Text labeling method, device and equipment of video image and storage medium

Abstract

The application provides a text labeling method, device and equipment of a video image and a storage medium, relates to the technical field of video monitoring, and comprises the following steps: obtaining target camera information of a target camera; the target camera is a camera corresponding to a monitoring video image to be labeled; and a plurality of labeling fields corresponding to the target camera are generated according to the target camera information. The method is suitable for the text labeling process of a video image, and is used for solving the problem of low labeling efficiency of artificial induction labeling fields.

Description

Technical Field

[0001] This application relates to the field of video surveillance technology, and in particular to a method, apparatus, device, and storage medium for text annotation of video images. Background Technology

[0002] With the implementation of the data governance initiative, the standardization of text labeling for video images captured by cameras at monitoring points has become increasingly important.

[0003] For the annotation fields corresponding to camera information required by national standards, the current annotation scheme mainly relies on manual annotation. For example, administrators can obtain various relevant information about a certain camera and remotely call the device interface on the platform to remotely send the "camera information" to the device for administrators to configure the camera; or they can summarize various relevant information into the annotation fields corresponding to the camera, and then log in to the onscreen display (OSD) interface corresponding to the camera to annotate the camera's annotation fields in the "Camera Information" column of the OSD interface corresponding to the camera.

[0004] However, manually summarizing and labeling fields is less efficient. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a method, apparatus, device, and storage medium for text annotation of video images. This method can obtain relevant information about a target camera through querying, thereby enabling automatic summarization and annotation of the annotation fields corresponding to the target camera, and improving annotation efficiency.

[0006] In a first aspect, this application provides a method for text annotation of video images, the method comprising: obtaining target camera information of a target camera; the target camera being the camera corresponding to the video image to be annotated; and generating multiple annotation fields corresponding to the target camera based on the target camera information.

[0007] In the text annotation method for video images provided in this application embodiment, the computing device can obtain the target camera information of the target camera and automatically summarize various annotation fields based on the target camera information. Compared with the current manual summarization and manual annotation, the annotation efficiency of this application is higher and the cost is lower.

[0008] In one possible implementation, multiple annotation fields corresponding to the target camera are generated based on the target camera information, including: extracting preset keywords from the target camera information of a preset first type; and determining the annotation fields corresponding to the target camera information of the preset first type based on the extracted preset keywords.

[0009] In one possible implementation, based on the target camera information, multiple annotation fields corresponding to the target camera are generated, including: matching the target camera information of a preset second type according to a preset matching rule to obtain a matching result; the matching rule includes the mapping relationship between keywords and matching results; and determining the annotation fields corresponding to the target camera information of the preset second type based on the matching result.

[0010] In one possible implementation, multiple annotation fields corresponding to the target camera are generated based on the target camera information, including: acquiring video images captured by the target camera; classifying the video images based on a classification algorithm to obtain classification results; and determining the annotation fields corresponding to the camera information of a preset type based on the classification results.

[0011] In one possible implementation, based on the target camera information, multiple annotation fields corresponding to the target camera are generated, including: querying whether the target camera has preset capabilities; if the query result shows that the target camera has preset capabilities, then determining the first preset annotation field corresponding to the preset capabilities; if the query result shows that the target camera does not have preset capabilities, then determining the second preset annotation field corresponding to the preset capabilities.

[0012] Optionally, the method further includes: selecting an annotation template; selecting a target camera; and annotating the target camera with various annotation fields at preset positions in the annotation template.

[0013] Secondly, this application provides a text annotation device for video images, the device comprising various modules for the method described in the first aspect above.

[0014] Thirdly, this application provides a computer program product that, when run on a computing device, causes the computing device to perform the steps of the related method described in the first aspect, so as to implement the method described in the first aspect.

[0015] Fourthly, this application provides a computing device including a processor and a memory; the memory stores processor-executable instructions; when the processor is configured to execute the instructions, the computing device performs the method described in the first aspect above.

[0016] Fifthly, this application provides a computer-readable storage medium comprising: computer software instructions; which, when executed in a computing device, cause the computing device to implement the method described in the first aspect above.

[0017] In a sixth aspect, this application provides a chip including a processor and an interface. The processor is coupled to a memory through the interface, and when the processor executes a computer program in the memory or a computing device executes instructions, the method described in the first aspect is executed.

[0018] The beneficial effects of the second to sixth aspects mentioned above can be referred to the first aspect, and will not be repeated here. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a diagram illustrating the annotation of surveillance videos;

[0021] Figure 2 This is a schematic diagram of the OSD interface;

[0022] Figure 3 A schematic diagram illustrating one component of the text annotation system for video images provided in this application embodiment;

[0023] Figure 4 A schematic diagram illustrating the composition of the electronic device provided in the embodiments of this application;

[0024] Figure 5 A flowchart illustrating the text annotation method for video images provided in this application embodiment;

[0025] Figure 6 A schematic diagram illustrating the composition of a text annotation device for video images provided in an embodiment of this application. Detailed Implementation

[0026] Hereinafter, the terms "first," "second," and "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first," "second," or "third," etc., may explicitly or implicitly include one or more of that feature.

