Seat identity recognition method and device, computer equipment and storage medium

Abstract

The invention relates to a seat identity recognition method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a panoramic video stream of an activity place through a panoramic camera, and constructing a three-dimensional space model of the activity place; outputting a three-dimensional space coordinate of each seat in the activity place based on the three-dimensional space model; determining camera parameters of a local camera based on the three-dimensional space coordinates of each seat; acquiring a local image through a local camera based on the camera parameters; and performing seat identity recognition based on the local image to obtain a seat identity recognition result. Through the method and the device, the problem of low accuracy of identity recognition caused by poor definition of the target image in related technologies is solved, the local image acquired by the local camera is adjusted by using the panoramic video stream of the panoramic camera, the definition of the image can be improved, and the accuracy of identity recognition is further improved.

Description

Technical Field

[0001] The present application relates to the technical field of video processing, and particularly to a seat identity recognition method, apparatus, computer device, and storage medium. Background Art

[0002] With the continuous development of video surveillance technology, video surveillance devices have been widely used in the security field. In the monitoring scenarios of large-scale events, it is usually required to purchase tickets with real names and take seats according to the numbers, and be able to automatically detect key personnel and abnormal personnel and take warning and preventive measures.

[0003] Currently, panoramic cameras with a large monitoring range (such as bullet cameras, etc.) are used for monitoring. The panoramic images captured by panoramic cameras have a large range, but the clarity of the target images in the panoramic images is poor, and the details of the target images cannot be seen clearly, resulting in a low accuracy rate of identity recognition.

[0004] In view of the problem of poor clarity of target images in the related art, resulting in a low accuracy rate of identity recognition, no effective solution has been proposed yet. Summary of the Invention

[0005] In the present embodiment, a seat identity recognition method, apparatus, computer device, and storage medium are provided to solve the problem of poor clarity of target images in the related art, resulting in a low accuracy rate of identity recognition.

[0006] In a first aspect, in the present embodiment, a seat identity recognition method is provided, which is applicable to a seat identity recognition system; the seat identity recognition system includes a panoramic camera and a local camera; the method includes:

[0007] Obtain a panoramic video stream of the activity venue through the panoramic camera, and construct a three-dimensional space model of the activity venue; output the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model;

[0008] Determine the camera parameters of the local camera based on the three-dimensional space coordinates of each seat;

[0009] Obtain a local image through the local camera based on the camera parameters;

[0010] Perform seat identity recognition based on the local image to obtain a seat identity recognition result.

[0011] In some of these embodiments, obtaining a panoramic video stream of the activity venue through the panoramic camera and constructing a three-dimensional space model of the activity venue includes:

[0012] Obtain a panoramic video stream of the activity venue through the panoramic camera, perform structured analysis on the panoramic video stream to obtain a panoramic image;

[0013] Perform three-dimensional modeling on the panoramic image using a neural network model to obtain a three-dimensional space model of the activity venue.

[0014] In some embodiments, outputting the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model includes:

[0015] Extract the longitude, latitude, and altitude information of each seat in the three-dimensional space model;

[0016] Obtain the three-dimensional space coordinates of each seat according to the longitude, latitude, and altitude information of each seat.

[0017] In some embodiments, obtaining the three-dimensional space coordinates of each seat according to the longitude, latitude, and altitude information of each seat includes:

[0018] Determine whether there is duplication in the seat information of the seat;

[0019] When there is no duplication in the seat information of the seat, associate the longitude, latitude, and altitude information of each seat with the corresponding seat information to obtain the three-dimensional space coordinates of each seat;

[0020] When there is duplication in the seat information of the seat, number the seat to obtain coding information; associate the longitude, latitude, and altitude information of each seat with the corresponding numbering information to obtain the three-dimensional space coordinates of each seat.

[0021] In some embodiments, determining the camera parameters of the local camera based on the three-dimensional space coordinates of each seat includes:

[0022] Input the three-dimensional space coordinates into a conversion formula to obtain the camera parameters in the local camera coordinate system; the three-dimensional space coordinates are in the three-dimensional space coordinate system;

[0023] Or, input the three-dimensional space coordinates into a conversion formula to obtain the camera parameters in the local camera coordinate system; the three-dimensional space coordinates are in the three-dimensional space coordinate system;

[0024] Acquire a local image through the local camera based on the camera parameters;

[0025] Adjust the shooting angle of the local camera and update the camera parameters with the face orientation of the target object in the local image as a condition.

