Method and device for monitoring industrial plant
By combining the two-dimensional image data of the video stream with the three-dimensional factory model, the position and orientation of the camera equipment are automatically determined, and the problem of unknown position and zoom factor in multi-camera equipment monitoring is solved, and efficient monitoring and status evaluation of industrial factories is achieved .
Patent Information
- Application Number
- CN202380028847.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-03-23
- Filing Date
- 2023-03-23
- Publication Date
- 2024-11-08
AI Technical Summary
The prior art is difficult to effectively monitor video streams generated by multi-camera devices in industrial factories, especially when the camera position, orientation and zoom factor are unknown, and the recording characteristics in the video stream cannot be automatically extracted, resulting in low monitoring efficiency and difficult to conduct real-time. Intervention.
By receiving video streams and assigning 2D image data components to factory objects using factory three-dimensional models, the positioning, orientation and zoom factors of the camera equipment are automatically determined, thereby outputting the video stream and its object or recording characteristics, realizing automated monitoring and status Classification.
It improves the monitoring efficiency of industrial plants, can quickly locate and evaluate the factory status when an accident occurs, optimizes factory operations and management, and simplifies the processing and analysis of video streaming data.
Smart Images

Figure CN118922787A_ABST
Abstract
Description
[0001] The invention relates to a method and a device for observing or monitoring an industrial plant. Furthermore, a computer program product is proposed, which functions program-controllable devices so that they carry out a method for monitoring an industrial plant.
[0002] Industrial plants (e.g., plants in particular related to the chemical industry), distribution systems for raw materials or processed products, and logistics industrial systems are usually visually monitored or recorded with the aid of cameras. In order to reliably monitor the complex interactions of plant objects in industrial plants, many surveillance cameras are usually used to monitor the corresponding spatial areas and provide video stream data.
[0003] It is desirable to be able to reliably evaluate such real-time video data and to be able to intervene if the plant behavior exhibits irregularities. In the past, camera devices were arranged in a manner distributed over the spatial area to be monitored and, for example, were pivotably mounted or provided with a zoom function. The generated video stream usually does not contain any information other than the video data, so that the specific position of the monitoring camera providing the video stream or the settings of this camera remain unknown. Therefore, in the past, monitoring (especially manual monitoring) has been carried out on the displayed video or film.
[0004] It is desirable to simplify the visual monitoring of industrial plants, in particular by means of video streams. In particular, it is desirable to provide information in addition to image data or video sequences. Typically, only image data are available in already installed monitoring systems of industrial plants.
[0005] The assignment of two-dimensional image data components of an industrial plant to an existing three-dimensional (3D) plant model is described in the following document: N. Navab et al.: "Cyclicon: a software platform for the creation and update of virtual factories", 1999 IEEE, pages 459 to 463, 1999 7th IEEE International Conference on Emerging Technologies and Factory Automation. Proceedings ETFA'99, ISBN: 0-7803-5670-5. Cyclicon allows a two-dimensional projection representing a three-dimensional plant model to be superimposed on the two-dimensional image data. However, this requires that the known configuration of the monitoring camera is assigned in advance to specific 3D model data and vice versa. In addition, the user may be required to mark specific predefined image points in the 2D image data so that the superposition of the video stream can be carried out.
[0006] In the prior art, an essential prerequisite for image analysis is that the source and background content of the two-dimensional image data are predefined. This is often not the case, especially since there are a large number of video streams from different cameras whose recording settings, orientations and other characteristics are not recorded. Furthermore, the cameras are usually not fixed but can be rotated. Therefore, it is often impossible for a user to manually annotate the video stream data while it is running.
[0007] Against this background, it is an object of the present invention to provide an improved method for monitoring an industrial plant, in particular with a plurality of camera devices and plant objects.
[0008] Therefore, a method for monitoring an industrial plant comprising a plant object is proposed, the method comprising the following steps:
[0009] receiving a video stream of the plant generated by means of a camera device, wherein the video stream comprises a time series of two-dimensional image data;
[0010] assigning the two-dimensional image components of the video stream to plant objects by means of a three-dimensional model of the plant, in which corresponding object properties are assigned to the plant objects;
[0011] determining recording characteristics of the image data based on the image components assigned to one or more plant objects and corresponding object characteristics, wherein the recording characteristics include a position, orientation, and / or zoom factor of a camera device capturing the video stream; and
[0012] The video stream and the determined object characteristics and / or recording characteristics are output.