[0027] First, a brief introduction to the terminology used in the embodiments of this application will be given.

[0028] 1. Network Camera / Internet Protocol Camera (IPC): A network camera is a new generation of camera that combines traditional camera technology with network technology. It can transmit video images over a network to another part of the world, and remote viewers do not need any special software; a standard web browser (such as Microsoft IE or Netscape) is sufficient to monitor the video images. An IPC generally consists of a lens, image sensor, sound sensor, signal processor, A / D converter, encoding chip, main control chip, network and control interface, etc.

[0029] 2. Network Video Recorder (NVR): The primary function of an NVR is to receive digital video streams transmitted from IPC (Internet Protocol Camera) devices over a network, and then store and manage them, thereby realizing the advantages of a distributed architecture brought about by networking. Through an NVR, video images captured by multiple network cameras can be viewed, browsed, played back, managed, and stored simultaneously.

[0030] 3. Camera information labeling fields: The camera information recorded in section 5.1.4 of "GA / T 751 Video Image Text Labeling Specification" includes the following parts:

[0031] Depending on whether the camera is controllable, it can be labeled as "moving" or "fixed".

[0032] Depending on the camera type, such as shotgun, spherical, or other, it can be labeled "shotgun", "spherical", or "curved" respectively.

[0033] Depending on whether the camera is installed indoors or outdoors, it can be labeled "indoor" or "outdoor".

[0034] Depending on the purpose of the camera—security, traffic, or key locations—it can be labeled "security," "traffic," or "key locations," respectively.

[0035] Depending on the monitoring location, it can be marked as "East", "South", "West", or "North".

[0036] For example, Figure 1 This is a diagram illustrating the annotation of surveillance videos. For example... Figure 1 As shown, the surveillance video contains a timestamp field "2022-05-24 21:34:59" and a corresponding camera information field "Guqiangwaizhi Garden Road Agricultural Road Northeast Corner Non-Machine Lane Gun North Spot". The meaning of this camera information field is: [Image of camera captured]. Figure 1The camera shown in the surveillance video is a fixed, uncontrollable bullet camera installed outdoors for security monitoring. The specific installation location is at the northeast corner of Huayuan Road and Nongye Road, mainly monitoring the non-motorized vehicle lanes, with the monitoring direction being north.

[0037] For the annotation fields corresponding to camera information required by national standards, the current annotation scheme mainly relies on manual annotation. For example, managers can obtain various relevant information about a certain camera, summarize these various relevant information into the annotation fields corresponding to that camera, and then log in to the OSD interface corresponding to that camera to annotate the camera's annotation fields in the "Camera Information" section of the OSD interface.

[0038] For example, Figure 2 This is a schematic diagram of the OSD interface. (Example) Figure 2 As shown, the OSD interface includes: the exact time when the image or picture was generated, information about the jurisdiction where the image or picture was generated, and camera information.

[0039] The exact time when the image or picture was generated is Beijing time (Greenwich Mean Time, GMT+8:00), and the format of this exact time is "YYYY-MM-DD hh:mm:ss". Here, "YYYY" is a 4-digit number representing the year; "MM" is a 2-digit number representing the month; "DD" is a 2-digit number representing the day; "hh" is a 2-digit number representing the hour in 24-hour format; "mm" is a 2-digit number representing the minute; and "ss" is a 2-digit number representing the second. If the month, day, hour, minute, or second is less than 10, it is padded with leading zeros. For example, 15:21:01 on July 17, 2007 can be displayed as "2007-07-17 15:21:01". The information regarding the jurisdiction where the image or picture was generated includes the province (municipality, or autonomous region), city, district / county, township / street, and the name of the passage (road). Camera information is as described in the terminology section above and will not be repeated here.

[0040] However, manually summarizing and labeling fields is less efficient.

[0041] Based on this, embodiments of this application provide a method, apparatus, device, and storage medium for annotating video images. By querying a server that stores camera information of multiple (surveillance) cameras or a target camera, the target camera information can be obtained, thereby automatically summarizing and annotating the annotation fields corresponding to the target camera information, improving the efficiency of annotation.

[0042] The following description is provided in conjunction with the accompanying drawings.

[0043] Figure 3 This is a schematic diagram illustrating one component of a text annotation system for video images provided in an embodiment of this application. For example... Figure 3 As shown, the system includes: a camera 100, an image processing device 200, and a server 300. The camera 100, the image processing device 200, and the server 300 can be connected via a wired network or a wireless network.

[0044] Among them, camera 100 can be used to collect video images (or surveillance videos) of the monitored area.

[0045] For example, the camera 100 may be the aforementioned IPC, or other image acquisition devices with image acquisition capabilities.