[0026] In some embodiments, acquiring a local image through the local camera based on the camera parameters includes:

[0027] Based on the camera parameters, obtain a local video stream through the local camera;

[0028] Perform structured analysis on the local video stream to obtain a local image.

[0029] In some embodiments, perform seat identity recognition based on the local image to obtain a seat identity recognition result, including:

[0030] Compare the face image in the local image with the ticket purchase identity image to generate a first seat identity recognition result; the first seat identity recognition result includes sitting in the correct seat and stranger;

[0031] And / or, compare the face image in the local image with the warning identity image to generate a second seat identity recognition result; the first seat identity recognition result includes warning and alarm.

[0032] In a second aspect, a seat identity recognition device is provided in this embodiment, which is applicable to a seat identity recognition system; the seat identity recognition system includes a panoramic camera and a local camera; the device includes: a construction module, a conversion module, an acquisition module, and an identity recognition module;

[0033] The construction module is configured to obtain a panoramic video stream of the activity venue through the panoramic camera, construct a three-dimensional space model of the activity venue; output the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model;

[0034] The conversion module is configured to determine the camera parameters of the local camera based on the three-dimensional space coordinates of each seat;

[0035] The acquisition module is configured to obtain a local image through the local camera based on the camera parameters;

[0036] The identity recognition module is configured to perform seat identity recognition based on the local image to obtain a seat identity recognition result.

[0037] In a third aspect, a computer device is provided in this embodiment, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the seat identity recognition method described in the first aspect above is implemented.

[0038] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored. When the program is executed by a processor, the seat identity recognition method described in the first aspect above is implemented.

[0039] Compared with the related technologies, the seat identity recognition method, device, computer device, and storage medium provided in this embodiment obtain a panoramic video stream of the activity venue through a panoramic camera, and construct a three-dimensional space model of the activity venue; output the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model; determine the camera parameters of the local camera based on the three-dimensional space coordinates of each seat; obtain a local image through the local camera based on the camera parameters; perform seat identity recognition based on the local image to obtain a seat identity recognition result, solving the problem in the related technologies that the clarity of the target image is poor, resulting in a low accuracy rate of identity recognition. Using the panoramic video stream of the panoramic camera to adjust the local image obtained by the local camera can improve the clarity of the image, and thus improve the accuracy rate of identity recognition.

[0040] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects, and advantages of this application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of this application and constitute a part of this application. The illustrative embodiments and descriptions thereof are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0042] Figure 1 is a structural block diagram of a seat identity recognition system provided in an embodiment of this application;

[0043] Figure 2 is a structural block diagram of a video data acquisition module provided in an embodiment of this application;

[0044] Figure 3 is a flowchart of a seat identity recognition method provided in an embodiment of this application;

[0045] Figure 4 is a flowchart of determining the camera parameters of the local camera provided in an embodiment of this application;

[0046] Figure 5 is a schematic flowchart of a seat identity recognition method provided in a preferred embodiment of this application;

[0047] Figure 6 is a structural block diagram of a seat identity recognition device provided in an embodiment of this application.

[0048] In the figure: 10, panoramic camera; 20, local camera; 30, processor; 40, video data acquisition module; 210, construction module; 220, conversion module; 230, acquisition module; 240, identity recognition module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To more clearly understand the purpose, technical solution, and advantages of the present application, the present application will be described and explained below in conjunction with the accompanying drawings and embodiments.

[0050] Unless otherwise defined, the technical terms or scientific terms involved in the present application shall have the general meaning understood by those with ordinary skills in the technical field to which the present application belongs. In the present application, words such as "a", "an", "one kind", "the", "these", etc. do not indicate a limitation in quantity, and they can be singular or plural. The terms "including", "comprising", "having" and any variants thereof involved in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent in these processes, methods, products, or devices. The terms "connected", "coupled", etc. involved in the present application do not limit to physical or mechanical connections, but may include electrical connections, whether directly or indirectly connected. The "multiple" involved in the present application means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Usually, the character " / " indicates that the objects associated before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in the present application only distinguish similar objects and do not represent a specific order for the objects.

[0051] The method embodiment provided in this embodiment can be executed in a seat identity recognition system. Figure 1 is the structural block diagram of the seat identity recognition system in this embodiment. As Figure 1 shown, the system may include a panoramic camera 10, a local camera 20, and a processor 30; among them, the panoramic camera 10 can be a camera with a large field of view angle and can capture panoramic images. If the panoramic camera 10 is fixedly arranged, then the number of panoramic cameras 10 is determined by the size of the activity venue. The larger the activity venue, the more the number of panoramic cameras 10, and after their arrangement, they can capture all positions of the activity venue. If the panoramic camera 10 is movably arranged, then the panoramic camera 10 can obtain panoramic images of the activity venue under a preset path. The local camera 20 can be a high-precision camera and can capture clear local images. The number of local cameras 20 is similar to that of the panoramic camera 10 and will not be elaborated here.