[0013] Receiving the video stream in particular takes place at a monitoring location remote from the location of the camera device. In this respect, during the step of receiving the video stream, the camera device is installed at an unknown location. At the monitoring location, the recorded characteristics are not directly observable but are advantageously derived from the two-dimensional image components and the three-dimensional model of the plant.
[0014] These method steps, in particular those of assigning and determining, are preferably performed in an automated manner. The automated performance can be performed in the background in a computer-implemented manner without the user explicitly calling up the record properties and object properties.
[0015] An industrial plant is understood to mean in particular a system of technical facilities which interact with each other and are used, for example, for the manufacture, processing or transfer of substances. Technical facilities can be understood as plant objects or plant parts. For example, infrastructure plants for water and / or wastewater, recooling plants, power distribution facilities, fuel depots and supply facilities are suitable as industrial plants. In an embodiment, the monitored industrial plant is a plant related to the chemical industry.
[0016] In the method, corresponding context information related to the camera and / or the factory objects captured in the video stream is determined based on image data obtained from a camera device such as a digital monitoring camera or a video stream including a time series of two-dimensional image data. By outputting the video stream and / or the two-dimensional images and the determined object or recording characteristics, the state of the monitored industrial plant can be classified in an improved manner.
[0017] Recording properties are understood to mean in particular properties which can be assigned to a video stream or to individual two-dimensional image data and which are dependent on the creation of the respective image. These can be, for example, the image angle, the segment, the recording position and the orientation of the camera device. Exposure settings are also conceivable as recording properties. Camera properties can also be a term used.
[0018] Environmental conditions, such as light, darkness, weather conditions, etc., may also be considered when determining the recording characteristics.
[0019] An image component may be, for example, an image segment from the entire image or an image data set created by filtering.
[0020] For example, a three-dimensional plant model like a CAD model may be used in which the plant objects (i.e. components of an industrial plant) have known object properties. Suitable object properties include in particular the position, size or dimensions, arrangement or orientation and a list of subcomponents or material properties and surface properties of the respective plant objects. Furthermore, conceivable object properties include a list of assignable static or dynamic data, such as, but not limited to, material and design details, flow media and parameters, such as substances, flow rates, temperatures, pressures or manipulation and control variables of fittings.
[0021] The position, orientation or zoom factor of the corresponding camera device can be derived by an evaluation of the two-dimensional image components, in particular implemented by a computer. That is, with the help of the proposed method, the recording conditions or camera devices for image components or specific plant objects can be characterized more specifically as recording characteristics based on a sequence of two-dimensional image data obtained in a video stream using a suitable three-dimensional model of the industrial plant. Without collecting additional data, the recording characteristics with respect to the orientation, i.e. the direction in which the monitoring camera is facing, as well as the captureable image angle of the monitoring camera or the currently set zoom factor can be obtained. The orientation can be specified in a local or global coordinate system.
[0022] In an embodiment, one or more camera devices have a video capture area. The video capture area comprises the spatial surroundings of the respective camera device and is defined, for example, by camera characteristics such as its capture angle, panning possibilities, zoom possibilities, resolution, light sensitivity, etc. In the case of a fixed mounted camera device with fixed focal length and zoom, the video stream obtained by the camera device shows a fixed image segment, which in this respect forms the video capture area of the surroundings.
[0023] In an embodiment, the industrial plant is arranged in a spatial site or a plant site. In general, the corresponding video capture area is smaller than the plant site. For example, only a large number of partially overlapping video capture areas of multiple camera devices cover the plant site. In an embodiment, the video capture areas are on the plant site, but can be located independently of each other or can be separated in space by non-monitored areas.
[0024] In an embodiment, the camera device is arranged at a factory site and the three-dimensional model of the factory particularly comprises the entire factory site.The step of determining the recording characteristics then preferably comprises determining the positioning of the camera device at the factory site and further preferably within the video capture area.
[0025] In an embodiment, the position of the camera device in a global coordinate system and / or a local coordinate system is output.
