, and the pixel value of the pixel in the gray differential image whose gray value is less than the preset gray value threshold is determined as The second preset value further obtains the binarized image corresponding to each two adjacent frames of the video image.

In practical applications, the preset gray value threshold can be set according to actual needs, and there is no limitation here. The first preset value and the second preset value may also be set according to actual needs. For example, the first preset value may be 1, and the second preset value may be 0.

After obtaining the binarized image corresponding to every two adjacent frames of video images, the terminal device determines the area formed by the pixels with the pixel value of the first preset value in the binarized image as the area where the moving object is located. Based on the area where the moving object is located in the binarized image, the terminal device selects the target area corresponding to the area where the moving object is located from the next frame of the two video images corresponding to the binarized image.

S2: If at least the target area in the video image of the first preset number of consecutive frames in the initial surveillance video completely overlaps, the initial surveillance video is determined to be the surveillance video to be screened, and the surveillance video to be screened is monitored The target area in the video image of the first preset number of consecutive frames included in the video is subjected to target recognition.

In the embodiment of this application, after the terminal device selects the target area occupied by the moving object in the initial surveillance video in each frame of its video image, it overlaps and compares every two adjacent frames of video images in the initial surveillance video to detect Whether the target areas in every two adjacent frames of video images in the initial surveillance video completely overlap, and then detect whether the target areas in the initial surveillance video at least have a first predetermined number of consecutive frames of video images completely overlap. The terminal device detects whether there are at least a first preset number of consecutive frames in the initial surveillance video. The target area in the video image is completely overlapped. The purpose is to determine whether the moving object stays in the screen monitored by the initial surveillance device for a period of time and stays there. Whether the time is greater than the maximum temporary parking time.

In practical applications, when a vehicle stays in a certain area of an outdoor street longer than the maximum temporary parking time, it means that this area of the street allows long-term parking, which means that this area of the street can be used as a parking space. Therefore, this application In an embodiment, the first preset number is related to the frame rate of the initial monitoring device and the maximum temporary parking duration. Specifically, the first preset number is the product of the frame rate of the initial monitoring device and the maximum temporary parking duration.

The terminal device detects whether the target area in every two adjacent frames of the video image in the initial surveillance video completely overlaps means: detecting the target area in the i-th frame of the video image in the initial surveillance video and the target area in the i+1-th frame of the video image Whether it completely overlaps. Among them, 1≤i≤T-1, i is an integer, and T is the total number of frames of video images included in the initial surveillance video. Exemplarily, the terminal device detects whether the target area in the first frame of video image in the initial surveillance video completely overlaps with the target area in the second frame of video image, and detects the target area in the second frame of video image in the initial surveillance video Whether it completely overlaps with the target area in the third frame of video image, and so on.

As an embodiment of the present application, the terminal device detecting whether the target areas in every two adjacent frames of video images in the initial surveillance video completely overlap may specifically include the following steps:

Calculate the first degree of overlap of the target area in every two adjacent frames of video images in the initial surveillance video, and detect whether the first degree of overlap of the target area in every two adjacent frames of video images in the initial surveillance video is greater than the preset first overlap Degree threshold.

Among them, the first degree of overlap of the target area in every two adjacent frames of video images in the initial surveillance video is: the area of the overlapped part of the target area in every two adjacent frames of video images is equal to that of every two adjacent frames of video images. The ratio of the sum of the area of the target area. The preset first overlap threshold can be set according to actual conditions, and there is no limitation here.

If the terminal device detects that the first overlap degree of the target area in two adjacent frames of video images in the initial surveillance video is greater than the preset first overlap degree threshold, it determines that the target areas in the two adjacent frames of video images completely overlap. If the terminal device detects that there are a second preset number of consecutive target areas in two adjacent frames of video images completely overlapped in the initial surveillance video, it determines that there are at least a first preset number of consecutive target areas in the video image of the initial surveillance video. The areas completely overlap. Wherein, when the first preset number is an even number, the second preset number = the first preset number/2; when the first preset number is an odd number, the second preset number = (the first preset number + 1 ) /2.

If the terminal device detects that the target area in the video image of at least the first preset number of consecutive frames in an initial surveillance video completely overlaps, it means that a moving object has stayed in the screen monitored by the initial surveillance device for a period of time, and it has stayed The duration is greater than the maximum temporary parking duration. At this time, the terminal device determines the initial surveillance video as the surveillance video to be screened, and performs target recognition on the target area in the video image of the first preset number of consecutive frames contained in the surveillance video to be screened. The purpose of area target recognition is to identify whether the object in the target area is a vehicle.