[0046] It should be noted that, Figure 3 The example shown uses a bullet camera (also known as a shotgun camera, bullet camera, etc.) as the camera 100. The camera 100 can also be a dome camera, a high-speed PTZ camera, a panoramic camera, or a radar integrated camera, etc. This application does not limit the specific form of the camera 100.

[0047] In some embodiments, the camera 100 may further include a orientation module. The orientation module can be used to determine the monitoring direction of the camera 100.

[0048] For example, the orientation module may include an electronic compass, which can determine the monitoring direction of the camera 100 based on the azimuth angle measured by the electronic compass and a reference coordinate system with the camera 100 as the reference.

[0049] In some embodiments, the camera 100 may further include an encoder. The encoder can be used to acquire the surveillance video captured by the camera 100 and encode the surveillance video using a specific compression standard (such as the H.264 compression standard) to obtain encoded video data (bitstream).

[0050] In some embodiments, the camera 100 can also be used to send encoded video data to the image processing device 200.

[0051] As described above, the camera 100 and the image processing device 200 can be connected via a wired network or a wireless network. This wired or wireless network may include one or more media or devices capable of transmitting encoded video data from the camera 100 to the image processing device 200.

[0052] In some embodiments, the wired or wireless network may include one or more communication media that enable the camera 100 to transmit encoded video data directly to the image processing device 200 in real time. In this embodiment, the camera 100 may modulate the encoded video data according to a communication standard (e.g., a wireless communication protocol) and transmit the modulated encoded video data to the image processing device 200. The one or more communication media may include wireless and / or wired communication media, such as radio frequency (RF) spectrum or one or more physical transmission lines. Optionally, the one or more communication media may form part of a packet-based network, such as a local area network (LAN), a wide area network (WAN), or a global network (e.g., the Internet). Optionally, the one or more communication media may include a router, switch, base station, or other devices facilitating communication from the camera 100 to the image processing device 200.

[0053] Image processing device 200 is used to receive and store encoded video data sent by camera 100.

[0054] In some embodiments, the image processing device 200 is further configured to decode the encoded video data to obtain surveillance video.

[0055] For example, the image processing apparatus 200 can be the aforementioned NVR, other forms of recording equipment, or other computing devices with decoding capabilities. For instance, the other computing devices with decoding capabilities can be computers, servers, etc. The server can be a single server, or a server cluster consisting of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. Optionally, the server can also be implemented on a cloud platform. For example, the cloud platform can include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, or multi-cloud, or any combination thereof. This application does not limit the specific form of the image processing apparatus 200.

[0056] Optionally, the image processing device 200 may further include a display module. This display module can be used to display the surveillance video obtained after the image processing device decodes the encoded video data.

[0057] It should be noted that the display module can be a component within the image processing device 200. For example, it could be a display screen or touchscreen within the image processing device 200. Alternatively, the display module can be a standalone display device connected to the image processing device. Examples include liquid crystal displays (LCDs), plasma displays, organic light-emitting diode (OLED) displays, or other types of displays. Furthermore, the display module can also be a smart terminal device connected to the image processing device 200. Examples include mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). Optionally, the image processing device 200 can also be one of the aforementioned smart terminal devices.

[0058] Server 300 stores camera information for multiple cameras. Server 300 can summarize the annotation fields for each camera based on this stored information. The specific summarization process can be found in the text annotation method for video images described below, and will not be repeated here.

[0059] The specific form of the server 300 can be referred to the above-mentioned computing device, and will not be repeated here.

[0060] For example, server 300 may be an industry application platform server or an IoT element governance platform server, etc.

[0061] The execution entity of the video image text annotation method provided in this application embodiment can be the aforementioned server 300. As described above, server 300 can be a server, a computing device such as a computer; or, server 300 can be an application (APP) installed on the aforementioned computing device that provides video image text annotation functionality; or, server 300 can be the central processing unit (CPU) in the aforementioned computing device; or, server 300 can be a functional module in the aforementioned computing device used to execute the video image text annotation method. This application embodiment does not impose any limitations on this.

[0062] For simplicity, the following description will use Server 300 as the computing device as an example.

[0063] Figure 4 This is a schematic diagram illustrating the composition of a computing device provided in an embodiment of this application. Figure 4 As shown, the computing device includes: a processor 10, a memory 20, a communication line 30, a communication interface 40, and an input / output interface 50.

[0064] The processor 10, memory 20, communication interface 40, and input / output interface 50 can be connected via communication line 30.

[0065] The processor 10 is configured to execute instructions stored in the memory 20 to implement the text annotation method for video images provided in the following embodiments of this application. The processor 10 may be a CPU, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 10 may also be any other device with processing capabilities, such as a circuit, device, or software module; this embodiment of the application does not limit this. In one example, the processor 10 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are mentioned. As an optional implementation, the computing device may include multiple processors; for example, in addition to processor 10, it may also include processor 60. Figure 4 (The example shown is a dashed line).

[0066] The memory 20 is used to store instructions. For example, the instructions may be computer programs. Optionally, the memory 20 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions; it may also be a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions; it may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, etc. The embodiments of this application do not limit this.