[0026] The global coordinate system may be relative to the plant site, while the local coordinate system is relative to the corresponding video capture area. In the environment, the three-dimensional model of the plant covers the plant site in the global coordinate system, and the positioning of the camera device in the global coordinate system and preferably also in the local coordinate system is determined. In this regard, the video capture area preferably covers the local coordinate system.
[0027] The observation or monitoring of the plant is thus improved. If an event such as an accident occurs, personnel can locate and reach the scene of the accident more quickly and easily. The automatic supplementation of recordings and / or object data that cannot be obtained from the video stream alone helps to assess the current plant status or the current situation. This can be used not only to manage accidents, but also generally to assess, optimize and facilitate operator control during plant operation.
[0028] In an embodiment, the monitoring cameras themselves are captured as part of the factory (ie, as factory objects in the 3D model). In any case, the position or location of the respective camera may be known and may be used to determine the orientation and zoom factor.
[0029] Advantageously, the video stream is output together with the object or recording properties so that the comprehensive image information can be specified, for example, in a mobile terminal comprising a display device or a control console for monitoring an industrial plant.
[0030] In this respect, in an embodiment, the video stream as well as the object properties and the recording properties are represented by means of a display device.
[0031] Monitoring a plant is also understood to mean, in particular, observing, evaluating and optimizing by improving the provision of information. In this respect, capturing or obtaining information about the "monitored" plant by means of video stream data is considered monitoring.
[0032] In an embodiment of the method, the following steps are performed: a database is created, which assigns further functional properties and / or context data to the plant objects. The functional properties include, for example, process data, temperature or flowing material. In an embodiment, the context data may in particular include time data, weather data and / or visibility conditions. The above-mentioned assignable static or dynamic data are suitable as context data.
[0033] In particular, the database can be linked to a three-dimensional model of the plant so that corresponding recorded plant objects can be identified from the image components with the aid of the three-dimensional model data and the functional properties. In particular, based on the identification of the plant objects in the image components and the object properties stored in the 3D model (such as size, position or orientation), the camera position, its orientation and / or a zoom factor can be determined.
[0034] In particular, image processing methods as mentioned in the introduction are suitable here. In an embodiment of the method, in particular, the functional properties and / or the background data are updated in real time.
[0035] In the method, the dynamic recording characteristic can be determined, for example, by means of a time sequence of two-dimensional image components of the video stream. It is conceivable to capture the camera movement or zoom speed and output it as the recording characteristic.
[0036] In an embodiment of the method, the orientation or the zoom factor of the respective camera device providing the video stream data is changed, in particular in an automated manner, depending on the recording characteristics of the dynamic or static capture.
[0037] In an embodiment of the method, the video stream does not include information data about the recording characteristics. In this respect, preferably, the recording characteristics are determined only by comparing the assigned two-dimensional image components with the data of the 3D model. In an embodiment, the three-dimensional model data about the industrial plant may include the positioning of one or more camera devices.
[0038] In an embodiment, the zoom factor of the camera device is determined based on a plurality of temporally consecutive two-dimensional image data of the camera device.
[0039] By comparing a plurality of temporally consecutive image data with the object properties present in the three-dimensional model, a zoom factor or a zoom speed can be determined in this respect.
[0040] In an embodiment, the method comprises at least one of the following steps:
[0041] transmitting the video stream to a processing platform;
[0042] transmitting the 3D model to the processing platform; and
[0043] The determined recording characteristics are transmitted from the processing platform to a display device.
[0044] Preferably, the processing platform is designed similar to a cloud service.The processing platform can then be configured to perform the following steps: assigning two-dimensional image components and determining corresponding recording characteristics are performed in a computer-implemented manner in a secure processing environment.
[0045] The processing platform can be implemented, for example, by means of the Microsoft Azure environment or through web services of other providers (eg AWS). The corresponding data are preferably transmitted via a secure and encryption-protected communication protocol.
[0046] In an embodiment, the processing platform is designed similarly to an app running on a terminal (e.g., a smart phone or tablet computer). The processing platform is then configured to perform the following steps: assigning two-dimensional image components and determining corresponding recording characteristics are performed in a computer-implemented manner in a secure processing environment of the terminal.
[0047] In an embodiment, the method comprises receiving a plurality of video streams from different camera devices.