In practical applications, the terminal device can use a deep learning-based target recognition algorithm to recognize whether the object in the target area is a vehicle. Among them, the target recognition algorithm based on deep learning may be a convolutional neural network algorithm. Since the target recognition algorithm based on deep learning is an existing technology, the specific recognition principle based on the deep learning target recognition algorithm will not be repeated here.

S3: If it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames included in the surveillance video to be screened is a vehicle, the surveillance video to be screened is determined as the target surveillance video, and the target The target area in the video image of the first continuous preset number of frames included in the surveillance video is determined to be a parking area, and the coordinate information of the parking area in the video image of the continuous first preset number of frames is determined.

In the embodiment of the present application, if the terminal device recognizes that the moving object in the target area of the video image of the first preset number of consecutive frames included in a surveillance video to be screened is a vehicle, it indicates that the surveillance video to be screened includes the continuous first preset number. Suppose the target area in the video image of the number of frames is the area where the vehicle can stay for a long time. At this time, the terminal device determines the surveillance video to be screened as the target surveillance video, and determines the surveillance equipment corresponding to the target surveillance video as the target surveillance equipment. The target area in the continuous first preset number of frames of video images included in the target surveillance video is determined to be a parkingable area, and the coordinate information of the parking area in the first continuous preset number of frames of video images included in the target surveillance video is determined.

Wherein, the coordinate information of the parking area in the video image of the first preset number of consecutive frames contained in the target surveillance video can be determined by the coordinates of the center point of the parking area in the video image of the first preset number of consecutive frames contained in the target surveillance video. Information description. Specifically, since the video image is usually rectangular, the terminal device can use one of the vertices of the video image of the first preset number of consecutive frames contained in the target surveillance video as the coordinate origin, and use the two sides constituting the vertex as the coordinate axis to establish Coordinate system, and then determine the coordinate information of the center point of the parking area in the first preset number of consecutive video images.

S4: Obtain the information of the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first preset number of frames The coordinate information in the video image determines the information of the actual parking space corresponding to the parkingable area contained in the target surveillance video.

Since the parking area determined by the terminal device is relative to the monitoring screen of the monitoring device, in order to map it to the actual scene, and then determine the parking space in the actual scene, the terminal device is determining the parking area After the coordinate information in the video image of the first preset number of consecutive frames included in the target surveillance video, the preset surveillance area information of the target surveillance device is acquired based on the unique identity of the target surveillance device corresponding to the target surveillance video.

It should be noted that the unique identification of the preset monitoring device and the information of the preset monitoring area of the preset monitoring device are correspondingly stored in the monitoring data of the relevant department of the city in advance. The terminal device can obtain the information of the preset monitoring area of the target monitoring device from the monitoring database of the relevant department based on the unique identity of the target monitoring device. Among them, the information of the preset monitoring area of the target monitoring device is described by the name of the street monitored by the target monitoring device, the location information of the target monitoring device on the street monitored by the target monitoring device, and the field of view of the target monitoring device.

After the terminal device obtains the information of the preset monitoring area of the target monitoring device, based on the coordinate information of the parking area in the first preset number of consecutive video images, determine the actual parking area corresponding to the target monitoring device's field of view. The area occupied by the parking space, and based on the name of the street monitored by the target monitoring device, the location information of the target monitoring device on the street monitored by the target monitoring device, and the actual parking space corresponding to the parking area, generate a parking area The corresponding actual parking space information. That is to say, the information of the actual parking space corresponding to the parking area is through the name of the street monitored by the target monitoring device, the location information of the target monitoring device on the street monitored by the target monitoring device, and the actual parking space corresponding to the parking area. Scope description.

It can be seen from the above that the method for determining parking spaces provided by the embodiments of the present application can automatically determine the parking space information in the actual scene corresponding to the monitoring screen of the target monitoring device based on the monitoring video collected by the target monitoring device, which is convenient for The parking management system counts the scattered parking spaces in the actual scene corresponding to the monitoring screen of the target monitoring device, which is conducive to the parking management system to dispatch the scattered parking spaces when the indoor parking spaces are scarce, reducing the difficulty of parking and improving the parking efficiency .