[0067] It should be noted that the memory 20 can exist independently of the processor 10 or it can be integrated with the processor 10. The memory 20 can be located inside or outside the computing device, and this embodiment does not impose any restrictions on this.

[0068] Communication line 30 is used to transmit information between the various components included in the computing device. Communication line 30 can be an industry standard architecture (ISA) line, a peripheral component interconnect (PCI) line, or an extended industry standard architecture (EISA) line, etc. This communication line 30 can be divided into address lines, data lines, control lines, etc. For ease of representation, Figure 4 The line is represented by a single solid line, but this does not mean that there is only one line or one type of line.

[0069] The communication interface 40 is used to communicate with other devices (such as the aforementioned camera 100, or image processing device 200, etc.) or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. The communication interface 40 can be a module, circuit, transceiver, or any device capable of enabling communication.

[0070] Input / output interface 50 is used to enable human-computer interaction between the user and the computing device. This includes, for example, gesture-based, text-based, or voice-based interactions between the user and the computing device.

[0071] For example, the input / output interface 50 may be a mouse, keyboard, display screen or touch screen, etc., through which user and computing device can realize work interaction or text interaction.

[0072] It should be noted that, Figure 4 The structure shown does not constitute a limitation on the computing device, except Figure 4 In addition to the components shown, a computing device may include more or fewer components than illustrated, or combinations of certain components, or different component arrangements.

[0073] The text annotation method for video images provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0074] Figure 5This is a flowchart illustrating a method for text annotation of video images provided in an embodiment of this application. Optionally, this method can be implemented by someone with the above-described... Figure 4 The computing device with the hardware structure shown executes the commands. For example... Figure 5 As shown, the method includes S101 to S102.

[0075] S101, The computing device acquires the target camera information of the target camera.

[0076] The target camera is the camera corresponding to the video image to be labeled, or in other words, the camera that captured the video image to be labeled. Target camera information may include controllability information, camera type information, installation location information, purpose information, and monitoring direction information. Controllability information indicates whether the target camera's attitude can be controlled and adjusted. Camera type information indicates the type of target camera. Installation location information indicates the installation location of the target camera. Monitoring direction information indicates the monitoring direction of the target camera.

[0077] In one possible implementation, as described above, the server 300 (computing device) stores camera information for multiple cameras. In this case, the computing device can obtain the target camera information of the target camera by calling the stored camera information for the multiple cameras.

[0078] Optionally, the computing device may have preset planning information, which is used to indicate the target camera for which camera information needs to be collected. The computing device can periodically acquire the target camera information according to the planning information and according to the preset period, generate various annotation fields corresponding to the target camera based on the target camera information according to the steps in S102 below.

[0079] For example, the target camera can be preset to at least one camera among cameras that have stored camera information in a computing device.

[0080] Optionally, the target camera for which camera information needs to be collected can also be manually configured. As mentioned above, the computing device may also include input / output interfaces, such as a mouse, keyboard, or monitor. The computing device can display a configuration interface on the monitor, which may include camera option buttons corresponding to multiple cameras. The computing device can receive selection operations of one or more camera option buttons from administrators via mouse and keyboard, determine that the camera corresponding to the selected camera option button is the target camera, and retrieve the target camera information of the target camera.

[0081] For example, the camera option button mentioned above could be a checkmark box or a dotted circle. This application does not limit this.

[0082] Optionally, the configuration interface may also include batch operation option buttons. The computing device can receive the selection operation of the batch operation option buttons by the administrator through the mouse and keyboard, determine the cameras corresponding to all option buttons as target cameras, and call the target camera information of the target cameras.

[0083] For example, after identifying the target camera, the computing device can use the target camera's identifier as an index to traverse the stored camera information of multiple cameras and find the camera information corresponding to the target camera's identifier as the target camera's camera information.

[0084] For example, camera information of multiple cameras stored in a computing device may be as shown in Table 1 below.

[0085] Table 1

[0086]

[0087] As shown in Table 1, the camera information stored in the computing device for multiple cameras can include camera items, controllable information items, camera type items, installation location items, purpose items, and monitoring direction items. Specifically, the camera item includes Camera 1, Camera 2, and Camera 3. The controllable information item includes controllable and uncontrollable. The camera type item includes type 1, type 2, and type 3. The installation location item includes location 1, location 2, and location 3. The purpose item includes purpose 1, purpose 2, and purpose 3. The monitoring direction item includes direction 1, direction 2, and direction 3. There is a correspondence between Camera 1 (controllable, type 1, location 1, purpose 1, and direction 1), Camera 2 (controllable, type 2, location 2, purpose 2, and direction 2), and Camera 3 (uncontrollable, type 3, location 3, purpose 3, and direction 3).

[0088] Optionally, the configuration interface may also include template option buttons corresponding to multiple annotation templates. The computing device can receive selection operations from administrators on the template option buttons corresponding to the target annotation template via mouse and keyboard, thereby determining the target annotation template.