[0048] The steps of assigning two-dimensional image components, determining corresponding recording characteristics and outputting the video stream are preferably carried out for each video stream and associated camera device using in each case a corresponding 3D model of the corresponding industrial plant or plant part. In embodiments, the same 3D model may be used, and in other embodiments different 3D models are used.
[0049] The camera devices in particular capture different areas of the industrial plant so that the capture direction of the respective two-dimensional image components of the respective video streams is defined according to the orientation, positioning and zoom setting of the respective camera. In this respect, additional context like recording properties or object properties can be added to each video stream. It is conceivable to superimpose a representation of the video stream image and the additional properties. The additional properties are understood to be in particular camera data and object data.
[0050] Embodiments include optionally forwarding one of the plurality of video streams to a processing platform designed as a cloud service.
[0051] Furthermore, a device is proposed for carrying out the method for monitoring an industrial plant as described above and below. A device comprises in particular:
[0052] A camera device for generating a video stream of the industrial plant;
[0053] A storage device for providing a three-dimensional model of the plant, in which corresponding object properties are assigned to the plant objects;
[0054] a processing device for assigning two-dimensional image components of the video stream to factory objects by means of the 3D model and for determining the recording characteristics; and / or
[0055] A display device is provided for outputting the video stream and the determined object properties and / or recording properties, in particular as a superimposition and assignment to a 3D model.
[0056] In this case, the camera device, the storage device, the processing device and the display device are preferably communicatively coupled to each other.The functionality of the processing device may be provided by a software service in a cloud environment.
[0057] The corresponding method steps or functionalized devices (e.g., processor units or processing devices) can be implemented in hardware and / or software. If implemented in hardware, the corresponding functions can be embodied as a device or a part of a device, such as a computer or a microprocessor. If implemented in software, the corresponding units can be embodied as a computer program product, an app, a function, a routine, a part of a program code or an executable object, in particular a software service in a cloud environment.
[0058] Furthermore, a computer program product is proposed, which comprises computer-readable instructions which, when executed by a computer, cause the computer to perform the above method. A computer program product in particular comprises machine-readable instructions which, when processed by one or more processor devices of a processing environment, cause one or all method steps of the proposed method to be performed.
[0059] A computer program product, such as a computer program device, may be provided or supplied, for example, as a storage medium, such as, for example, a memory card, a USB stick, a CD-ROM, a DVD or in the form of a file downloadable from a server in a network. This may be done, for example, in a wireless communication network by transmitting a corresponding file comprising the computer program product or the computer program device.
[0060] The embodiments and features described for the proposed device apply mutatis mutandis to the proposed method.
[0061] Other possible implementations of the present invention also include the above or below about the combination of features or embodiments not explicitly mentioned in the example description. In this case, those skilled in the art will also add separate aspects as improvements or supplements to the corresponding basic forms of the present invention.
[0062] Further advantageous configurations and aspects of the invention are subject matter of the dependent claims and of the examples of the invention described below.The invention is explained in more detail below based on preferred embodiments with reference to the drawings.
[0063] Figure 1 A flow chart showing method steps of a variant of a method for monitoring an industrial plant;
[0064] Figure 2 An expanded flow chart showing method steps of another variant of the method for monitoring an industrial plant;
[0065] Figure 3 An embodiment of an apparatus for monitoring an industrial plant is schematically shown;
[0066] Figure 4schematically shows the assignment of video streams and image components to plant objects to illustrate the method for monitoring an industrial plant; and
[0067] FIG. 5 shows an embodiment of a display device.
[0068] In the figures, identical or functionally identical elements are provided with the same reference symbols, unless otherwise indicated.
[0069] Figure 1 and Figure 2 A flow chart showing exemplary method steps for a method for monitoring an industrial plant is shown. These method steps are specifically described in the following manner: Figure 3 The invention is implemented in an embodiment of the apparatus for monitoring an industrial plant schematically shown in FIG.
[0070] in this regard, Figure 3 A monitoring system or device 1 of an industrial plant 2 is shown, which can be, for example, a complex pipeline system, a factory, a refinery, a production line or a logistics facility. The plant 2, which geographically occupies a wide spatial area, can be captured by one or more monitoring cameras 3, 4 designed as digital cameras. In this case, in particular, video stream data are generated in real time. In this case, the cameras 3, 4 used can be arranged at different locations in the area of the plant 2 and can be oriented, for example, pivotably or fixedly. It is also conceivable that different cameras are equipped with optical zoom. In this way, the video stream will show different image fragments to reproduce parts or objects of the plant 2.