[0052] The panoramic camera 10 and the local camera 20 are both connected to the processor 30, and various method embodiments can run in the processor 30. Among them, the processor 30 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. Those of ordinary skill in the art can understand that Figure 1 The structure shown is only schematic and does not limit the structure of the above system. For example, the system may further include more or fewer components than those shown in Figure 1 or have a different configuration from that shown in Figure 1 shown.

[0053] On the basis of Figure 1 , the system may further include a memory for storing data, a transmission device for communication functions, and input / output devices. The above system may also include a transmission device for communication functions and input / output devices.

[0054] The memory can be used to store computer programs. For example, software programs and modules of application software, such as the computer program corresponding to the seat identification method in this embodiment. The processor 30 executes various functional applications and data processing by running the computer program stored in the memory, that is, implements the above method. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely set relative to the processor 30, and these remote memories can be connected to the system through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0055] The transmission device is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the system. In one instance, the transmission device includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device may be a radio frequency (Radio Frequency, abbreviated as RF) module, which is used to communicate with the Internet wirelessly.

[0056] Such as Figure 2As shown in the figure, the seat identity recognition system further includes a video data acquisition module 40, which is connected to the processor 30 and is used to process the data collected by each camera. Specifically, the video data acquisition module 40 includes a management node and a number of sub-nodes; each sub-node processes the camera connected to it and transmits the processed data to the management node; for example: if the sub-node is connected to the panoramic camera 10, then the sub-node performs structured analysis on the panoramic video stream to obtain a panoramic image; the panoramic image is used as the initial data for 3D modeling. Another example: if the sub-node is connected to the local camera 20, then the sub-node performs structured analysis on the local video stream to obtain a local image; the local image is used as the initial data for seat identity recognition. It can be considered that the video data acquisition module 40 adopts a distributed cluster deployment, with a central management node and multiple sub-nodes, and the management node manages the sub-nodes. Among them, the sub-nodes can be various plugins, and the plugins are responsible for data access adaptation; the use of plugin design can expand cameras from different manufacturers.

[0057] In this embodiment, a seat identity recognition method is provided. Figure 3 It is a flowchart of the seat identity recognition method in this embodiment. As Figure 3 shown, the process includes the following steps:

[0058] Step S210, obtain the panoramic video stream of the activity venue through the panoramic camera, and construct a 3D space model of the activity venue; based on the 3D space model, output the 3D space coordinates of each seat in the activity venue;

[0059] Step S220, determine the camera parameters of the local camera based on the 3D space coordinates of each seat;

[0060] Step S230, obtain the local image through the local camera based on the camera parameters;

[0061] Step S240, perform seat identity recognition based on the local image to obtain the seat identity recognition result.

[0062] Specifically, the activity venue includes, but is not limited to, venues capable of holding activities such as libraries, gymnasiums, swimming pools, outdoor music festival venues, etc. The panoramic camera and the local camera are both arranged at preset positions in the activity venue. The panoramic video streams captured by each panoramic camera can cover the entire activity venue. Of course, the local images obtained by the local cameras can also cover the entire activity venue.

[0063] Among them, there are many ways to construct a three-dimensional space model of the activity venue. For example: input the panoramic video stream into a neural network model to output the three-dimensional space model of the activity venue. Another example: the panoramic camera is moving, and based on the panoramic video stream and the moving path of the panoramic camera, combined with a three-dimensional reconstruction algorithm, the three-dimensional space model of the activity venue can also be obtained; another example: the panoramic camera is fixed, and based on the panoramic video stream and the set pose of the panoramic camera, combined with a three-dimensional reconstruction algorithm, the three-dimensional space model of the activity venue can also be obtained, etc.; examples are not given one by one here. Generally speaking, the three-dimensional space model is in a three-dimensional space coordinate system, and each seat of the three-dimensional space model has corresponding three-dimensional space coordinates in the three-dimensional space coordinate system, so the three-dimensional space coordinates of each seat can be output separately.

[0064] Among them, the camera parameters are in the local camera coordinate system. By pre-calibrating the conversion relationship between the local camera coordinate system and the three-dimensional space coordinate system in advance, the conversion relationship can be used to combine the three-dimensional space coordinates of each seat to obtain the camera parameters of each seat relative to the local camera; then the layout camera can capture a local image under these camera parameters, and this local image is a clear image of the seat. In other embodiments, a neural network model or other conversion algorithms are used to calculate the camera parameters of the local camera based on the three-dimensional space coordinates of each seat, and this is not limited herein.