[0089] The annotation template is used to indicate the preset position (or annotation position) corresponding to the annotation field. The position layout of the annotation field is different in different annotation templates. The target annotation template is one of multiple annotation templates. For example, the annotation template may include national standard templates and custom templates. The application embodiment does not limit this.

[0090] Optionally, the configuration interface may also include a preview area for the annotation template. After receiving the selection operation of the template option button by the administrator, the computing device may also display the layout of the annotation field positions of the selected target annotation template in the preview area of ​​the annotation template.

[0091] It should be noted that the computing device can determine the target annotation template before or after determining the target camera. This application does not impose any limitations on this.

[0092] S102. The computing device generates various annotation fields corresponding to the target camera based on the target camera information.

[0093] The various annotation fields corresponding to the target camera may include: controllable information field, camera type field, installation location field, purpose field, and monitoring direction field. Taking a traffic camera as an example, the video image captured by the target camera can be traffic flow monitoring video or vehicle snapshot image. This application embodiment does not limit this. The specific process of the computing device generating the various annotation fields corresponding to the target camera can be referred to in the following possible implementation methods, and will not be repeated here.

[0094] Optionally, as described above, the computing device can obtain target camera information of the target camera according to preset plan information and generate multiple annotation fields corresponding to the target camera. In this case, after S102 above, the method may further include: the computing device selecting an annotation template; the computing device selecting the target camera; and the computing device annotating the multiple annotation fields corresponding to the target camera at preset positions on the annotation template. The processes of the computing device selecting the annotation template and selecting the target camera can be referred to the description of selecting the annotation template and target camera in S101 above, and will not be repeated here.

[0095] In the text annotation method for video images provided in this application embodiment, the computing device can obtain the target camera information of the target camera and automatically summarize various annotation fields based on the target camera information. Compared with the current manual summarization and manual annotation, the annotation efficiency of this application is higher and the cost is lower.

[0096] The following describes the specific implementation method of the computing device in S102 generating various annotation fields corresponding to the target camera based on the target camera information.

[0097] In one possible implementation, the computing device can extract preset keywords from the target camera information of a preset first type, and determine the annotation field corresponding to the target camera information of the preset first type based on the extracted preset keywords.

[0098] Both the preset first type and the preset key fields can be preset by administrators in the computing device. The target camera information of the preset first type may include one or more of the following: camera type information, camera purpose information, and monitoring direction information.

[0099] For example, when the target camera information of the first type is preset as camera type information, the preset keywords may include "gun", "ball", or "other". After the computing device obtains the camera type information, it can use a keyword detection algorithm to extract the keywords "gun", "ball", or "other", and determine that the camera type field corresponding to the target camera is "gun", "ball", or "other". Alternatively, it can use keywords and other preset fixed characters to determine the camera type field corresponding to the target camera, such as "gun camera" or "ball camera".

[0100] For example, when the target camera of the first type is preset as usage information, the preset keywords may include "public security", "traffic", or "other". After the computing device obtains the usage information, it can use a keyword detection algorithm to extract the keywords "public security", "traffic", or "other", and determine that the usage field corresponding to the target camera is "public security", "traffic", or "other".

[0101] For example, when the target camera of the first type is preset to monitor the direction information, the preset keywords can include "east", "west", "south", or "north". After the computing device obtains the monitoring direction information, it can use a keyword detection algorithm to extract the keywords "east", "west", "south", or "north", thereby determining that the monitoring direction field corresponding to the target camera is "east", "west", "south", or "north".

[0102] Optionally, as described above, the computing device (server) can be connected to the camera. In this case, for the monitoring direction information in the preset first type of target camera information, if the camera information of multiple cameras stored in the computing device does not include the monitoring direction information of the target camera, or if the preset keyword extraction cannot extract the keyword corresponding to the monitoring direction information of the target camera, then the computing device can send a direction query request to the target camera and receive the monitoring direction information sent by the target camera, and determine the monitoring direction field corresponding to the target camera based on the monitoring direction information sent by the target camera.

[0103] The direction query request information is used to request monitoring direction information from the target camera. The specific process of obtaining the monitoring direction information can be referred to the description in the orientation module of camera 100 above, and will not be repeated here.

[0104] Optionally, as described above, the computing device (server) can be connected to the camera. In this case, for the camera type information in the preset first type of target camera information, if the camera type information of the multiple cameras stored in the computing device does not include the camera type information of the target camera, or if the preset keyword extraction of the camera type information of the target camera fails to extract the keywords corresponding to the camera type information, then the computing device can send a function query request to the target camera and receive the pan-tilt-zoom (PTZ) capability information sent by the target camera. Based on the PTZ capability information sent by the target camera, the computing device determines the camera type field corresponding to the target camera.

[0105] Among them, PTZ capability information is used to indicate whether the camera has horizontal movement capability, vertical movement capability, and zoom capability.