Please refer to FIG. 2, which is an implementation flowchart of a method for determining a parking space provided by another embodiment of the present application. This embodiment is based on the embodiment corresponding to FIG. 1, considering that there may be a marked parking space in the actual scene corresponding to the monitoring screen of the target monitoring device. Based on this, S3 in this embodiment specifically includes S31~S34 , Detailed as follows:

S31: Perform target detection on the continuous first preset number of frames of video images included in the target surveillance video, and detect whether the first continuous frame of video images included in the target surveillance video includes a frame with a preset shape.

In this embodiment, after the terminal device determines the target surveillance video, it performs target detection on the continuous first preset number of frames of video images contained in the target surveillance video to detect the first preset number of consecutive frames of video images contained in the target surveillance video. Whether to include a frame with a preset shape. The purpose of detecting whether the video image of the continuous first preset number of frames included in the target surveillance video contains a frame with a preset shape is to determine whether there is a lined parking space in the actual scene corresponding to the surveillance picture of the target surveillance device. Since the outline of the lined parking space is usually a parallelogram, in this embodiment, the preset shape can be set as a parallelogram.

As an embodiment of the present application, the terminal device may use an edge detection algorithm based on the OpenCV algorithm to detect and acquire a frame with a preset shape in the video image. Since the edge detection algorithm based on the OpenCV algorithm is an existing technology, its specific detection principle will not be described here.

S32: If the continuous first preset number of frames of video images included in the target surveillance video include a frame of a preset shape, calculate a second degree of overlap between the frame of the preset shape and the target area.

In this embodiment, if the terminal device detects that the video image of the first preset number of consecutive frames included in the target surveillance video contains a frame with a preset shape, it means that there may be a parking space in the actual scene corresponding to the surveillance screen of the target surveillance device. At this time, in order to further determine whether the detected frame of the preset shape actually corresponds to the parking space in the actual scene, the terminal device calculates the second degree of overlap between the frame of the preset shape and the target area.

As an embodiment of the present application, S32 can be specifically implemented through S321 to S322 as shown in FIG. 3, and the details are as follows:

S321: If the video image of the first preset number of consecutive frames included in the target surveillance video includes a frame of a preset shape, calculate the difference between the frame of the preset shape and the target area included in the video image. The area of the overlapping part, and calculating the sum of the area of the frame of the preset shape and the area of the target area;

S322: Determine the ratio of the area of the overlapping part to the sum of the areas as the second degree of overlap between the frame of the preset shape and the target area.

In this embodiment, after the terminal device calculates the second degree of overlap between the frame of the preset shape and the target area, it compares the second degree of overlap with the second preset degree of overlap threshold. Wherein, the second preset overlap degree threshold can be set according to actual needs, and there is no limitation here.

If the terminal device detects that the second overlap between the frame of the preset shape and the target area is less than the second preset overlap threshold, execute S33; if the terminal device detects the second overlap between the frame of the preset shape and the target area If the degree is greater than or equal to the second preset overlap degree threshold, S34 is executed.

S33: If the second degree of overlap is less than a second preset degree of overlap threshold, determine the target area in the first preset number of consecutive frames of video images included in the target surveillance video as a parking area.

In this embodiment, if the terminal device detects that the second overlap between the frame of the preset shape and the target area is less than the second preset overlap threshold, it means that the overlap area between the frame of the preset shape and the target area is relatively large. Small, which means that the frame of the preset shape corresponds to the parking space in the actual scene and is not a lined parking space. At this time, the terminal device determines the target area in the video image of the first preset number of consecutive frames contained in the target video as Parking area.

S34: If the second degree of overlap is greater than or equal to the second preset degree of overlap threshold, determine the frame of the preset shape in the first preset number of consecutive frames of video images included in the target surveillance video as Parking area.

In this embodiment, if the terminal device detects that the second overlap between the frame of the preset shape and the target area is greater than or equal to the second preset overlap threshold, it indicates the overlap between the frame of the preset shape and the target area. The area is larger, which means that the frame of the preset shape corresponds to the marked parking space in the actual scene. At this time, the terminal device converts the frame of the preset shape in the video image of the first preset number of consecutive frames contained in the target video. The body is determined as a parking area.

As can be seen from the above, in the method for determining parking spaces provided by this embodiment, when there are marked parking spaces in the actual scene corresponding to the monitoring screen of the target monitoring device, priority is given to the parking spaces corresponding to the marked parking spaces. The frame of the shape is determined as the parking area, so that the determined parking space is more accurate.