[0071] The video stream data (in Figure 3 The video data provided by the installed camera system do not include information about the respective orientations of the cameras 3, 4, zoom factors or, for example, focus settings.
[0072] exist Figure 4 In FIG. 4 , frames of a video stream VS are schematically represented on the left hand side, by way of example. In this case, the industrial plant 2 is indicated in a simplified manner by four plant objects A, B, C, D. Furthermore, the video stream VS comprises a representation of the surroundings of the industrial plant. One of the cameras 3, 4 can then focus on an image component PT, for example a pipe system C between two plant parts B and D. In order to make the display more detailed and more meaningful for the personnel, a first method step (cf. Figure 1 ) involves receiving video stream data VS (step S1).
[0073] Thereafter, method steps S2 and S3 involve establishing a relationship between an available three-dimensional (3D) model of the monitored industrial plant 2 or the plant object or its components and the image components of the video stream VS. For this purpose, in step S2, a three-dimensional model (e.g. a CAD (Computer Aided Design) model of the industrial plant 2) is used to convert the image components of the video stream VS into a 3D model. Figure 4 The corresponding two-dimensional image components PT indicated in are assigned to plant objects of the industrial plant.
[0074] Figure 4 The representation in Figure 1 shows this assignment through dashed arrows. The 3D CAD model of the plant is schematically shown in Figure 1. Figure 4 On the right-hand side of the . In this case, the plant objects A', B', C', D' present in the 3D model CAD of the plant have object properties. For example, the detailed CAD data exists as object properties. In this case, the object properties may include size, positioning, spatial orientation and further properties. Figure 4 In the example shown, the image component PT relates to a pipe C which extends, for example, horizontally and has, for example, a specific flowing material. In this respect, for example, object data specifying the permissible surface temperature of the pipe C' can be retrieved from another database related to the functioning of the industrial plant.
[0075] In step S3, the camera characteristics of the camera 3, 4 providing the image component PT in the video stream VS are determined as recording characteristics of the image. For this purpose, the two-dimensional image data PT reproducing the plant object C, i.e. the pipe system, are compared with the object characteristics present in the three-dimensional plant model CAD. From this, for example, the positioning and / or orientation or the viewing direction of the camera providing the image segment PT can be determined. Furthermore, the zoom factor of the respective camera can be derived from the knowledge of the positioning and the image segment PT. In this respect, recording characteristics, in particular the positioning orientation and the zoom factor of the camera device, can be captured from the two-dimensional video stream data VS.
[0076] In step S4, these background data including the plant object data and the recorded properties as well as the video stream are then output.
[0077] In this respect, the proposed method provides for image data-based tracking of the monitoring cameras 3, 4 used. In particular, camera movements and zoom settings of the respective cameras can be determined in real time. The computer-implemented evaluation and image processing of the video stream data can be carried out according to known methods, as for example mentioned in conjunction with the Cyclicon software mentioned in the introduction. However, other algorithms are also conceivable for identifying plant objects present in the three-dimensional model based on two-dimensional image data. Algorithms for identifying superimposed points of a 3D model in a 2D image are likewise known. Such algorithms can also be used here.
[0078] Figure 2The additional method steps or processes indicated in Figure 3 Executed, Figure 3 A cloud-based monitoring system of an industrial plant 2 is shown. A preparation step S10 involves generating one or more video streams by means of video surveillance cameras 3, 4. Figure 4 The video stream data VS schematically indicated on the left side of is fed to the console computer 6 via the local computing system. The local computing system 5 receives the video stream data VS of, for example, different surveillance cameras 3, 4 and prepares these video stream data for presentation on a display. The corresponding data processing steps are performed locally, which is performed by Figure 4 The curly braces in LKL indicate.
[0079] Since the acquired video stream data VS is present without further context, in particular without knowing the location of the surveillance cameras 3, 4 used, this or specific video stream data VS with additional information can be displayed via a suitable terminal of the user USR, for example via a tablet computer or a mobile display device 8. For this purpose, a cloud platform 7 with corresponding software services 10, 11, for example using Microsoft Azure, is configured. The cloud computing environment CLD is in Figure 4 Indicated by dotted lines.
