Monitoring method, device, equipment, system and storage medium

Abstract

The invention provides a monitoring method, device, equipment and system and a storage medium, and relates to the technical field of image processing, in particular to the fields of artificial intelligence, intelligent transportation and the like. According to the specific implementation scheme, under the condition that it is determined that a target vehicle arriving at a target trigger line exists in first video data, attribute features of the target vehicle are recognized and obtained; the first video data is acquired by a first acquisition device in a first monitoring area; second video data corresponding to the attribute characteristics of the target vehicle are acquired, the second video data are acquired by a second acquisition device in a second monitoring area, and an overlapping area exists between the first monitoring area and the second monitoring area; and based on the second video data, identifying to obtain a vehicle identifier of the target vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to the technical fields of artificial intelligence, intelligent transportation, etc. Background Art

[0002] With the advancement of science and technology, urban construction is becoming more and more intelligent, and the monitoring and management of vehicles on the road are also moving towards intelligence. However, the existing way of monitoring vehicles on the road by manual inspection is inefficient and labor-intensive. Therefore, a more intelligent management method is needed to monitor and manage vehicles. Summary of the invention

[0003] The present disclosure provides a monitoring method, apparatus, device, system and storage medium.

[0004] According to one aspect of the present disclosure, there is provided a monitoring method, comprising:

[0005] When it is determined that there is a target vehicle that reaches the target trigger line in the first video data, the attribute characteristics of the target vehicle are identified; the first video data is obtained by the first acquisition device collecting data from the first monitoring area;

[0006] Acquire second video data corresponding to the attribute characteristics of the target vehicle, where the second video data is acquired by a second acquisition device from a second monitoring area, and there is an overlapping area between the first monitoring area and the second monitoring area;

[0007] Based on the second video data, a vehicle identification of the target vehicle is identified.

[0008] According to another aspect of the present disclosure, there is provided a monitoring device, comprising:

[0009] A first processing unit is used to identify and obtain the attribute characteristics of a target vehicle that has reached a target trigger line in the first video data; the first video data is obtained by a first acquisition device collecting data from a first monitoring area;

[0010] A data calling unit, used for acquiring second video data corresponding to the attribute characteristics of the target vehicle, wherein the second video data is acquired by a second acquisition device from a second monitoring area, and there is an overlapping area between the first monitoring area and the second monitoring area;

[0011] The second processing unit is used to identify the vehicle identification of the target vehicle based on the second video data.

[0012] According to another aspect of the present disclosure, a monitoring system is provided, wherein the monitoring system comprises:

[0013] a first collection device;

[0014] At least two second collection devices are arranged on both sides of the first collection device;

[0015] A monitoring device is used to execute any method in the embodiments of the present disclosure.

[0016] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any method in the embodiments of the present disclosure.

[0020] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any method according to the embodiments of the present disclosure.

[0021] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements any method according to the embodiments of the present disclosure when executed by a processor.

[0022] In this way, the disclosed solution can call the video data collected by the second acquisition device (that is, the second video data) when it is determined that there is a target vehicle that meets the conditions (for example, there is a target vehicle that reaches the target trigger line) in the video data collected by the first acquisition device (that is, the first video data), and use the second video data to identify the vehicle identification of the target vehicle. In this way, on the basis of effectively expanding the monitoring range of the first monitoring area, the effective identification of the vehicle identification can also be achieved.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0025] FIG. 1( a ) is a scene diagram of a monitoring system that can implement an embodiment of the present disclosure;

[0026] FIG1( b ) is a schematic diagram of an application scenario of a monitoring system in a parking lot according to an embodiment of the present application;

[0027] Figure 2 is a schematic flow chart 1 of a monitoring method according to an embodiment of the present application;

[0028] Figure 3 This is a schematic flow chart of a monitoring method according to an embodiment of the present application. Figure 2 ;

[0029] FIG. 4( a ) and FIG. 4( b ) are schematic diagrams of a scene in which a vehicle reaches a target trigger line according to an embodiment of the present application;

[0030] Figure 5 This is a schematic diagram of an application scenario of a monitoring system in a parking lot according to an embodiment of the present application. Figure 2 ;

[0031] Figure 6 is a schematic diagram of an orderly dot matrix in a monitoring screen according to an embodiment of the present application;

[0032] Figure 7 is a schematic diagram of video frames captured by a wide-angle camera and a common camera according to an embodiment of the present application;

[0033] Figure 8 It is a schematic diagram of the license plate information capture process of the monitoring method according to an embodiment of the present application;

[0034] Fig. 9 is a schematic diagram of a vehicle entry process according to a monitoring method according to an embodiment of the present application;

[0035] Fig.10 is a schematic diagram of a vehicle departure process according to a monitoring method according to an embodiment of the present application;

[0036] Fig.11 is a schematic diagram of the structure of a monitoring device according to an embodiment of the present application;

[0037] Fig.12 is a schematic diagram of the structure of a monitoring system according to an embodiment of the present application;

[0038] Fig.13 It is a block diagram of an electronic device used to implement the monitoring method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0040] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The term "at least one" in this article means any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C. The terms "first" and "second" in this article refer to multiple similar technical terms and distinguish them. They do not mean to limit the order or to limit them to only two. For example, the first feature and the second feature refer to two types / two features. The first feature can be one or more, and the second feature can also be one or more.

[0041] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the specific embodiments below. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0042] With the advancement of science and technology, urban construction is becoming more and more intelligent, and the management needs of road parking spaces are also moving towards intelligence. The use of manual patrols to monitor road parking spaces is inefficient and labor-intensive. Therefore, a more intelligent management method is needed to monitor and manage parking spaces; for example, management is carried out by installing high-position cameras. However, this method has some disadvantages, such as a limited number of managed parking spaces and a high requirement for the installation angle.

[0043] Based on this, the disclosed solution provides a monitoring method, so as to solve the problems that the existing high-position cameras have limited number of parking spaces to be managed, have high requirements on the installation angle, and have high requirements on the installation location.

[0044] Specifically, Figure 1(a) is a scene diagram of the monitoring system that can implement the embodiment of the present disclosure. In one example, as shown in Figure 1(a), the monitoring system may include: a monitoring device, a first acquisition device, and a second acquisition device arranged on both sides of the first acquisition device.