Please refer to FIG. 4, which is a structural block diagram of a terminal device according to an embodiment of the present application. The terminal device in this embodiment may be a terminal device such as a smart phone or a tablet computer. The units included in the terminal device are used to execute the steps in the embodiments corresponding to FIGS. 1 to 3. For details, please refer to related descriptions in the embodiments corresponding to FIGS. 1 to 3 and FIGS. 1 to 3. For ease of description, only the parts related to this embodiment are shown. 4, the terminal device 400 includes: a frame selection unit 41, a target recognition unit 42, a first determination unit 43, and a second determination unit 44. among them:

The frame selection unit 41 is used to obtain the surveillance video collected by each preset monitoring device, detect whether the surveillance video contains a moving object based on the preset moving object detection strategy, and determine the surveillance video containing the moving object as the initial surveillance video , Box select the target area occupied by the moving objects contained in the initial surveillance video in each frame of the video image.

The target recognition unit 42 is configured to determine that the initial surveillance video is the surveillance video to be screened if at least the target area in the first preset number of consecutive frames of video images completely overlap Target recognition is performed on the target area in the first predetermined number of consecutive frames of video images included in the surveillance video to be screened.

The first determining unit 43 is configured to determine that the surveillance video to be screened is the target surveillance video if it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames included in the surveillance video to be screened is a vehicle. , Determining the target area in the continuous first preset number of frames of video images included in the target surveillance video as a parkingable area, and determining that the parkingable area is in the first continuous preset number of frames of video images The coordinate information.

The second determining unit 44 is configured to obtain the information of the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first The coordinate information in the video image of a preset number of frames determines the information of the actual parking space corresponding to the parking area included in the target surveillance video.

As an embodiment of the present application, the first determination unit 43 specifically includes: a target detection unit, a first calculation unit, and a third determination unit. among them:

The target detection unit is configured to perform target detection on the continuous first preset number of frames of video images included in the target surveillance video, and detect whether the first continuous preset number of frames of video images included in the target surveillance video contains a preset shape framework.

The first calculation unit is configured to calculate the frame of the preset shape and the second of the target area if the frame of the preset shape is included in the continuous first preset number of frames of the video image contained in the target surveillance video. Degree of overlap.

The third determining unit is configured to, if the second overlap degree is less than a second preset overlap degree threshold, determine the target area in the first preset number of consecutive video images contained in the target surveillance video as parking area.

As an embodiment of the present application, the terminal device 400 further includes a fourth determining unit.

The fourth determining unit is configured to, if the second degree of overlap is greater than or equal to a second preset degree of overlap threshold, determine the shape of the preset shape in the continuous first preset number of frames of video images included in the target surveillance video The frame is determined as a parking area.

As an embodiment of the present application, the first calculation unit is specifically configured to:

If the video image of the first preset number of consecutive frames included in the target surveillance video includes a frame of a preset shape, calculate the overlap between the frame of the preset shape contained in the video image and the target area The area of, and calculating the sum of the area of the frame of the preset shape and the area of the target area;

The ratio of the area of the overlap portion to the sum of the area is determined as the second degree of overlap between the frame of the preset shape and the target area.

As an embodiment of the present application, the frame selection unit 41 specifically includes a reading unit, a first processing unit, a second processing unit, a third processing unit, and a fifth determining unit. among them:

The reading unit is used for reading each frame of video images contained in the surveillance video.

The first processing unit is configured to perform smoothing processing and gray-scale processing on each frame of the video image included in the surveillance video, to obtain a gray-scale image of each frame of the video image.

The second processing unit is configured to perform differential processing on the grayscale images of each two adjacent frames of the video image to obtain a grayscale difference image corresponding to each two adjacent frames of the video image.

The third processing unit is configured to perform binarization processing on each of the gray-scale difference images based on a preset gray-scale value threshold to obtain a binarized image corresponding to every two adjacent frames of the video image.

The fifth determining unit is configured to determine whether the surveillance video contains a moving object based on each of the binarized images.

It can be seen from the above that the terminal device provided in this embodiment can automatically determine the parking space information in the actual scene corresponding to the monitoring screen of the target monitoring device based on the monitoring video collected by the target monitoring device, which is convenient for the parking management system to check Statistics on the scattered parking spaces in the actual scene corresponding to the monitoring screen of the target monitoring device is helpful for the parking management system to dispatch the scattered parking spaces when the indoor parking spaces are in short supply, which reduces the difficulty of parking and improves the parking efficiency.