[0106] For example, when the PTZ capability information sent by the target camera indicates that the target camera supports PTZ capability, the computing device can determine that the camera type field corresponding to the target camera is "sphere"; when the PTZ capability information sent by the target camera indicates that the target camera does not support PTZ capability, the computing device can determine that the camera type field corresponding to the target camera is "gun".

[0107] Optionally, as described above, the computing device (server) can be connected to the camera. In this case, for the camera usage information in the preset first type of target camera information, if the camera information of multiple cameras stored in the computing device does not include the camera usage information of the target camera, or if the preset keyword extraction of the camera usage information of the target camera fails to extract the keywords corresponding to the camera usage information, the computing device can determine the camera usage of the target camera based on the preset correspondence between the types of monitoring points and the identity identifiers of cameras, and determine the usage field corresponding to the target camera based on the camera usage of the target camera.

[0108] The type of monitoring point indicates the purpose of the cameras in the monitoring point.

[0109] For example, monitoring points can be categorized as road monitoring points and security monitoring points. The purpose of cameras at road monitoring points is to capture video images of the road. The purpose of cameras at security monitoring points is to capture video images for security purposes. If the monitoring point type corresponding to the target camera's identifier is a road monitoring point, the computing device can determine that the target camera's purpose field is "road". If the monitoring point type corresponding to the target camera's identifier is a security monitoring point, the computing device can determine that the target camera's purpose field is "security".

[0110] In another possible implementation, the computing device can match the target camera information of the second type according to the preset matching rules, obtain the matching result, and determine the annotation field corresponding to the target camera information of the second type based on the matching result.

[0111] The matching rules include the mapping relationship between keywords and matching results. The preset second type of target camera information may include installation location information. Matching can employ fuzzy matching or precise matching; details can be found in relevant technical descriptions and will not be elaborated upon here.

[0112] For example, if the target camera information of the second type is preset as installation location information, keywords can include outdoor keywords such as road, street, park, etc., indicating outdoors, and indoor keywords such as floor, lobby, etc., indicating indoor. The matching result can include indoor or outdoor. The computing device can extract keywords from the installation location information according to the preset keywords, and match the extracted keywords according to the matching rules to obtain the matching result, such as indoor or outdoor. Then, it can determine whether the installation location field is "indoor" or "outdoor", or use keywords and other preset fixed characters to determine the camera type field corresponding to the target camera, such as "indoor" or "outdoor", or "internal" or "external".

[0113] In another possible implementation, the computing device can acquire video images captured by the target camera, classify the video images based on a classification algorithm, obtain classification results, and determine the annotation fields corresponding to the target camera information of a preset type based on the classification results.

[0114] The preset type of target camera information may include one or more of the following: installation location information, controllability information, and camera type information. When the preset type of target camera information is installation location information, the classification result may include indoor monitoring video images or outdoor monitoring images. When the preset type of target camera information is controllability information, the classification result may include video images captured by a movable camera or a fixed camera. When the preset type of target camera information is camera type information, the classification result may include video images captured by a bullet camera or a dome camera. The classification algorithm may be, for example, a neural network algorithm, a Bayesian algorithm, or a support vector machine, etc. This application embodiment does not impose any limitations on this.

[0115] For example, when the video image of the target camera is classified as an indoor video image based on the classification algorithm, the computing device can determine that the installation location field of the target camera is "indoor"; when the video image of the target camera is classified as an outdoor video image based on the classification algorithm, the computing device can determine that the installation location field of the target camera is "outdoor".

[0116] For example, a computing device can acquire video images captured by a target camera within a preset time period, and perform cumulative difference processing on these images to obtain a cumulative difference image. This cumulative difference image can be used to characterize the degree of change in the video images captured by the target camera within the preset time period. When the total pixel value in the cumulative difference image is greater than a preset pixel value threshold, the computing device can determine that the classification result is a video image captured by a movable camera, and determine the controllable field corresponding to the controllable information as "moving". When the total pixel value in the cumulative difference image is less than or equal to the preset pixel value threshold, the computing device can determine that the classification result is a video image captured by a non-moving camera, and determine the controllable field corresponding to the controllable information as "fixed".

[0117] For example, a computing device can acquire video images captured by a target camera within a preset time period and perform cumulative difference processing on these images to obtain a cumulative difference image. This cumulative difference image can be used to characterize the degree of change in the video images captured by the target camera within the preset time period. When the total pixel value in the cumulative difference image is greater than a preset pixel value threshold, the computing device can determine that the classification result is a video image captured by a spherical camera and determine that the camera type field corresponding to the camera type information is "spherical". When the total pixel value in the cumulative difference image is less than or equal to the preset pixel value threshold, the computing device can determine that the classification result is a video image captured by a bullet camera and determine that the camera type field corresponding to the camera type information is "bullet".