[0065] Among them, when performing seat identity recognition based on the local image, corresponding seat identity recognition results will be generated according to different seat identity recognition methods. For example: comparing the local image with the ticket purchase identity image will generate a first seat identity recognition result; another example: comparing the local image with the warning identity image will generate a second seat identity recognition result, etc. Thus, the identity recognition can be flexibly adjusted according to the application scenario, while improving the recognition accuracy and increasing the scope of application.

[0066] Through the above steps, obtain the panoramic video stream of the activity venue through the panoramic camera, construct the three-dimensional space model of the activity venue; output the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model; determine the camera parameters of the local camera based on the three-dimensional space coordinates of each seat to complete the high-precision positioning of the local camera; obtain the local image through the local camera based on the camera parameters; perform seat identity recognition based on the local image to obtain the seat identity recognition result, which solves the problem in the related technology that the clarity of the target image is poor, resulting in low accuracy of identity recognition. Using the panoramic video stream of the panoramic camera to adjust the local image obtained by the local camera can improve the clarity of the image, and use the local image with high clarity as the basis for identity recognition, thereby improving the accuracy of identity recognition.

[0067] The above process will be described in detail below:

[0068] In some of these embodiments, obtaining a panoramic video stream of the activity venue through a panoramic camera and constructing a three-dimensional space model of the activity venue in step S210 includes the following steps:

[0069] Step S211, obtaining a panoramic video stream of the activity venue through a panoramic camera, performing structured analysis on the panoramic video stream to obtain panoramic images;

[0070] Step S212, using a neural network model to perform three-dimensional modeling on the panoramic images to obtain a three-dimensional space model of the activity venue.

[0071] Specifically, the process of performing structured analysis on the panoramic video stream to obtain panoramic images can be implemented by invoking a structured analysis service in the video data acquisition module. Of course, video processing technology can also be used to perform structured analysis on the panoramic video stream to obtain panoramic images, and there is no limitation on this.

[0072] Among them, the neural network model is pre-trained and can be obtained by training using relevant neural network algorithms. Then, inputting the panoramic images into the neural network model can output the three-dimensional space model of the activity venue.

[0073] Through this embodiment, first, the panoramic video stream is structurally analyzed into panoramic images to reduce the computational amount of three-dimensional modeling, and then the neural network model is used to perform three-dimensional modeling on the panoramic images to obtain a three-dimensional space model of the activity venue, improving the accuracy and construction efficiency of model establishment.

[0074] In some of these embodiments, outputting the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model in step S210 includes the following steps:

[0075] Step S213, extracting the longitude and latitude information and altitude information of each seat in the three-dimensional space model;

[0076] Step S214, obtaining the three-dimensional space coordinates of each seat according to the longitude and latitude information and altitude information of each seat.

[0077] Specifically, the above process can be: first, segment each seat in the three-dimensional space model, use an object recognition algorithm to recognize each seat, and mark the longitude and latitude information and altitude information of each seat in the three-dimensional space coordinate system. Then, use a coordinate extraction algorithm to extract the longitude and latitude information and altitude information of each seat in the three-dimensional space model, and finally combine the longitude and latitude information and altitude information of each seat into three-dimensional space coordinates for output.

[0078] Through this embodiment, the longitude, latitude, and altitude information of each seat in the three-dimensional space model is extracted, and then combined into the three-dimensional space coordinates of each seat, enabling the accurate positioning of the spatial position of each seat, and thus enabling the accurate calculation of the camera parameters of the local camera based on this.

[0079] In some of these embodiments, obtaining the three-dimensional space coordinates of each seat according to the longitude, latitude, and altitude information of each seat in step S214 includes the following steps:

[0080] Determine whether there is any duplication in the seat information of the seats;

[0081] When there is no duplication in the seat information of the seats, associate the longitude, latitude, and altitude information of each seat with the corresponding seat information to obtain the three-dimensional space coordinates of each seat;

[0082] When there is duplication in the seat information of the seats, number the seats to obtain coding information; associate the longitude, latitude, and altitude information of each seat with the corresponding numbering information to obtain the three-dimensional space coordinates of each seat.