[0080] In particular, the 3D plant model service 10 and the app service 11 for being communicatively coupled to the user terminal 8 are provided as software services.
[0081] also, Figure 3 A database device 9 is shown coupled to the cloud environment CLD via an interface 12. The database 9 comprises corresponding 3D model data of the monitored industrial plant 2. These data may be CAD data. Furthermore, the database 9 may comprise additional information or background data about the plant objects installed in the plant 2. This may be, for example, the above-mentioned information about the flowing material of a specific pipeline. In step S11, a corresponding 3D plant model or 3D model data is generated in advance or provided. For example, such model data are generated during the design or planning of the industrial plant.
[0082] In step S12, the software service 10 instantiates a corresponding three-dimensional plant model based on the 3D model data (e.g., CAD data) obtained from the database 9. Then, the software service denoted by 11 of the cloud environment 7 basically performs the method steps S1, S2, S3 and S4, which are considered together as Figure 1 and Figure 2 The dotted double arrow shows the communication coupling between the terminal 8 (ie the display device 8 of the user USR) and the software service or app 11.
[0083] FIG5 shows a possible embodiment of a display state of a terminal 8. The terminal is a display device 8 comprising a display 14, on which, for example, video stream data VS is represented. In addition, the user terminal 8, which is implemented as a display device, is provided with an operating element 13. Via the operating element 13, the user USR can call up context information about the image data VS' represented on the display 14, for example, via a touch screen function or other tactile elements.
[0084] exist Figure 5A In the Figure 4 . At the same time, in the cloud environment CLD, via the software service 11, the software service 10 retrieves the corresponding plant object data associated with the plant objects A, B, C, D identified in the video stream VS. Furthermore, these object data are assigned as described with respect to method step S2.
[0085] For example, by means of the software service 11, it can be identified that the pipeline C in the image component represented by the dashed line has an elevated temperature that does not meet the target temperature. If the user selects the represented plant area C, an enlarged representation of the area with the additional information XYZ (represented by 15) added or superimposed appears, for example Figure 5B The additional information 15 can, for example, represent a warning and indicate to the user a safety event in the monitored plant. Based on the camera information determined in method step S3, the user can switch back and forth between different cameras. By determining the recording characteristics with regard to orientation and zoom settings, this simplifies the navigation and selection of the video stream images displayed by means of the display device 8.
[0086] In summary, the proposed monitoring method allows to enrich pure video stream data with contextual data like object properties stored in 3D models and to track possible camera pans or zooms. The proposed functionalities and extended representation of video image data can be provided via a cloud environment and cloud services via a suitable user interface of a display device.
[0087] Although the invention has been described in more detail based on examples, various modifications are possible. For example, the indicated image component (i.e., the tube) may be any plant component. Furthermore, the monitoring may be influenced by additional sensor data (e.g., recordings from a spectral camera). Thus, further improvements to the monitoring performance may be provided. Instead of the CAD data mentioned for the 3D model, other formats such as OBJ or other formats are also possible.
[0088] Reference numerals:
[0089] 1Factory Monitoring System
[0090] 2 Factory
[0091] 3 cameras / surveillance cameras
[0092] 4 cameras / surveillance cameras
[0093] 5 Local computing devices
[0094] 6. Console
[0095] 7. Cloud Environment
[0096] 8 Display Devices
[0097] 9 Database
[0098] 10 3D Models
[0099] 11 App Services
[0100] 12 interfaces
[0101] 13 Operating elements
[0102] 14 Display
[0103] 15 Additional Information
[0104] A, B, C, D representation of factory objects in video streams
[0105] A', B', C', D' are factory objects with object properties according to the 3D model
[0106] PT image component
[0107] S1 receives the video stream
[0108] S2 assigns 2D image components to factory objects based on the 3D model
[0109] S3 Determine the recording characteristics
[0110] S4 outputs video stream data with camera / object characteristics
[0111] S5 adds background data to the video stream data
[0112] S10 generates video stream
[0113] S11 generates 3D factory model
[0114] S12 instantiated 3D factory model
[0115] VS Video Streaming
[0116] XYZ context, camera or additional information
Claims
1. A method for monitoring an industrial plant (2) comprising a plant object, the method comprising the following steps: Receiving (S1) a video stream (VS) of the plant (2) generated by means of a camera device (3), wherein the video stream (VS) comprises a time sequence of two-dimensional image data; Assigning (S2) the two-dimensional image components (PT) of the video stream (VS) to plant objects (A', B', C', D') with the aid of a three-dimensional (3D) model (CAD) of the plant (2), in which corresponding object properties (XYZ) are assigned to the plant objects (A', B', C', D'); determining (S3) recording characteristics of the image data based on the image components (PT) assigned to one or more plant objects (C') and the corresponding object characteristics (XYZ), wherein the recording characteristics include the position, orientation and zoom factor of the camera device (3) capturing the video stream; and The video stream (VS') is output (S4) together with the determined object properties (XYZ) and recording properties.