[0118] In another possible implementation, the computing device can query whether the target camera has a preset capability; if the query result indicates that the target camera has a preset capability, then the first preset label field corresponding to the preset capability is determined; if the query result indicates that the target camera does not have a preset capability, then the second label field corresponding to the preset capability is determined.

[0119] Optionally, as described above, the computing device stores camera information for multiple cameras. In this case, the computing device can query whether the target camera has preset capabilities by accessing the controllable information of the target camera.

[0120] For example, the preset capability can be at least one of the aforementioned horizontal movement capability, vertical movement capability, and zoom capability. The first preset label field is "moving," and the second preset label field is "fixed." The controllable information of the target camera can include the PTZ capability information of the target camera. If the PTZ capability information of the target camera indicates that the target camera has the preset capability, the computing device can determine that the controllable information field among the various label fields corresponding to the target camera is the first preset label field "moving." If the PTZ capability information of the target camera indicates that the target camera does not have the preset capability, the computing device can determine that the controllable information field among the various label fields corresponding to the target camera is the second preset label field "fixed."

[0121] Optionally, as described above, the computing device (server) can be connected to the camera. In this case, when the computing device cannot query whether the target camera has the preset capability from the camera information of multiple stored cameras, the electronic device can query the target camera to see if it has the preset capability.

[0122] For example, taking at least one of the preset capabilities mentioned above—horizontal movement capability, vertical movement capability, and zoom capability—as an example, with the first preset annotation field being "dynamic" and the second preset annotation field being "fixed," the computing device can send a function query request to the target camera and receive PTZ capability information sent by the target camera. If the PTZ capability information sent by the target camera indicates that the target camera possesses the preset capability, the computing device can determine that the controllable information field among the various annotation fields corresponding to the target camera is the first preset annotation field "dynamic"; if the PTZ capability information sent by the target camera indicates that the target camera does not possess the preset capability, the computing device can determine that the controllable information field among the various annotation fields corresponding to the target camera is the second preset annotation field "fixed."

[0123] It should be noted that the text annotation method for video images provided in this application embodiment has been described using the annotation process as an example. This annotation method can also be used to detect existing annotations in video images. For example, a computing device can obtain a reference annotation field of the video image captured by the target camera according to the above annotation method. When the reference annotation field is different from the current annotation field of the video image captured by the target camera, the computing device can replace the current annotation field with the reference annotation field, thereby realizing the detection and updating of the current annotation field.

[0124] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] In an exemplary embodiment, this application also provides a text annotation device for video images, which can be applied to the image processing device described above. Figure 6 This is a schematic diagram illustrating the composition of a text annotation device for video images provided in an embodiment of this application. For example... Figure 6 As shown, the device includes an acquisition module 601 and a processing module 602.

[0126] The acquisition module 601 is used to acquire target camera information of the target camera; the target camera is the camera corresponding to the video image to be labeled.

[0127] The processing module 602 is used to generate various annotation fields corresponding to the target camera based on the target camera information.

[0128] In some possible embodiments, the processing module 602 is specifically used to extract preset keywords from the target camera information of the preset first type; and to determine the annotation field corresponding to the target camera information of the preset first type based on the extracted preset keywords.

[0129] In other possible embodiments, the processing module 602 is specifically used to match the target camera information of the preset second type according to the preset matching rules to obtain the matching results; the matching rules include the mapping relationship between keywords and matching results; and determine the annotation field corresponding to the target camera information of the preset second type based on the matching results.

[0130] In some other possible embodiments, the processing module 602 is specifically used to acquire video images captured by the target camera; classify the video images based on a classification algorithm to obtain classification results; and determine the annotation fields corresponding to the target camera information of a preset type based on the classification results.

[0131] In some other possible embodiments, the processing module 602 is specifically used to query whether the target camera has a preset capability; if the query result shows that the target camera has a preset capability, then the first preset label field corresponding to the preset capability is determined; if the query result shows that the target camera does not have a preset capability, then the second preset label field corresponding to the preset capability is determined.

[0132] In some other possible embodiments, the processing module 602 is also used to select an annotation template; select a target camera; and annotate multiple annotation fields at preset positions on the annotation template.

[0133] It should be noted that, Figure 6 The module division shown is illustrative and represents only one logical functional division; in actual implementation, other division methods are possible. For example, two or more functions can be integrated into a single processing module. These integrated modules can be implemented either in hardware or as software functional modules.

[0134] In an exemplary embodiment, this application also provides a computer-readable storage medium including computer-executable instructions that, when run on a computing device, cause the computing device to perform any of the methods provided in the above embodiments.

[0135] In an exemplary embodiment, this application also provides a computer program product containing computer execution instructions, which, when run on a computing device, causes the computing device to perform any of the methods provided in the above embodiments.

[0136] In an exemplary embodiment, this application also provides a chip, including: a processor and an interface, wherein the processor is coupled to a memory through the interface, and when the processor executes a computer program in the memory or a computing device executes instructions, any of the methods provided in the above embodiments are executed.