[0045] Furthermore, in one example, the acquisition angle of the first acquisition device is larger than that of the second acquisition device. Thus, when the monitoring area is monitored by the first acquisition device, the monitoring range can be effectively improved, thereby increasing the number of supervised parking spaces. Furthermore, since the second acquisition device is provided on both sides of the first acquisition device, the monitoring range of the second acquisition device can be effectively used to improve the overall monitoring range, thereby increasing the number of supervised parking spaces. Moreover, when the acquisition angle of the first acquisition device is too large, for example, when the first acquisition device is a fisheye camera, the video data collected by the fisheye camera cannot effectively identify the vehicle identification. In this case, the disclosed solution can effectively call the second acquisition device, such as the video data collected by an ordinary camera, to identify the vehicle identification. Thus, on the basis of further effectively expanding the monitoring range, effective monitoring of vehicles and parking spaces can also be achieved.

[0046] Furthermore, in one example, the first acquisition device may be a wide-angle camera with a wider viewing angle, which may have a 180-degree acquisition viewing angle in the horizontal direction; in another example, the second acquisition device may be a common camera. In this way, the vehicle monitoring is realized through the linkage of the wide-angle camera and the common camera. For example, through the linkage of the wide-angle camera and the common camera, the monitoring field of view of the wide-angle camera is maximized, thereby effectively increasing the number of parking spaces under supervision, and providing technical support for reducing supervision costs.

[0047] For example, the monitoring system of the present application is set up at the entrance and exit of the parking lot, or the first collection device and the second collection device in the monitoring system are set up to capture the vehicle's license plate information, entry time information, and departure time information, etc.; further, as shown in Figure 1(b), the first collection device and the second collection device in the monitoring system of the present application are also set up at a suitable location (such as the middle location) in the parking lot to manage the parking spaces.

[0048] The following is a further detailed description of the disclosed solution; Figure 2 1 is a schematic flow chart of a monitoring method according to an embodiment of the present application. The method can be optionally applied to electronic devices, such as personal computers, servers, server clusters and other electronic devices.

[0049] Further, the method includes at least part of the following contents. Figure 2 As shown, including:

[0050] Step S201: when it is determined that a target vehicle that has reached a target trigger line exists in the first video data, attribute features of the target vehicle are identified.

[0051] Here, the first video data is acquired by the first acquisition device from the first monitoring area. Further, in one example, the first monitoring area is a designated area, such as at least a portion of a designated road, so as to monitor vehicles or parking areas in the designated road.

[0052] Step S202: Acquire second video data corresponding to the attribute characteristics of the target vehicle.

[0053] Here, the second video data is obtained by the second acquisition device acquiring the second monitoring area, and there is an overlapping area between the first monitoring area and the second monitoring area. In other words, there is an overlapping part between the monitoring areas of the first acquisition device and the second acquisition device. Further, in one example, the second monitoring area is at least a part of the designated road. In this case, the monitoring range of the first monitoring area can be expanded through the second monitoring area.

[0054] Step S203: Based on the second video data, the vehicle identification of the target vehicle is identified.

[0055] Here, in one example, the vehicle identification of the target vehicle may specifically be license plate information, or may also be other identification information that can indicate the uniqueness of the vehicle, and the present disclosure does not impose any limitation on this.

[0056] In this way, the disclosed solution can call the video data collected by the second acquisition device (that is, the second video data) when it is determined that there is a target vehicle that meets the conditions (for example, there is a target vehicle that reaches the target trigger line) in the video data collected by the first acquisition device (that is, the first video data), and use the second video data to identify the vehicle identification of the target vehicle. In this way, on the basis of effectively expanding the monitoring range of the first monitoring area, the effective identification of the vehicle identification can also be achieved.

[0057] In addition, the disclosed solution can be used in parking space management scenarios. For example, the first monitoring area and the second monitoring area both include the area where the parking spaces are located. In this case, the use of the disclosed solution can effectively increase the number of supervised parking spaces, providing technical support for improving management efficiency and reducing supervision costs.

[0058] In a specific example, the attribute characteristics of the target vehicle may include but are not limited to one of the following: the direction of the vehicle, the type of the vehicle, the color of the vehicle, etc.

[0059] In a specific example, the target trigger line can be set in the first acquisition device, so that the target vehicle reaching the target trigger line can be locked in time during the monitoring of the first video data.

[0060] In a specific example, the acquisition angle of the first acquisition device is greater than the acquisition angle of the second acquisition device. In this way, when the first acquisition device is used to monitor the monitoring area, the second acquisition device can be effectively used to increase the monitoring range of the first acquisition device and expand the acquisition angle of the first acquisition device.

[0061] In a specific example of the disclosed solution, before step S201, the monitoring method further includes:

[0062] The vehicle appearing in the first video data collected by the first collection device is monitored, for example, the vehicle appearing in the first video data collected by the first collection device is monitored in real time.

[0063] It is determined whether there is a target vehicle reaching a target trigger line in the first video data.

[0064] In this way, the disclosed solution performs video stream analysis on the video data collected by the first acquisition device, for example, performs real-time analysis of the video stream, without performing video stream analysis on the video data collected by the second acquisition device, for example, does not perform real-time analysis of the video stream on the video data collected by the second acquisition device. In this way, computing power resources are effectively saved, making the monitoring process of the disclosed solution smoother and faster.

[0065] Furthermore, in a specific example, when it is determined that there is no target vehicle that reaches the target trigger line in the first video data, it is detected whether the vehicle identifications of other vehicles that appear in the overlapping area in the first video data are stored. Furthermore, when the vehicle identifications of other vehicles that appear in the overlapping area are stored, the video data collected by the first acquisition device can continue to be monitored; otherwise, when the vehicle identifications of other vehicles that appear in the overlapping area in the first video data are not stored, the attribute characteristics of other vehicles that do not have the vehicle identifications stored are identified; and the third video data corresponding to the attribute characteristics of other vehicles that do not have the vehicle identifications stored is obtained; the third video data is obtained by the second acquisition device collecting the second monitoring area;

[0066] Based on the third video data, the vehicle identifications of other vehicles whose vehicle identifications are not stored are identified. That is, in the case where the vehicle identifications of other vehicles appearing in the overlapping area in the first video data are not stored, the attribute characteristics of other vehicles whose vehicle identifications are not stored are identified, and based on the obtained attribute characteristics and the video data of the second acquisition device corresponding thereto, the vehicle identifications of the other vehicles are further identified. In this way, on the basis of effectively expanding the monitoring range of the first monitoring area, the effective recognition rate of vehicle identifications can be further improved, and when applied to the scenario of parking space management, it can lay the foundation for further improving management efficiency and reducing supervision costs.