[0083] Specifically, the seat information of the seats is obtained by using an object recognition algorithm; for example, for two seats with corresponding marks of Area B 133-1 and Area B 133-2 respectively; then the corresponding seat information is B1331 and B1332 respectively. At this time, there is no duplication in the seat information of the seats, so associate the longitude, latitude, and altitude information of seat B1331 with B1331 to obtain the corresponding three-dimensional space coordinates; then associate the longitude, latitude, and altitude information of seat B1332 with B1332 to obtain the corresponding three-dimensional space coordinates.

[0084] However, due to the low clarity of the panoramic camera, Area B 133-1 is recognized as Area B 133; Area B 133-2 is also recognized as Area B 133; or there are duplicate seats, and there are two seats with two Area B 133s; then it is considered that there is duplication in the seat information of the seats, and the seats are numbered in order or with appended letters to obtain coding information; for example: number one of the Area B 133s as B133A; number the other Area B 133 as B133B; finally, associate the longitude, latitude, and altitude information of seat B133A with B133A to obtain the corresponding three-dimensional space coordinates; then associate the longitude, latitude, and altitude information of seat B133B with B133B to obtain the corresponding three-dimensional space coordinates.

[0085] Through this embodiment, the influence of duplicate seat information on subsequent calculations can be effectively avoided, further ensuring the accuracy of seat identity recognition.

[0086] In some of these embodiments, determining the camera parameters of the local camera based on the three-dimensional spatial coordinates of each seat includes the following steps:

[0087] Step S221: Input the three-dimensional spatial coordinates into the conversion formula to obtain the camera parameters in the local camera coordinate system; the three-dimensional spatial coordinates are in the three-dimensional spatial coordinate system.

[0088] Or, as Figure 4 shown, Step S222: Input the three-dimensional spatial coordinates into the conversion formula to obtain the camera parameters in the local camera coordinate system; the three-dimensional spatial coordinates are in the three-dimensional spatial coordinate system.

[0089] Step S223: Based on the camera parameters, obtain a local image through the local camera.

[0090] Step S224: Adjust the shooting angle of the local camera and update the camera parameters based on the face orientation of the target object in the local image.

[0091] Specifically, there are multiple calculation methods for determining the camera parameters of the local camera. This application mainly provides two implementation methods, and both of these implementation methods involve the conversion formula.

[0092] Among them, the expression of the conversion formula is:

[0093] p1 = s * r * p2 + T;

[0094] In the formula, p1 represents the coordinate point of the camera parameters in the local camera coordinate system; P2 represents the coordinate point of the three-dimensional spatial coordinates in the three-dimensional spatial coordinate system; S represents the scale factor; R represents the rotation matrix; T represents the translation vector.

[0095] Among them, S, R, and T are all calibration values. After setting up the panoramic camera and the local camera, calibration needs to be performed first to obtain S, R, and T. For an activity venue, calibration can be performed only once. Among them, the local camera coordinate system is the camera coordinate system of the local camera, and it can be constructed with the optical center as the origin of the camera coordinate system, the x and y directions parallel to the image as the Xc axis and the Yc axis, and the Zc axis parallel to the optical axis, with the condition that Xc, Yc, and Zc are perpendicular to each other.

[0096] The first method is: Input the three-dimensional spatial coordinates p2 into the conversion formula, and the camera parameters p1 in the local camera coordinate system can be obtained. The camera parameters p1 can be regarded as the PT value of the local camera. Through this method, automatic conversion can be achieved without manual picking on the map, enabling the positioning of the panoramic camera and the following and capturing of the local camera to be quickly connected, and the local camera can capture clear local images.

[0097] The second method is as follows: based on the first method, the camera parameters will be adjusted and updated. The process of adjustment and update is as follows: based on the camera parameters, local images are obtained through a local camera; conditional on the face orientation of the target object in the local image, the shooting angle of the local camera is adjusted, and the camera parameters are updated; thus, clear and optimal local images can be obtained. Generally, if the face orientation of the target object in the local image is a frontal face, then this local image is the best. Through this method, automatic conversion is achieved without manual picking on the map, enabling the rapid connection between the positioning of the panoramic camera and the following and capturing of the local camera, and the local camera can capture clear and optimal local images.

[0098] In some of these embodiments, obtaining local images through the local camera based on the camera parameters in step S230 includes the following steps:

[0099] Step S231, obtaining a local video stream through the local camera based on the camera parameters;

[0100] Step S232, performing structured analysis on the local video stream to obtain local images.

[0101] Specifically, under the camera parameters, the local camera can accurately locate and continuously obtain a local video stream; call the structured analysis service in the video data acquisition module to perform structured analysis on the local video stream to obtain local images. Of course, video processing technology can also be used to perform structured analysis on the local video stream to obtain local images, and this is not limited.