Fig. 5 is a structural block diagram of a terminal device provided by another embodiment of the present application. As shown in FIG. 5, the terminal device 5 of this embodiment includes: a processor 50, a memory 51, and computer-readable instructions 52 stored in the memory 51 and running on the processor 50, such as determining a parking space Method of the program. When the processor 50 executes the computer-readable instruction 52, the steps in the above embodiments of the method for determining a parking space are implemented, such as S1 to S4 shown in FIG. 1. Alternatively, when the processor 50 executes the computer-readable instructions 52, the functions of the units in the embodiment corresponding to FIG. 4 are implemented, for example, the functions of the units 41 to 44 shown in FIG. 4. For details, please refer to the corresponding FIG. 4 The relevant description in the embodiment of, will not be repeated here.

Exemplarily, the computer-readable instruction 52 may be divided into one or more units, and the one or more units are stored in the memory 51 and executed by the processor 50 to complete the present application . The one or more units may be a series of computer-readable instruction instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer-readable instruction 52 in the terminal device 5. For example, the computer-readable instruction 52 may be divided into a frame selection unit, a target recognition unit, a first determination unit, and a second determination unit, and the specific functions of each unit are as described above.

The terminal device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art can understand that FIG. 5 is only an example of the terminal device 5, and does not constitute a limitation on the terminal device 5. It may include more or less components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, and the like.

The so-called processor 50 may be a central processing unit (Central Processing Unit, CPU), it can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 51 may be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5. The memory 51 may also be an external storage device of the terminal device 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), and a secure digital (Secure Digital, SD) equipped on the terminal device 5. Card, Flash Card, etc. Further, the memory 51 may also include both an internal storage unit of the terminal device 5 and an external storage device. The memory 51 is used to store the computer-readable instructions and other programs and data required by the terminal device. The memory 51 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the division of the above functional units and modules is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as required. Module completion, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above-mentioned integrated units can be hardware-based Formal realization can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only used to facilitate distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, this application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. in.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be implemented by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile computer. In a readable storage medium, when the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, a person of ordinary skill in the art should understand that it can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of protection of this application.

Claims (20)

1. A method for determining a parking space is characterized in that it includes:

   Obtain the surveillance videos collected by each preset surveillance device, detect whether the surveillance video contains moving objects based on the preset moving object detection strategy, determine the surveillance video containing the moving objects as the initial surveillance video, and select the initial surveillance video. The target area occupied by the moving objects contained in the surveillance video in each frame of the video image;

   If at least the target area in the video image of the first preset number of consecutive frames completely overlaps in the initial surveillance video, the initial surveillance video is determined to be the surveillance video to be screened, and the surveillance video to be screened includes Performing target recognition on the target area in the first preset number of consecutive frames of video images;

   If it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames contained in the surveillance video to be screened is a vehicle, the surveillance video to be screened is determined as the target surveillance video, and the target surveillance video The target area included in the video images of the first preset number of consecutive frames is determined to be a parking area, and the coordinate information of the parking area in the video images of the first consecutive preset number of frames is determined;

   Obtain the information of the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first preset number of frames of video images The coordinate information in, determines the actual parking space information corresponding to the parkingable area contained in the target surveillance video.
2. The method for determining a parking space according to claim 1, wherein if it is recognized that the moving object in the target area of the first preset number of consecutive video images contained in the surveillance video to be screened is a vehicle, then The surveillance video to be screened is determined as the target surveillance video, the target area in the video image of the first preset number of consecutive frames included in the target surveillance video is determined as a parking area, and it is determined that the parking area is The coordinate information in the first preset number of consecutive frames of video images includes:

   Performing target detection on the continuous first preset number of frames of video images included in the target surveillance video, and detecting whether the target surveillance video includes a frame with a preset shape in the continuous first preset number of frames of video images;

   If the continuous first preset number of frames of video images included in the target surveillance video include a frame of a preset shape, calculating a second degree of overlap between the frame of the preset shape and the target area;

   If the second degree of overlap is less than a second preset degree of overlap threshold, the target area in the first preset number of consecutive frames of video images included in the target surveillance video is determined as a parking area.
3. The method for determining a parking space according to claim 2, wherein if the first predetermined number of consecutive frames of video images included in the target surveillance video include a frame with a predetermined shape, the predetermined shape is calculated. After setting the second degree of overlap between the shaped frame and the target area, the method further includes:

   If the second degree of overlap is greater than or equal to the second preset degree of overlap threshold, the frame of the preset shape in the first preset number of consecutive frames of video images included in the target surveillance video is determined to be parkingable area.
4. The method for determining a parking space according to claim 2, wherein if the first predetermined number of consecutive frames of video images included in the target surveillance video include a frame with a predetermined shape, the predetermined shape is calculated. The second degree of overlap between the frame of the shape and the target area includes:

   If the video image of the first preset number of consecutive frames included in the target surveillance video includes a frame of a preset shape, calculate the overlap between the frame of the preset shape contained in the video image and the target area The area of, and calculating the sum of the area of the frame of the preset shape and the area of the target area;

   The ratio of the area of the overlap portion to the sum of the area is determined as the second degree of overlap between the frame of the preset shape and the target area.
5. The method for determining a parking space according to any one of claims 1-4, wherein said acquiring surveillance video collected by each preset surveillance device, and detecting whether the surveillance video is included in the surveillance video based on a preset moving object detection strategy Contains moving objects, including:

   Reading each frame of video images included in the surveillance video;

   Performing smoothing processing and gray-scale processing on each frame of the video image included in the surveillance video to obtain a gray-scale image of the video image of each frame;

   Performing differential processing on the grayscale images of each two adjacent frames of the video image to obtain a grayscale difference image corresponding to each two adjacent frames of the video image;

   Performing binarization processing on each of the gray-level difference images based on a preset gray-level value threshold to obtain a binarized image corresponding to each two adjacent frames of the video image;

   Determine whether the surveillance video contains a moving object based on each of the binarized images.
6. A terminal device, characterized in that it comprises:

   The frame selection unit is used to obtain the surveillance video collected by each preset monitoring device, detect whether the surveillance video contains a moving object based on the preset moving object detection strategy, and determine the surveillance video containing the moving object as the initial surveillance video , Box select the target area occupied by the moving objects contained in the initial surveillance video in each frame of the video image;

   The target recognition unit is configured to determine that the initial surveillance video is the surveillance video to be screened if at least the target area in the first preset number of consecutive frames of video images completely overlap Performing target recognition on the target area in the first preset number of consecutive frames of video images included in the surveillance video to be screened;

   The first determining unit is configured to determine that the surveillance video to be screened is the target surveillance video if it is identified that the moving object in the target area of the video image of the first preset number of consecutive frames included in the surveillance video to be screened is a vehicle. , Determining the target area in the continuous first preset number of frames of video images included in the target surveillance video as a parkingable area, and determining that the parkingable area is in the first continuous preset number of frames of video images Coordinate information;

   The second determining unit is configured to obtain information about the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first The coordinate information in the video image of a preset number of frames determines the information of the actual parking space corresponding to the parking area included in the target surveillance video.
7. The terminal device according to claim 6, wherein the first determining unit comprises:

   The target detection unit is configured to perform target detection on the continuous first preset number of frames of video images included in the target surveillance video, and detect whether the first continuous preset number of frames of video images included in the target surveillance video contains a preset shape The frame;

   The first calculating unit is configured to calculate the frame of the preset shape and the first of the target area if the frame of the preset shape is included in the video image of the first preset number of consecutive frames included in the target surveillance video. Two degree of overlap

   The third determining unit is configured to determine, if the second overlap degree is less than a second preset overlap degree threshold, that the target area in the first preset number of consecutive video images included in the target surveillance video is available Parking area.
8. The terminal device according to claim 7, wherein the terminal device further comprises:

   The fourth determining unit is configured to, if the second overlap degree is greater than or equal to a second preset overlap degree threshold, combine the preset shape in the first preset number of consecutive video images contained in the target surveillance video The frame of is determined as a parking area.
9. The terminal device according to claim 7, wherein the first calculation unit is specifically configured to:

   If the video image of the first preset number of consecutive frames included in the target surveillance video includes a frame of a preset shape, calculate the overlap between the frame of the preset shape contained in the video image and the target area The area of, and calculating the sum of the area of the frame of the preset shape and the area of the target area;

   The ratio of the area of the overlap portion to the sum of the area is determined as the second degree of overlap between the frame of the preset shape and the target area.
10. The terminal device according to any one of claims 6-9, wherein the frame selection unit comprises:

    A reading unit for reading each frame of video images included in the surveillance video;

    The first processing unit is configured to perform smoothing processing and gray-scale processing on each frame of the video image included in the surveillance video to obtain a gray-scale image of each frame of the video image;

    The second processing unit is configured to perform differential processing on the grayscale image of each two adjacent frames of the video image to obtain a grayscale difference image corresponding to each two adjacent frames of the video image;

    The third processing unit is configured to perform binarization processing on each of the gray-scale difference images based on a preset gray-scale value threshold to obtain a binarized image corresponding to each two adjacent frames of the video image;

    The fifth determining unit is configured to determine whether the surveillance video contains a moving object based on each of the binarized images.
11. A terminal device, comprising a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, wherein the processor executes the computer-readable instructions as follows step:

    Obtain the surveillance videos collected by each preset surveillance device, detect whether the surveillance video contains moving objects based on the preset moving object detection strategy, determine the surveillance video containing the moving objects as the initial surveillance video, and select the initial surveillance video. The target area occupied by the moving objects contained in the surveillance video in each frame of the video image;

    If at least the target area in the video image of the first preset number of consecutive frames completely overlaps in the initial surveillance video, the initial surveillance video is determined to be the surveillance video to be screened, and the surveillance video to be screened includes Performing target recognition on the target area in the first preset number of consecutive frames of video images;

    If it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames contained in the surveillance video to be screened is a vehicle, the surveillance video to be screened is determined as the target surveillance video, and the target surveillance video The target area included in the video images of the first preset number of consecutive frames is determined to be a parking area, and the coordinate information of the parking area in the video images of the first consecutive preset number of frames is determined;

    Obtain the information of the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first preset number of frames of video images The coordinate information in, determines the actual parking space information corresponding to the parkingable area contained in the target surveillance video.
12. The terminal device according to claim 11, wherein if it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames contained in the surveillance video to be screened is a vehicle, then the The surveillance video to be screened is determined to be the target surveillance video, the target area in the continuous first preset number of frames of video images contained in the target surveillance video is determined to be a parking area, and it is determined that the parking area is in the continuous The coordinate information in the video image of the first preset number of frames includes:

    Performing target detection on the continuous first preset number of frames of video images included in the target surveillance video, and detecting whether the target surveillance video includes a frame with a preset shape in the continuous first preset number of frames of video images;

    If the continuous first preset number of frames of video images included in the target surveillance video include a frame of a preset shape, calculating a second degree of overlap between the frame of the preset shape and the target area;

    If the second degree of overlap is less than a second preset degree of overlap threshold, the target area in the first preset number of consecutive frames of video images included in the target surveillance video is determined as a parking area.
13. The terminal device according to claim 12, wherein if the video image of the first preset number of consecutive frames included in the target surveillance video contains a frame with a preset shape, then calculating the frame of the preset shape After the second degree of overlap between the frame and the target area, the method further includes:

    If the second degree of overlap is greater than or equal to the second preset degree of overlap threshold, the frame of the preset shape in the first preset number of consecutive frames of video images included in the target surveillance video is determined to be parkingable area.
14. The terminal device according to claim 12, wherein, if the video image of the first preset number of consecutive frames included in the target surveillance video contains a frame with a preset shape, then calculating the frame of the preset shape The second degree of overlap between the frame and the target area includes:

    If the video image of the first preset number of consecutive frames included in the target surveillance video includes a frame of a preset shape, calculate the overlap between the frame of the preset shape contained in the video image and the target area The area of, and calculating the sum of the area of the frame of the preset shape and the area of the target area;

    The ratio of the area of the overlap portion to the sum of the area is determined as the second degree of overlap between the frame of the preset shape and the target area.
15. The terminal device according to any one of claims 11-14, wherein the acquiring surveillance video collected by each preset surveillance device, and detecting whether the surveillance video contains a moving object based on a preset moving object detection strategy ,include:

    Reading each frame of video images included in the surveillance video;

    Performing smoothing processing and gray-scale processing on each frame of the video image included in the surveillance video to obtain a gray-scale image of the video image of each frame;

    Performing differential processing on the grayscale images of each two adjacent frames of the video image to obtain a grayscale difference image corresponding to each two adjacent frames of the video image;