[0067] In a specific example of the disclosed solution, at least two of the second acquisition devices may be provided on both sides of the first acquisition device, for example, one second acquisition device is provided on each side of the first acquisition device, so that the monitoring range of the first acquisition device is expanded by using the second acquisition devices provided on both sides. Based on this, after obtaining the attribute characteristics of the target vehicle, the second video data corresponding to the attribute characteristics of the target vehicle can also be determined, for example, the second acquisition device corresponding to the orientation of the target vehicle is determined, thereby ensuring that the acquired second video data contains the target vehicle, thereby providing support for effectively identifying the vehicle identification of the target vehicle.

[0068] Specifically, before obtaining the second video data corresponding to the attribute feature of the target vehicle, the monitoring method further includes:

[0069] Based on the attribute characteristics of the target vehicle, the second acquisition device to be called is determined from at least two of the second acquisition devices arranged on both sides of the first acquisition device; for example, the second acquisition device corresponding to the direction of the target vehicle is determined.

[0070] Furthermore, the above-mentioned step of obtaining the second video data corresponding to the attribute feature of the target vehicle (such as step S202 described above) may specifically include:

[0071] After determining the second acquisition device to be called, the second video data acquired by the second acquisition device to be called is acquired.

[0072] Furthermore, in one example, the acquisition start time of the second video data is related to the acquisition start time of the first video data when the target vehicle reaches the target trigger line, thereby providing support for effectively identifying the vehicle identification of the target vehicle.

[0073] Figure 3 This is a schematic flow chart of a monitoring method according to an embodiment of the present application. Figure 2 The method may be optionally applied to electronic devices, such as personal computers, servers, server clusters, and other electronic devices.

[0074] Further, the method includes at least part of the following contents. Figure 3 As shown, including:

[0075] Step S301: when it is determined that a target vehicle that has reached a target trigger line exists in the first video data, attribute features of the target vehicle are identified.

[0076] Here, the first video data is obtained by collecting the first monitoring area by the first collecting device;

[0077] Step S302: Acquire second video data corresponding to the attribute features of the target vehicle.

[0078] Here, the second video data is obtained by collecting data from the second monitoring area by the second collecting device, and there is an overlapping area between the first monitoring area and the second monitoring area;

[0079] Step S303: Filter out the target video frame where the target vehicle that has reached the target trigger line is located from the second video data.

[0080] For example, in a specific example, the first acquisition device and the second acquisition device both belong to the same monitoring system, so the clock and video frame rate of the first acquisition device and the second acquisition device are the same, or the clock differs by a first preset value, and the video frame rate differs by a second preset value. At this time, the following method can also be used to quickly filter out the target video frame where the target vehicle is located in the second video data. In this way, on the basis of effectively expanding the monitoring range of the first monitoring area, the recognition efficiency can also be effectively improved. Specifically, the above-mentioned filtering out the target video frame where the target vehicle is located from the second video data (such as step S303 described above) can specifically include:

[0081] Step S303 - 1 : Determine the frame information of the first video frame where the target vehicle that reaches the target trigger line is located in the first video data.

[0082] It should be noted here that "reaching the target trigger line" in this example can be understood as: as shown in Figure 4(a), the vehicle reaches the target trigger line in the direction of travel, or, as shown in Figure 4(b), the target vehicle reaches and crosses the target trigger line in the direction of travel.

[0083] Step S303-2: based at least on the frame information (such as the frame number) of the first video frame where the target vehicle reaches the target trigger line in the first video data, filter out the target video frame where the target vehicle reaches the target trigger line from the second video data.

[0084] For example, in one example, when the clock and video frame rate of the first acquisition device and the second acquisition device are the same, a video frame with the same frame number as the first video frame can be selected from the second video data as the target video frame.

[0085] Furthermore, in one example, the target video frame where the target vehicle is located in the second video data can be further screened out in the following manner, thereby improving the recognition accuracy, thereby laying a foundation for further improving the monitoring efficiency and improving the vehicle management efficiency. Specifically, the above-mentioned step S303-2 can also specifically include:

[0086] Step S303-2-1: Based on the frame information of the first video frame where the target vehicle reaching the target trigger line is located in the first video data, a second video frame corresponding to the frame information of the first video frame is screened out from the second video data.

[0087] Step S303-2-2: Based on a preset perspective transformation relationship, the target position of the target vehicle in the first video frame in the video frame captured by the second acquisition device is obtained.

[0088] In a specific example, before step S303-2-2, a preset perspective transformation relationship can also be constructed in the following manner, so that support is provided for quickly locking the target video frame, thereby laying a foundation for further improving the recognition efficiency. The specific steps include: based on the ordered dot matrix of the overlapping area of ​​the first monitoring area and the second monitoring area, a preset perspective transformation relationship between the video frame collected by the first acquisition device and the video frame collected by the second acquisition device is obtained.

[0089] Step S303-2-3: When it is determined that the similarity between the attribute characteristics of the target object at the target position in the second video frame and the attribute characteristics of the target vehicle meets the preset similarity requirements, the screened second video frame is used as the target video frame.

[0090] Step S304: Identify the target vehicle in the target video frame to obtain a vehicle identification of the target vehicle.

[0091] In this way, the disclosed solution provides a specific vehicle identification solution, which can realize effective identification of vehicle identification on the basis of effectively expanding the monitoring range of the monitoring area through the linkage of the first acquisition device and the second acquisition device.

[0092] In addition, the disclosed solution can be used in parking space management scenarios. For example, the first monitoring area and the second monitoring area both include the area where the parking spaces are located. In this case, the use of the disclosed solution can effectively increase the number of supervised parking spaces, providing technical support for improving management efficiency and reducing supervision costs.