[0102] Through this embodiment, the local camera accurately obtains a local video stream under the camera parameters, and calls the structured analysis service to quickly complete the structured analysis of the local video stream to obtain clear local images.

[0103] In some of these embodiments, performing seat identity recognition based on the local image in step S240 to obtain a seat identity recognition result includes the following steps:

[0104] Step S241, comparing the face image in the local image with the ticket purchase identity image to generate a first seat identity recognition result; the first seat identity recognition result includes sitting in the correct seat and stranger;

[0105] And / or, step S242, comparing the face image in the local image with the warning identity image to generate a second seat identity recognition result; the first seat identity recognition result includes warning and alarm.

[0106] Specifically, steps S241 and S242 can be selected and combined according to requirements. For example: if the requirement is to identify correct seating; then only step S241 needs to be executed; if the requirement is to identify warnings and alerts; then only step S242 needs to be executed; if the requirement is to identify correct seating and also to issue warnings and alerts; then steps S241 and S242 need to be executed.

[0107] Among them, both the ticket-purchasing identity image and the warning identity image are stored in the storage module or database. When making a comparison, the ticket-purchasing identity image and the warning identity image are extracted from the storage module or database.

[0108] Compare the face image in the partial image with the ticket-purchasing identity image. If the face image is consistent with the ticket-purchasing identity image, it is considered correct seating and continue monitoring; if the face image is inconsistent with the ticket-purchasing identity image, it is considered a stranger and a warning message is generated; the warning message is provided to the user or displayed on the display module for seat identity recognition, so as to quickly screen out strangers.

[0109] Compare the face image in the partial image with the warning identity image. If the face image is inconsistent with the warning identity image, continue to give a warning and continue monitoring; if the face image is consistent with the ticket-purchasing identity image, an alert message is generated, and the alert message is provided to the user or displayed on the display module for seat identity recognition, so as to be able to discover potential safety hazards in advance and improve the safety of using the activity venue.

[0110] It should be noted that the above process will perform seat identity recognition for each seat. After all seats have completed the above process, all seat identity recognition results (including the first seat identity recognition result and the second seat identity recognition result) will be displayed on the display module for seat identity recognition.

[0111] The following describes and illustrates this embodiment through preferred embodiments.

[0112] Figure 5 It is a flowchart of the seat identity recognition method of this preferred embodiment.

[0113] As Figure 5 shown, obtain the panoramic video stream of the activity venue through a panoramic camera, process the panoramic video stream into a panoramic image through video structured analysis service, and then use 3D modeling service to perform real-time 3D modeling on the panoramic image to obtain the 3D space model of the activity venue; extract the longitude, latitude and altitude information of each seat in the 3D space model; transmit the longitude, latitude and altitude information to the SaaS application.

[0114] The SaaS application associates the seat information, longitude and latitude information, and altitude information of each seat to obtain the three-dimensional space coordinates of each seat. Among them, when there is no duplication in the seat information of the seats, the longitude and latitude information and altitude information of each seat are associated with the corresponding seat information to obtain the three-dimensional space coordinates of each seat; when there is duplication in the seat information of the seats, the seats are numbered to obtain the coding information; the longitude and latitude information and altitude information of each seat are associated with the corresponding number information to obtain the three-dimensional space coordinates of each seat.

[0115] The three-dimensional space coordinates are transmitted to the positioning algorithm service of the local camera for conversion to obtain the camera parameters in the local camera coordinate system. The SaaS application uses the Software Development Kit (SDK) to transfer the camera parameters to the local camera to achieve precise control of the camera, thereby completing the best-angle shooting of the face on the seat and obtaining the local video stream. The captured local video stream is processed into local images by the video structuring analysis service, and then the captured local images are subject to identity comparison by the identity comparison service. There are two comparison methods. One is: comparing the face image in the local image with the ticket-purchasing identity image. If the face image is consistent with the ticket-purchasing identity image, it is considered that the seat is occupied correctly and monitoring continues; if the face image is inconsistent with the ticket-purchasing identity image, it is considered a stranger and a warning message is generated. The other is: comparing the face image in the local image with the warning identity image. If the face image is inconsistent with the warning identity image, the warning continues and monitoring continues; if the face image is consistent with the ticket-purchasing identity image, an alarm message is generated and the alarm message is provided to the user or displayed on the display module for seat identity recognition, so as to be able to detect potential safety hazards in advance and improve the security of using the event venue.