    Performing binarization processing on each of the gray-level difference images based on a preset gray-level value threshold to obtain a binarized image corresponding to each two adjacent frames of the video image;

    Determine whether the surveillance video contains a moving object based on each of the binarized images.
16. A computer non-volatile readable storage medium, the computer non-volatile readable storage medium storing computer readable instructions, wherein the computer readable instructions are executed by a processor to implement the following steps:

    Obtain the surveillance videos collected by each preset surveillance device, detect whether the surveillance video contains moving objects based on the preset moving object detection strategy, determine the surveillance video containing the moving objects as the initial surveillance video, and select the initial surveillance video. The target area occupied by the moving objects contained in the surveillance video in each frame of the video image;

    If at least the target area in the video image of the first preset number of consecutive frames completely overlaps in the initial surveillance video, the initial surveillance video is determined to be the surveillance video to be screened, and the surveillance video to be screened includes Performing target recognition on the target area in the first preset number of consecutive frames of video images;

    If it is recognized that the moving object in the target area of the video image of the first preset number of consecutive frames contained in the surveillance video to be screened is a vehicle, the surveillance video to be screened is determined as the target surveillance video, and the target surveillance video The target area included in the video images of the first preset number of consecutive frames is determined to be a parking area, and the coordinate information of the parking area in the video images of the first consecutive preset number of frames is determined;

    Obtain the information of the preset monitoring area of the target monitoring device corresponding to the target monitoring video, based on the information of the preset monitoring area and the parking area included in the target monitoring video in its continuous first preset number of frames of video images The coordinate information in, determines the actual parking space information corresponding to the parkingable area contained in the target surveillance video.
17. The computer non-volatile readable storage medium according to claim 16, wherein if a moving object in the target area of the video image of the first preset number of consecutive frames contained in the surveillance video to be screened is identified Is a vehicle, the surveillance video to be screened is determined as the target surveillance video, the target area in the first preset number of consecutive video images contained in the target surveillance video is determined as a parkingable area, and the The coordinate information of the parking area in the video image of the first predetermined number of consecutive frames includes:

    Performing target detection on the continuous first preset number of frames of video images included in the target surveillance video, and detecting whether the target surveillance video includes a frame with a preset shape in the continuous first preset number of frames of video images;

    If the continuous first preset number of frames of video images included in the target surveillance video include a frame of a preset shape, calculating a second degree of overlap between the frame of the preset shape and the target area;

    If the second degree of overlap is less than a second preset degree of overlap threshold, the target area in the first preset number of consecutive frames of video images included in the target surveillance video is determined as a parking area.
18. The computer non-volatile readable storage medium according to claim 17, wherein if said target surveillance video contains a frame with a preset shape in a first predetermined number of consecutive frames of video images, After calculating the second degree of overlap between the frame of the preset shape and the target area, the method further includes:

    If the second degree of overlap is greater than or equal to the second preset degree of overlap threshold, the frame of the preset shape in the first preset number of consecutive frames of video images included in the target surveillance video is determined to be parkingable area.
19. The computer non-volatile readable storage medium according to claim 17, wherein if said target surveillance video contains a frame with a preset shape in a first predetermined number of consecutive frames of video images, Calculating the second degree of overlap between the frame of the preset shape and the target area includes:

    If the video image of the first preset number of consecutive frames included in the target surveillance video includes a frame of a preset shape, calculate the overlap between the frame of the preset shape contained in the video image and the target area The area of, and calculating the sum of the area of the frame of the preset shape and the area of the target area;

    The ratio of the area of the overlap portion to the sum of the area is determined as the second degree of overlap between the frame of the preset shape and the target area.
20. The computer non-volatile readable storage medium according to any one of claims 16-19, wherein said acquiring monitoring video collected by each preset monitoring device is detecting the monitoring video based on a preset moving object detection strategy. Whether the surveillance video contains moving objects, including:

    Reading each frame of video images included in the surveillance video;

    Performing smoothing processing and gray-scale processing on each frame of the video image included in the surveillance video to obtain a gray-scale image of the video image of each frame;

    Performing differential processing on the grayscale images of each two adjacent frames of the video image to obtain a grayscale difference image corresponding to each two adjacent frames of the video image;

    Performing binarization processing on each of the gray-level difference images based on a preset gray-level value threshold to obtain a binarized image corresponding to each two adjacent frames of the video image;

    Determine whether the surveillance video contains a moving object based on each of the binarized images.