[0093] In a specific example of the disclosed solution, after the vehicle identification of the target vehicle is identified, at least one of the following can also be performed: deleting the second video data; establishing an association relationship between the target video frame and the target vehicle, and storing the target video frame, thereby effectively saving storage resources and laying the foundation for effectively reducing the identification cost. In other words, in this example, there is no need to store the second video data collected by the second acquisition device for a long time, and there is no need to perform video stream analysis on the second video data collected by the second acquisition device. For example, there is no need to perform real-time video stream analysis on the video data collected by the second acquisition device, but the analysis will be performed after the second video data is called. In this way, computing resources are effectively saved, making the monitoring process of the disclosed solution smoother and faster.

[0094] In a specific example of the disclosed solution, the monitoring method further includes:

[0095] Monitoring the motion state of a first vehicle in the first video data; the first vehicle being the same as or different from the target vehicle;

[0096] When it is determined based on the motion state of the first vehicle that the first vehicle intersects with a parking space area in the first monitoring area, a vehicle entry event is generated for the first vehicle and the parking space where the first vehicle is located.

[0097] It can be understood that the step of monitoring the movement state of the vehicle can be executed after the vehicle identification of the first vehicle is identified, or it can be executed before that, or it can be executed in parallel, and the present disclosure does not limit this.

[0098] It should be noted that the specific process of vehicle parking can be found in the following description and will not be repeated here.

[0099] In this way, the disclosed solution provides a specific solution for parking space management. The disclosed solution can effectively increase the number of supervised parking spaces, providing technical support for improving management efficiency and reducing supervision costs.

[0100] In a specific example of the disclosed solution, the monitoring method further includes:

[0101] Monitoring vehicle characteristics of a first vehicle in a parking space corresponding to the vehicle entry event in the first video data;

[0102] Based on vehicle characteristics of a first vehicle in the parking space corresponding to the vehicle entry event, it is determined whether to generate a vehicle exit event for the first vehicle.

[0103] It should be noted that the specific process of vehicle departure can be found in the following description and will not be repeated here.

[0104] In this way, the disclosed solution provides a specific solution for parking space management. The disclosed solution can effectively increase the number of supervised parking spaces, providing technical support for improving management efficiency and reducing supervision costs.

[0105] The following is a further detailed description of the disclosed solution with reference to specific examples; the disclosed solution proposes a monitoring solution for camera linkage in a parking scene. Specifically, the following is a detailed description in two parts. The first part describes the scene preparation of the disclosed solution; the second part describes the specific core steps of the disclosed solution.

[0106] It should be pointed out that the monitoring system of this example includes a wide-angle camera and ordinary cameras arranged on both sides of the wide-angle camera. Moreover, the wide-angle camera in this example is integrated with a monitoring device capable of executing the monitoring method described above. In other words, the wide-angle camera in this example can not only collect video of the monitoring area, but also analyze the collected video data and call the video data collected by the ordinary camera when necessary, so as to realize the management of the parking space status by linkage with the ordinary camera.

[0107] Part 1: Scene Preparation

[0108] (1) Camera installation:

[0109] In this example, Figure 5 As shown, first, a wide-angle camera (such as a fisheye camera) is installed so that the viewing angle of the wide-angle camera can cover the entire scene that requires parking space management, such as monitoring the parking area and the driving area required to enter and exit the parking area; secondly, an ordinary camera is installed on both sides of the wide-angle camera to monitor the images on both sides of the wide-angle camera and to capture the license plate information.

[0110] It should be pointed out that the monitoring area of ​​the ordinary camera should overlap with the edge of the monitoring area of ​​the wide-angle camera to a large extent, so that when necessary, the video data collected by the ordinary camera can be called to capture the vehicle's license plate information.

[0111] Furthermore, a wide-angle camera (for example, a wide-angle camera equipped with a monitoring device that executes the above-mentioned monitoring method) can be used as a parking space status management device to manage the parking space status within the monitoring area and report vehicle entry events or vehicle departure events.

[0112] (2) Solution configuration:

[0113] A trigger line for calling a common camera (i.e., the target trigger line described above) is configured in the wide-angle camera, and the trigger line is used to trigger the wide-angle camera to call the video data collected by the common camera to capture the license plate information of the vehicle. For example, in one example, when a vehicle reaches or crosses the trigger line, the wide-angle camera calls the video data collected by the common camera, and based on the video data collected by the wide-angle camera and the video data collected by the common camera, the wide-angle camera collaboratively analyzes the vehicle that reaches or crosses the trigger line to identify the license plate information.

[0114] Furthermore, in order to facilitate collaborative analysis, the overlapping area between the wide-angle camera and the ordinary camera can be constructed by an ordered dot matrix (e.g., multiple ordered coordinate points). For example, both the monitoring screen of the wide-angle camera and the monitoring screen of the ordinary camera display an ordered dot matrix, which can indicate the overlapping area between the two.

[0115] It should be noted that the ordered dot matrix in the monitoring picture of the wide-angle camera is in the same order as the ordered dot matrix in the monitoring picture of the ordinary camera. In this way, the preset perspective transformation relationship between the wide-angle camera and the ordinary camera can be constructed using the ordered dot matrix, so as to provide support for target matching when the wide-angle camera calls the ordinary camera in the future. Figure 6 As shown, the overlapping area between the wide-angle camera and the ordinary camera set on the left (for example, recorded as overlapping area 1) can be represented by the ordered coordinate points 10-18; similarly, the overlapping area between the wide-angle camera and the ordinary camera set on the right (for example, recorded as overlapping area 2) can be represented by the ordered coordinate points 20-28.

[0116] For example, the position of the target vehicle to be analyzed in the wide-angle camera can be projected into the ordinary camera using a pre-built preset perspective transformation relationship to find out whether there is a target body that matches the position of the target vehicle in the ordinary camera. After a successful match, the license plate information of the successfully matched target body is detected and identified to obtain the license plate information of the target vehicle.

[0117] The second part is the specific core steps (1) the license plate information capture process, such as Figure 7 and Figure 8 As shown, the specific steps include:

[0118] Step S801: The wide-angle camera comprehensively monitors the collected video data (in order to distinguish it from the video data collected by the ordinary camera, the video data collected by the wide-angle camera can be referred to as the first video data), for example, detecting and tracking the vehicles in the monitoring area.

[0119] Step S802: Determine whether there is a target vehicle that reaches the trigger line in the first video data. If yes, execute step S803; otherwise, execute step S8011.