[0116] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0117] In this embodiment, a seat identity recognition device is also provided. This device is used to implement the above embodiment and the preferred implementation manner, and those that have been described will not be repeated here. The following terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0118] Figure 6 is the structural block diagram of the seat identity recognition device in this embodiment, asFigure 6 As shown in Figure 6 , the device includes: a construction module 210, a conversion module 220, an acquisition module 230, and an identity recognition module 240;

[0119] The construction module 210 is configured to obtain a panoramic video stream of an activity venue through a panoramic camera, construct a three-dimensional space model of the activity venue; and output three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model;

[0120] The conversion module 220 is configured to determine camera parameters of a local camera based on the three-dimensional space coordinates of each seat;

[0121] The acquisition module 230 is configured to obtain a local image through the local camera based on the camera parameters;

[0122] The identity recognition module 240 is configured to perform seat identity recognition based on the local image to obtain a seat identity recognition result.

[0123] Through the above device, the problem in the related art that the clarity of the target image is poor, resulting in a low accuracy rate of identity recognition, is solved. By using the panoramic video stream of the panoramic camera to adjust the local image obtained by the local camera, the clarity of the image can be improved, and thus the accuracy rate of identity recognition can be improved.

[0124] In some of these embodiments, the construction module 210 is further configured to obtain a panoramic video stream of the activity venue through the panoramic camera, perform structured analysis on the panoramic video stream to obtain a panoramic image;

[0125] Use a neural network model to perform three-dimensional modeling on the panoramic image to obtain a three-dimensional space model of the activity venue.

[0126] In some of these embodiments, the construction module 210 is further configured to extract the longitude and latitude information and altitude information of each seat in the three-dimensional space model;

[0127] Based on the longitude and latitude information and altitude information of each seat, obtain the three-dimensional space coordinates of each seat.

[0128] In some of these embodiments, the construction module 210 is further configured to determine whether there is a duplication in the seat information of the seat;

[0129] When there is no duplication in the seat information of the seat, associate the longitude and latitude information and altitude information of each seat with the corresponding seat information to obtain the three-dimensional space coordinates of each seat;

[0130] When there is a duplication in the seat information of the seat, number the seat to obtain coding information; associate the longitude and latitude information and altitude information of each seat with the corresponding numbering information to obtain the three-dimensional space coordinates of each seat.

[0131] In some of these embodiments, the conversion module 220 is further configured to input the three-dimensional space coordinates into a conversion formula to obtain camera parameters in the local camera coordinate system; the three-dimensional space coordinates are in the three-dimensional space coordinate system;

[0132] Alternatively, input the three-dimensional space coordinates into a conversion formula to obtain camera parameters in the local camera coordinate system; the three-dimensional space coordinates are in the three-dimensional space coordinate system;

[0133] Based on the camera parameters, obtain a local image through the local camera;

[0134] Taking the face orientation of the target object in the local image as a condition, adjust the shooting angle of the local camera and update the camera parameters.

[0135] In some of these embodiments, the acquisition module 230 is further configured to obtain a local video stream through the local camera based on the camera parameters;

[0136] Perform structured analysis on the local video stream to obtain a local image.

[0137] In some of these embodiments, the identity recognition module 240 is further configured to compare the face image in the local image with the ticket-purchasing identity image to generate a first seat identity recognition result; the first seat identity recognition result includes sitting in the correct seat and stranger;

[0138] and / or, compare the face image in the local image with the warning identity image to generate a second seat identity recognition result; the first seat identity recognition result includes warning and alarm.

[0139] It should be noted that the above-mentioned each module can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned each module can be located in the same processor; or the above-mentioned each module can also be located in different processors in any combined form.

[0140] In this embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0141] Optionally, the above computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0142] Optionally, in this embodiment, the above processor may be configured to execute the following steps through the computer program:

[0143] S1. Obtain the panoramic video stream of the activity venue through a panoramic camera, construct a three-dimensional space model of the activity venue; output the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model;

[0144] S2. Determine the camera parameters of the local camera based on the three-dimensional space coordinates of each seat;

[0145] S3. Obtain local images through the local camera based on the camera parameters;

[0146] S4. Perform seat identity recognition based on the local images to obtain the seat identity recognition result.

[0147] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated herein.

[0148] In addition, in combination with the seat identity recognition method provided in the above embodiments, a storage medium can also be provided in this embodiment to implement it. A computer program is stored on the storage medium; when the computer program is executed by a processor, any one of the seat identity recognition methods in the above embodiments is implemented.