[0137] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer-executable instructions. When these computer-executable instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer-executable instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0138] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0139] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0140] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for text annotation of a video image, characterized in that, The method comprises: obtaining target camera information of a target camera; the target camera is a camera corresponding to a video image to be labeled; inducing a plurality of labeling fields corresponding to the target camera according to the target camera information; The inducing a plurality of labeling fields corresponding to the target camera according to the target camera information comprises: performing first preset keyword extraction on target camera information of a preset first type; determining that the first preset keyword is a labeling field corresponding to the target camera information of the preset first type, or determining the labeling field corresponding to the target camera information of the preset first type by using the first preset keyword and other preset fixed characters; wherein the target camera information of the preset first type comprises one or more of camera type information, camera purpose information, and monitoring direction information; Or, performing second preset keyword extraction on target camera information of a preset second type, and performing matching on the extracted keywords according to a preset matching rule; performing third preset keyword extraction on the matching result; determining that the third preset keyword is a labeling field corresponding to the target camera information of the preset second type, or determining the labeling field corresponding to the target camera information of the preset second type by using the third preset keyword and other preset fixed characters; wherein the matching rule comprises a mapping relationship between the keywords and the matching result, and the target camera information of the preset second type comprises installation location information; Or, obtaining a video image collected by the target camera; classifying the video image based on a classification algorithm to obtain a classification result corresponding to camera information of a preset type; determining a labeling field corresponding to the camera information of the preset type according to the classification result; wherein the target camera information of the preset type comprises one or more of installation location information, controllable information, and camera type information; when the target camera information of the preset type is installation location information, the classification result comprises indoor monitoring video images or outdoor monitoring images; when the target camera information of the preset type is controllable information, the classification result comprises video images collected by a movable camera or video images collected by an immovable camera; when the target camera information of the preset type is camera type information, the classification result comprises video images collected by a gun-type camera or video images collected by a ball-type camera.

2. The method of claim 1, wherein, The inducing a plurality of labeling fields corresponding to the target camera according to the target camera information further comprises: querying whether the target camera has a preset capability; if the query result indicates that the target camera has the preset capability, determining a first preset labeling field corresponding to the preset capability; if the query result indicates that the target camera does not have the preset capability, determining a second preset labeling field corresponding to the preset capability.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: selecting a labeling template; selecting the target camera; labeling the plurality of labeling fields at a preset position of the labeling template.

4. A device for text annotation of a video image, characterized in that The text labeling device of the video image comprises an acquisition module and a processing module. The acquisition module is configured to acquire target camera information of a target camera; the target camera is a camera corresponding to a video image to be labeled; and the processing module is configured to induce a plurality of labeling fields corresponding to the target camera according to the target camera information. The processing module is specifically configured to: perform first preset keyword extraction on target camera information of a preset first type; determine that the first preset keyword is a labeling field corresponding to the target camera information of the preset first type, or determine the labeling field corresponding to the target camera information of the preset first type by using the first preset keyword and other preset fixed characters; wherein the target camera information of the preset first type comprises one or more of camera type information, camera purpose information, and monitoring direction information. Or, perform second preset keyword extraction on target camera information of a preset second type, and match the extracted keywords according to a preset matching rule; perform third preset keyword extraction on a matching result; determine that the third preset keyword is a labeling field corresponding to the target camera information of the preset second type, or determine the labeling field corresponding to the target camera information of the preset second type by using the third preset keyword and other preset fixed characters; wherein the matching rule comprises a mapping relationship between a keyword and a matching result, and the target camera information of the preset second type comprises installation location information. Or, acquire a video image collected by the target camera; classify the video image based on a classification algorithm to obtain a classification result corresponding to camera information of a preset type; and determine a labeling field corresponding to the camera information of the preset type according to the classification result; wherein the target camera information of the preset type comprises one or more of installation location information, controllable information, and camera type information; when the target camera information of the preset type is installation location information, the classification result comprises indoor monitoring video image or outdoor monitoring image; when the target camera information of the preset type is controllable information, the classification result comprises video image collected by a movable camera or video image collected by an immovable camera; and when the target camera information of the preset type is camera type information, the classification result comprises video image collected by a gun-type camera or video image collected by a ball-type camera.

5. The device of claim 4, wherein The processing module is further specifically configured to query whether the target camera has a preset capability; if the query result indicates that the target camera has the preset capability, determine a first preset labeling field corresponding to the preset capability; if the query result indicates that the target camera does not have the preset capability, determine a second preset labeling field corresponding to the preset capability; The processing module is further configured to select a labeling template, select the target camera, and label the plurality of labeling fields at a preset position of the labeling template.

6. A computing device, comprising: The computing device comprises a processor and a memory; The memory stores instructions executable by the processor; The processor is configured to execute the instructions to cause the computing device to implement the method of any one of claims 1-3.

7. A computer readable storage medium characterized by The computer-readable storage medium comprises computer software instructions; When the computer software instructions are run in a computing device, the computing device is caused to implement the method of any one of claims 1-3.

Images