[0120] Step S803: When it is determined that there is a target vehicle that has reached the trigger line, attribute recognition is performed on the target vehicle based on the first video data to obtain attribute characteristics of the target vehicle, such as the direction, color and type of the target vehicle.

[0121] Step S804: the wide-angle camera actively calls the video data collected by the ordinary camera (in order to distinguish from the video data collected by the wide-angle camera, the video data collected by the ordinary camera can be called second video data).

[0122] Step S805: The wide-angle camera determines the frame information (such as the frame number) of the video frame (which may be referred to as the first video frame) where the target vehicle reaching the trigger line in the first video data is located. And, using the pre-built preset perspective transformation relationship, the position of the target vehicle reaching the trigger line in the wide-angle camera (such as the position of the target vehicle reaching the trigger line in the first video frame) is projected into the video frame of the called ordinary camera, and the target position of the target vehicle reaching the trigger line in the video frame of the ordinary camera is obtained.

[0123] Step S806: the wide-angle camera selects a second video frame corresponding to the frame information of the first video frame from the second video data based on the frame information of the first video frame.

[0124] Step S807: When the wide-angle camera determines that the attribute characteristics of the target object corresponding to the target position in the second video frame and the degree of similarity between the attribute characteristics of the target vehicle meet the preset similarity requirements, the second video frame is used as the target video frame, and the license plate information of the target object in the target video frame is recognized.

[0125] Step S808: The wide-angle camera determines whether the license plate information is recognized; if it is recognized, step S809 is executed. Otherwise, step S8010 is executed.

[0126] Step S809: Using the recognized license plate information as the license plate information of the target license plate.

[0127] Furthermore, the wide-angle camera may also save the target video frame as data in the evidence chain.

[0128] Step S8010: Mark the target vehicle, for example, mark it as blocked, so as to facilitate the subsequent recognition of the license plate information of the vehicle marked as blocked, and return to step S801.

[0129] Step S8011: When it is determined that there is no target vehicle that has reached the trigger line, determine whether the license plate information of the vehicle that appears in the overlapping area of ​​the first video data has been captured. If there are other vehicles whose license plate information has not been captured (for example, when the other vehicles cross the trigger line, there is an occlusion phenomenon, resulting in unsuccessful recognition of the license plate information), then execute step S8012. Otherwise, return to step S801.

[0130] Step S8012: the wide-angle camera actively calls the required ordinary camera, and the required ordinary camera collects video data of other vehicles whose license plate information is not captured; the wide-angle camera also uses the video data collected by the ordinary camera based on the above-mentioned method to identify the license plate information of the other vehicles.

[0131] In one example, when it is determined that there are other vehicles whose license plate information has not been captured, it can be further determined whether the license plate information of the other vehicles whose license plate information has not been captured is blocked. If it is not blocked, the required ordinary camera is called to identify the license plate information of the other vehicles whose license plate information has not been captured.

[0132] It should be noted that in this example, there is no need to perform real-time analysis of the video stream of the ordinary camera. The corresponding video frame needs to be analyzed only when a call from the wide-angle camera is received. Therefore, it is only necessary to cache the video stream in the memory for a period of time, which saves computing power resources and allows the device to run more smoothly and quickly.

[0133] (2) The process of vehicle entry, such as Fig. 9 As shown, the specific steps include:

[0134] Step S901: The wide-angle camera comprehensively monitors the collected video data to monitor the motion state of the vehicles appearing in the monitoring area, for example, performing vehicle recognition on each video frame. Here, after the vehicle is recognized, the recognized vehicle can also be tracked.

[0135] In this example, the monitoring area of ​​the wide-angle camera may specifically be a parking area in a designated road, and roads for entering and exiting the parking area, and the like.

[0136] Step S902: Match the vehicle recognition result with the existing tracking target, and update the existing tracking target based on the matching result, so as to achieve real-time update of the tracking target.

[0137] Step S903: Determine whether there is an intersection between the tracking target and the parking space area in the monitoring area. If yes, execute step S904. Otherwise, execute step S906.

[0138] Step S904: Mark the state of the tracking target that intersects with the parking space area in the monitoring area as being in the parking state, and mark the state of the parking space where the tracking target is being parked as being occupied. Execute step S905.

[0139] Step S905: Analyze the movement trajectory of each tracking target that has not completed the positioning operation. Execute step S906.

[0140] Step S906: Determine whether the target is in a stable state (for example, if the moving trajectory of the target does not move significantly for multiple frames, it can be considered stable). If it is in a stable state, execute step S907. Otherwise, execute step S905.

[0141] Step S907: Determine whether the tracking target is parked in the parking area, if so, execute step S908. Otherwise, execute step S909.

[0142] Step S908: Generate a vehicle entry event for the tracked vehicle and the parking space where the tracked vehicle is located.

[0143] Step S909: If the vehicle is parked in a non-parking area, an illegal parking alarm is reported.

[0144] Here, in actual applications, each parking space that is in an occupied state but has not generated a vehicle entry event can also be analyzed. If the parking space is in an occupied state but there is no vehicle in the parking space, it is considered that the previous tracking target is a passing vehicle and the parking space state is cleared; if the parking space is in an occupied state and the previous tracking target still exists, but the movement trajectory of the tracking target is still changing, it is considered that the tracking target is in the process of entering the parking space, and the duration of the parking space occupation state is analyzed. If the set threshold is reached, a vehicle entry event is sent for the tracking target and the parking space where the tracking target is located. If the set threshold has not been reached, wait for subsequent analysis.

[0145] (3) The process of vehicle leaving the location, such as Fig.10 As shown, the specific steps include:

[0146] Step S1001: The wide-angle camera monitors the collected video data in real time to analyze the parking spaces for which vehicle entry events have been generated in the monitoring area.

[0147] Step S1002: If a parking space has generated a vehicle entry event, and the tracking number (or license plate information) of the tracking target in the parking space has not changed (in this case, it can be considered that the vehicle in the parking space has not changed), and the moving trajectory of the tracking target has not moved significantly, then it is considered that the tracking target has not changed. Execute step S1003.

[0148] Step S1003: Determine whether the update cycle of the relevant information of the parking space has been reached. If so, execute step S1004; otherwise, continue analyzing, for example, continue executing step S1003.

[0149] Step S1004: updating the relevant information of the parking space, for example, updating the image of the tracking target occupying the parking space.