[0149] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0150] Obviously, the drawings are only some examples or embodiments of the present application. For those of ordinary skill in the art, the present application can also be applied to other similar situations according to these drawings without creative work. In addition, it can be understood that although the work done during the development process here may be complex and time-consuming, for those of ordinary skill in the art, certain design, manufacturing, or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be regarded as insufficient disclosure of the present application.

[0151] The term "embodiment" in the present application means that the specific features, structures, or characteristics described in combination with the embodiment may be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily mean the same embodiment, nor does it mean being independent or alternative to other embodiments and mutually exclusive. Those of ordinary skill in the art can clearly or implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0152] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of patent protection. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A seat identity recognition method, characterized in that, Applicable to a seat identity recognition system; The seat identity recognition system includes a panoramic camera and a local camera; the method includes: Obtaining a panoramic video stream of an activity venue through the panoramic camera, and constructing a three-dimensional space model of the activity venue; Outputting three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model; Determining camera parameters of the local camera based on the three-dimensional space coordinates of each seat; Obtaining a local image through the local camera based on the camera parameters; Performing seat identity recognition based on the local image to obtain a seat identity recognition result.

2. The seat identity recognition method according to claim 1, characterized in that, Obtaining a panoramic video stream of an activity venue through the panoramic camera, and constructing a three-dimensional space model of the activity venue, including: Obtaining a panoramic video stream of an activity venue through the panoramic camera, performing structured analysis on the panoramic video stream to obtain a panoramic image; Performing three-dimensional modeling on the panoramic image using a neural network model to obtain a three-dimensional space model of the activity venue.

3. The seat identity recognition method according to claim 1, characterized in that, Outputting three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model, including: Extracting longitude and latitude information and altitude information of each seat in the three-dimensional space model; Obtaining three-dimensional space coordinates of each seat according to the longitude and latitude information and the altitude information of each seat.

4. The seat identity recognition method according to claim 3, characterized in that, Obtaining three-dimensional space coordinates of each seat according to the longitude and latitude information and the altitude information of each seat, including: Judging whether the seat information of the seat is repeated; When the seat information of the seat is not repeated, associating the longitude and latitude information and the altitude information of each seat with the corresponding seat information to obtain three-dimensional space coordinates of each seat; When the seat information of the seat is repeated, numbering the seat to obtain coding information; associating the longitude and latitude information and the altitude information of each seat with the corresponding numbering information to obtain three-dimensional space coordinates of each seat.

5. The seat identity recognition method according to claim 1, wherein Determining camera parameters of the local camera based on the three-dimensional space coordinates of each seat, including: Inputting the three-dimensional space coordinates into a conversion formula to obtain camera parameters in the local camera coordinate system; the three-dimensional space coordinates are in a three-dimensional space coordinate system; Or, inputting the three-dimensional space coordinates into a conversion formula to obtain camera parameters in the local camera coordinate system; the three-dimensional space coordinates are in a three-dimensional space coordinate system; Obtaining a local image through the local camera based on the camera parameters; Adjusting the shooting angle of the local camera and updating the camera parameters based on the face orientation of the target object in the local image.

6. The seat identity recognition method according to claim 1, wherein Obtaining a local image through the local camera based on the camera parameters, including: Obtaining a local video stream through the local camera based on the camera parameters; Performing structured analysis on the local video stream to obtain a local image.

7. The seat identity recognition method according to claim 1, wherein, Performing seat identity recognition based on the local image to obtain a seat identity recognition result, including: Compare the face image in the partial image with the ticket-purchasing identity image to generate a first seat identity recognition result; the first seat identity recognition result includes correct seat assignment and stranger; And / or, compare the face image in the partial image with the warning identity image to generate a second seat identity recognition result; the first seat identity recognition result includes warning and alarm.

8. A seat identity recognition device, characterized in that, Applicable to a seat identity recognition system; the seat identity recognition system includes a panoramic camera and a partial camera; the device includes: a construction module, a conversion module, an acquisition module, and an identity recognition module; The construction module is configured to obtain a panoramic video stream of the activity venue through the panoramic camera, construct a three-dimensional space model of the activity venue; output the three-dimensional space coordinates of each seat in the activity venue based on the three-dimensional space model; The conversion module is configured to determine the camera parameters of the partial camera based on the three-dimensional space coordinates of each seat; The acquisition module is configured to obtain a partial image through the partial camera based on the camera parameters; The identity recognition module is configured to perform seat identity recognition based on the partial image to obtain a seat identity recognition result.

9. A computer device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is set to run the computer program to execute the steps of the seat identity recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the seat identity recognition method according to any one of claims 1 to 7 are implemented.

Images