[0150] Step S1005: If a parking space has generated a vehicle entry event, and the tracking number (or license plate information) of the tracking target in the parking space has not changed (in this case, it can be considered that the vehicle in the parking space has not changed), but the moving trajectory of the tracking target has changed and intersects with the parking space, it is considered that the tracking target is in the leaving state. Execute step S1006.

[0151] Step S1006: Mark the state of the tracking target as being out of position, and save the video frame of being out of position as an evidence picture, while continuing the tracking analysis.

[0152] Step S1007: If a vehicle entry event has been generated in the parking space, but the tracking number (or license plate information) of the tracking target in the parking space has changed (in this case, it can be considered that the vehicle in the parking space has changed), then execute step S1008.

[0153] Step S1008: Determine whether there is a picture of evidence of the vehicle leaving the parking space saved. If so, it is considered that the original tracking target in the parking space has left the parking space, and then execute step S1009. Otherwise, that is, no picture of evidence of the vehicle leaving the parking space is saved, and then execute step S1010.

[0154] Step S1009: Generate a vehicle departure event for the original tracking target and parking space based on the saving time of the saved evidence image.

[0155] Step S1010: Generate a vehicle departure event for the original tracking target and the parking space according to the time of the last periodic update of the parking space.

[0156] It should be noted that if a parking space has generated a vehicle entry event, but the tracking number of the tracking target in the parking space has changed, it may also be caused by a power outage or other reasons. At this time, the new tracking number can be matched with the updated number before the power outage to determine whether the vehicle in the parking space has changed. For example, if the matching is consistent, the tracking number of the tracking target in the parking space can be updated and re-analyzed. Otherwise, if the matching is inconsistent, it is considered that the tracking target in the parking space has changed, and step S1008 is executed.

[0157] Step S1011: If a vehicle entry event has been generated for the parking space and there is no vehicle in the parking space, it is considered that the vehicle in the parking space has left the parking space, and step S1008 is executed.

[0158] Here, in actual applications, when a vehicle departure event is generated, it is possible to further determine whether the license plate information of the tracking target corresponding to the vehicle departure event has been captured. If the license plate information has not been captured, the tracking target of the vehicle departure event continues to be tracked, and when the tracking target enters the overlapping area, the video data of the ordinary camera is called to capture the license plate information. If the capture is successful, a license plate supplement event can also be generated.

[0159] In this way, the disclosed solution provides a solution for achieving 180-degree horizontal monitoring based on the linkage of a wide-angle camera and a regular camera. For example, the monitoring angle of the regular camera is utilized to maximize the monitoring angle of the wide-angle camera to achieve 180-degree horizontal monitoring. In this way, the number of supervised parking spaces is effectively increased and the supervision cost is reduced.

[0160] Moreover, in the disclosed solution, since the wide-angle camera is not easily blocked, the setting of the wide-angle camera, for example, the position of the pole has low requirements, which is convenient for construction and can achieve a simpler and faster supervision process; in addition, the disclosed solution uses a wide-angle camera to monitor the global scene, and only calls the ordinary camera for analysis when needed, and there is no need to call the ordinary camera when not needed, so a large amount of computing resources is saved, which is conducive to the continuous analysis of the wide-angle camera.

[0161] The disclosed solution also provides a monitoring device, such as Fig.11 As shown, the monitoring device comprises:

[0162] The first processing unit 1101 is used to identify the attribute characteristics of the target vehicle when determining that there is a target vehicle that reaches the target trigger line in the first video data; the first video data is obtained by the first acquisition device collecting data from the first monitoring area;

[0163] The data calling unit 1102 is used to obtain second video data corresponding to the attribute characteristics of the target vehicle, where the second video data is obtained by collecting data from a second monitoring area by a second collecting device, and there is an overlapping area between the first monitoring area and the second monitoring area;

[0164] The second processing unit 1103 is used to identify the vehicle identification of the target vehicle based on the second video data.

[0165] In a specific example of the disclosed solution, the data calling unit is further used to:

[0166] Based on the attribute characteristics of the target vehicle, determining the second acquisition device to be called from at least two of the second acquisition devices disposed on both sides of the first acquisition device;

[0167] After determining the second acquisition device to be called, the second video data acquired by the second acquisition device to be called is acquired.

[0168] In a specific example of the disclosed solution, the second processing unit is specifically used to:

[0169] Filtering out a target video frame where a target vehicle reaching a target trigger line is located from the second video data;

[0170] The target vehicle in the target video frame is identified to obtain a vehicle identification of the target vehicle.

[0171] In a specific example of the disclosed solution, the second processing unit is specifically used to:

[0172] Determine frame information of a first video frame in which a target vehicle reaching a target trigger line is located in the first video data;

[0173] Based at least on the frame information of the first video frame where the target vehicle that has reached the target trigger line is located in the first video data, a target video frame where the target vehicle that has reached the target trigger line is located is screened out from the second video data.

[0174] In a specific example of the disclosed solution, the second processing unit is specifically used to:

[0175] Based on the frame information of the first video frame where the target vehicle reaching the target trigger line is located in the first video data, filtering out the second video frame corresponding to the frame information of the first video frame from the second video data;

[0176] Based on a preset perspective transformation relationship, obtaining a target position of the target vehicle in the first video frame in the video frame captured by the second acquisition device;

[0177] When it is determined that the similarity between the attribute characteristics of the target object at the target position in the second video frame and the attribute characteristics of the target vehicle meets the preset similarity requirement, the screened second video frame is used as the target video frame.

[0178] In a specific example of the disclosed solution, the second processing unit is further used to:

[0179] Based on the ordered dot matrix of the overlapping area of ​​the first monitoring area and the second monitoring area, a preset perspective transformation relationship between the video frame collected by the first acquisition device and the video frame collected by the second acquisition device is obtained.

[0180] In a specific example of the disclosed solution, the second processing unit is further configured to perform at least one of the following:

[0181] After identifying the vehicle identification of the target vehicle, deleting the second video data;

[0182] After the vehicle identification of the target vehicle is identified, an association relationship is established between the target video frame and the target vehicle, and the target video frame is stored.

[0183] In a specific example of the disclosed solution, the first processing unit is further used to:

[0184] Monitoring vehicles appearing in the first video data collected by the first collecting device;

[0185] It is determined whether there is a target vehicle reaching a target trigger line in the first video data.

[0186] In a specific example of the disclosed solution, the first processing unit is further used for:

[0187] When it is determined that there is no target vehicle reaching the target trigger line in the first video data, it is detected whether vehicle identifications of other vehicles appearing in the overlapping area in the first video data are stored.

[0188] In a specific example of the disclosed solution, the first processing unit is further used to identify attribute features of other vehicles for which vehicle identifications are not stored, if it is determined that vehicle identifications of other vehicles appearing in the overlapping area in the first video data are not stored;

[0189] The data calling unit is further used to obtain third video data corresponding to attribute characteristics of other vehicles for which no vehicle identification is stored; the third video data is obtained by the second acquisition device collecting data from the second monitoring area;

[0190] The second processing unit is further configured to identify, based on the third video data, vehicle identifications of other vehicles for which no vehicle identifications are stored.

[0191] In a specific example of the disclosed solution, the monitoring device further includes: a monitoring unit; wherein the monitoring unit is used to:

[0192] Monitoring the motion state of a first vehicle in the first video data; the first vehicle being the same as or different from the target vehicle;

[0193] When it is determined based on the motion state of the first vehicle that the first vehicle intersects with a parking space area in the first monitoring area, a vehicle entry event is generated for the first vehicle and the parking space where the first vehicle is located.

[0194] In a specific example of the disclosed solution, the monitoring unit is further used to:

[0195] Monitoring vehicle characteristics of a first vehicle in a parking space corresponding to the vehicle entry event in the first video data;

[0196] Based on vehicle characteristics of a first vehicle in the parking space corresponding to the vehicle entry event, it is determined whether to generate a vehicle exit event for the first vehicle.

[0197] In a specific example of the disclosed solution, the acquisition viewing angle of the first acquisition device is greater than the acquisition viewing angle of the second acquisition device.

[0198] For the description of the specific functions and examples of each unit of the device in the embodiment of the present disclosure, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0199] The disclosed solution also provides a monitoring system, such as Fig.12 As shown, the monitoring system comprises:

[0200] First collection device 1201;

[0201] At least two second collection devices 1202 disposed on both sides of the first collection device;

[0202] The monitoring device 1203 is used to execute any method of the above embodiments of the present disclosure.

[0203] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0204] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0205] Fig.13 A schematic block diagram of an example electronic device 1300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0206] like Fig.13As shown, the device 1300 includes a computing unit 1301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from a storage unit 1308 into a random access memory (RAM) 1303. In the RAM 1303, various programs and data required for the operation of the device 1300 can also be stored. The computing unit 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0207] A number of components in the device 1300 are connected to the I / O interface 1305, including: an input unit 1306, such as a keyboard, a mouse, etc.; an output unit 1307, such as various types of displays, speakers, etc.; a storage unit 1308, such as a disk, an optical disk, etc.; and a communication unit 1309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1309 allows the device 1300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0208] The computing unit 1301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1301 performs the various methods and processes described above, such as monitoring methods. For example, in some embodiments, the monitoring method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1300 via the ROM 1302 and / or the communication unit 1309. When the computer program is loaded into the RAM 1303 and executed by the computing unit 1301, one or more steps of the monitoring method described above may be performed. Alternatively, in other embodiments, the computing unit 1301 may be configured to perform the monitoring method in any other appropriate manner (e.g., by means of firmware).

[0209] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0210] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0211] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0212] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0213] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0214] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0215] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0216] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A monitoring method, comprising: In the case of determining that a target vehicle that has reached the target trigger line exists in the first video data, identifying and obtaining attribute features of the target vehicle; The first video data is obtained by collecting the first monitoring area through the first collecting device; Acquire second video data corresponding to the attribute characteristics of the target vehicle, where the second video data is acquired by a second acquisition device from a second monitoring area, and there is an overlapping area between the first monitoring area and the second monitoring area; Based on the second video data, a vehicle identification of the target vehicle is identified.

2. The method according to claim 1, further comprising: Based on the attribute characteristics of the target vehicle, determining the second acquisition device to be called from at least two of the second acquisition devices disposed on both sides of the first acquisition device; Wherein, the obtaining of the second video data corresponding to the attribute feature of the target vehicle includes: After determining the second acquisition device to be called, the second video data acquired by the second acquisition device to be called is acquired.

3. The method according to claim 1 or 2, wherein: The identifying the vehicle identification of the target vehicle based on the second video data includes: Filtering out a target video frame where a target vehicle reaching a target trigger line is located from the second video data; The target vehicle in the target video frame is identified to obtain a vehicle identification of the target vehicle.

4. The method according to claim 3, wherein: The step of selecting a target video frame where a target vehicle reaching a target trigger line is located from the second video data includes: Determine frame information of a first video frame in which a target vehicle reaching a target trigger line is located in the first video data; Based at least on the frame information of the first video frame where the target vehicle that has reached the target trigger line is located in the first video data, a target video frame where the target vehicle that has reached the target trigger line is located is screened out from the second video data.

5. The method according to claim 4, wherein: The step of filtering out a target video frame where the target vehicle that has reached the target trigger line is located from the second video data based at least on the frame information of the first video frame where the target vehicle that has reached the target trigger line is located in the first video data comprises: Based on the frame information of the first video frame where the target vehicle reaching the target trigger line is located in the first video data, filtering out the second video frame corresponding to the frame information of the first video frame from the second video data; Based on a preset perspective transformation relationship, obtaining a target position of the target vehicle in the first video frame in the video frame captured by the second acquisition device; When it is determined that the similarity between the attribute characteristics of the target object at the target position in the second video frame and the attribute characteristics of the target vehicle meets the preset similarity requirement, the screened second video frame is used as the target video frame.

6. The method according to claim 5, further comprising: Based on the ordered dot matrix of the overlapping area of ​​the first monitoring area and the second monitoring area, a preset perspective transformation relationship between the video frame collected by the first acquisition device and the video frame collected by the second acquisition device is obtained.

7. The method according to any one of claims 3 to 6, after identifying the vehicle identification of the target vehicle, the method further comprises at least one of the following: deleting the second video data; An association relationship is established between the target video frame and the target vehicle, and the target video frame is stored.

8. The method according to any one of claims 1 to 7, further comprising: Monitoring vehicles appearing in the first video data collected by the first collecting device; It is determined whether there is a target vehicle reaching a target trigger line in the first video data.

9. The method according to claim 8, further comprising: When it is determined that there is no target vehicle reaching the target trigger line in the first video data, it is detected whether vehicle identifications of other vehicles appearing in the overlapping area in the first video data are stored.

10. The method according to claim 9, further comprising: In the case where it is determined that the vehicle identifications of other vehicles appearing in the overlapping area in the first video data are not stored, identifying attribute features of other vehicles for which the vehicle identifications are not stored; Acquire third video data corresponding to attribute features of other vehicles for which no vehicle identification is stored; the third video data is acquired by the second acquisition device from the second monitoring area; Based on the third video data, vehicle identifications of other vehicles for which no vehicle identifications are stored are identified.

11. The method according to any one of claims 1 to 10, further comprising: monitoring a motion state of a first vehicle in the first video data; The first vehicle is the same as or different from the target vehicle; When it is determined based on the motion state of the first vehicle that the first vehicle intersects with a parking space area in the first monitoring area, a vehicle entry event is generated for the first vehicle and the parking space where the first vehicle is located.

12. The method according to claim 11, further comprising: Monitoring vehicle characteristics of a first vehicle in a parking space corresponding to the vehicle entry event in the first video data; Based on vehicle characteristics of a first vehicle in the parking space corresponding to the vehicle entry event, it is determined whether to generate a vehicle exit event for the first vehicle.

13. The method according to any one of claims 1 to 12, wherein: The collection angle of view of the first collection device is greater than the collection angle of view of the second collection device.

14. A monitoring device, comprising: A first processing unit is used to identify and obtain attribute characteristics of a target vehicle when determining that there is a target vehicle that reaches a target trigger line in the first video data; The first video data is obtained by collecting the first monitoring area through the first collecting device; A data calling unit, used for acquiring second video data corresponding to the attribute characteristics of the target vehicle, wherein the second video data is acquired by a second acquisition device from a second monitoring area, and there is an overlapping area between the first monitoring area and the second monitoring area; The second processing unit is used to identify the vehicle identification of the target vehicle based on the second video data.

15. The device according to claim 14, wherein: The data calling unit is further used for: Based on the attribute characteristics of the target vehicle, determining the second acquisition device to be called from at least two of the second acquisition devices disposed on both sides of the first acquisition device; After determining the second acquisition device to be called, the second video data acquired by the second acquisition device to be called is acquired.

16. The device according to claim 14 or 15, wherein: The second processing unit is specifically configured to: Filtering out a target video frame where a target vehicle reaching a target trigger line is located from the second video data; The target vehicle in the target video frame is identified to obtain a vehicle identification of the target vehicle.

17. The device according to claim 16, wherein: The second processing unit is specifically configured to: Determine frame information of a first video frame in which a target vehicle reaching a target trigger line is located in the first video data; Based at least on the frame information of the first video frame where the target vehicle that has reached the target trigger line is located in the first video data, a target video frame where the target vehicle that has reached the target trigger line is located is screened out from the second video data.

18. The device according to claim 17, wherein: The second processing unit is specifically configured to: Based on the frame information of the first video frame where the target vehicle reaching the target trigger line is located in the first video data, filtering out the second video frame corresponding to the frame information of the first video frame from the second video data; Based on a preset perspective transformation relationship, obtaining a target position of the target vehicle in the first video frame in the video frame captured by the second acquisition device; When it is determined that the similarity between the attribute characteristics of the target object at the target position in the second video frame and the attribute characteristics of the target vehicle meets the preset similarity requirement, the screened second video frame is used as the target video frame.

19. The device according to claim 18, wherein: The second processing unit is further configured to: Based on the ordered dot matrix of the overlapping area of ​​the first monitoring area and the second monitoring area, a preset perspective transformation relationship between the video frame collected by the first acquisition device and the video frame collected by the second acquisition device is obtained.

20. The device according to any one of claims 16 to 19, wherein: The second processing unit is further configured to perform at least one of the following: After identifying the vehicle identification of the target vehicle, deleting the second video data; After the vehicle identification of the target vehicle is identified, an association relationship is established between the target video frame and the target vehicle, and the target video frame is stored.

21. The device according to any one of claims 14 to 20, wherein: The first processing unit is further configured to: Monitoring vehicles appearing in the first video data collected by the first collecting device; It is determined whether there is a target vehicle reaching a target trigger line in the first video data.

22. The device according to claim 21, wherein The first processing unit is further configured to: When it is determined that there is no target vehicle reaching the target trigger line in the first video data, it is detected whether vehicle identifications of other vehicles appearing in the overlapping area in the first video data are stored.

23. The device according to claim 22, wherein: The first processing unit is further configured to, when it is determined that the vehicle identifications of the other vehicles appearing in the overlapping area in the first video data are not stored, identify attribute features of the other vehicles for which the vehicle identifications are not stored; The data calling unit is further used to obtain third video data corresponding to attribute characteristics of other vehicles for which no vehicle identification is stored; the third video data is obtained by the second acquisition device collecting data from the second monitoring area; The second processing unit is further configured to identify, based on the third video data, vehicle identifications of other vehicles for which no vehicle identifications are stored.

24. The apparatus according to any one of claims 14 to 23, further comprising: Monitoring unit; wherein the monitoring unit is used to: Monitoring the motion state of a first vehicle in the first video data; the first vehicle being the same as or different from the target vehicle; When it is determined based on the motion state of the first vehicle that the first vehicle intersects with a parking space area in the first monitoring area, a vehicle entry event is generated for the first vehicle and the parking space where the first vehicle is located.

25. The device according to claim 24, wherein: The monitoring unit is further used for: Monitoring vehicle characteristics of a first vehicle in a parking space corresponding to the vehicle entry event in the first video data; Based on vehicle characteristics of a first vehicle in the parking space corresponding to the vehicle entry event, it is determined whether to generate a vehicle exit event for the first vehicle.

26. The device according to any one of claims 14 to 25, wherein: The collection angle of view of the first collection device is greater than the collection angle of view of the second collection device.

27. A monitoring system, wherein: The monitoring system comprises: a first collection device; At least two second collection devices are arranged on both sides of the first collection device; A monitoring device for executing the method according to any one of claims 1 to 13.

28. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.

29. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-13.

30. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 13.

Images