2. The method according to claim 1, wherein: The industrial plant (2) is arranged at a plant site, and the position of the camera device (3) at the plant site is determined.
3. The method according to claim 2, wherein: The camera device (3) has a video capturing area that is smaller than the factory site.
4. The method according to any one of claims 1 to 3, wherein: During the step of receiving the video stream (VS), the camera device (3) is installed at an unknown location.
5. The method according to any one of claims 1 to 4, wherein: These object properties (XYZ) include the location, size / dimensions, arrangement / orientation, component list, material properties and / or surface properties of the factory object (A', B', C', D').
6. The method according to claims 1 to 5, further comprising: A database (9) is created (S11) which assigns further functional properties and / or background data to the plant objects (A', B', C', D'), wherein the functional properties include in particular process data, temperature, flowing material and the background data include in particular time data, weather data and / or visibility conditions.
7. The method according to claim 6, wherein: These functional characteristics and / or background data are updated, in particular in real time.
8. The method according to any one of claims 1 to 7, wherein: This assignment (S2) is also carried out according to the functional properties of the plant objects (A', B', C', D').
9. The method according to any one of claims 1 to 8, wherein: The three-dimensional model is a computer-aided design model of the industrial plant (2).
10. The method according to any one of claims 1 to 9, wherein: Dynamic recording properties, in particular camera movement or zoom speed, are determined using the time sequence of two-dimensional image components of the video stream (VS).
11. The method according to claim 10, wherein: The camera movement and / or zoom speed is determined in real time.
12. The method according to any one of claims 1 to 11, wherein: The video stream (VS) does not comprise information data about the recording characteristics and the recording characteristics are determined solely by comparing the assigned two-dimensional image components (PT) with the data of the 3D model (CAD).
13. The method according to any one of claims 1 to 12, wherein: The 3D model data include the positioning of the camera device (3).
14. The method according to any one of claims 1 to 13, wherein: A zoom factor is determined based on a plurality of temporally consecutive two-dimensional image data of the camera device (3).
15. The method according to any one of claims 1 to 14, further comprising: The video stream (VS) and the object properties (XYZ) and / or recording properties are displayed (S5) by means of a display device (8).
16. The method according to any one of claims 1 to 15, further comprising: A three-dimensional (3D) model of the plant is created (S12), wherein object properties (XYZ) are assigned to the plant objects.
17. The method according to any one of claims 1 to 16, further comprising: Transmitting the video stream (VS) to a processing platform (7); Transmitting the 3D model (CAD) to the processing platform (7); as well as transmitting the determined recording characteristics from the processing platform (7) to a display device (8); Therein, the processing platform (7) is designed similarly to a cloud service (CLD) and is configured to perform the following steps: assigning (S2) two-dimensional image components and determining (S3) corresponding recording characteristics in a computer-implemented manner in a secure processing environment (CLD).
18. The method according to any one of claims 1 to 17, further comprising: receiving a plurality of video streams (VS) from different camera devices (3, 4); Therein, the steps of assigning (S2) two-dimensional image components (PT), determining (S3) corresponding recording characteristics and outputting (S4) the video stream (VS) are carried out for each video stream and the associated camera device (3, 4) in each case using a corresponding 3D model (CAD).
19. The method according to claim 18, further comprising: Optionally, one of the multiple video streams is forwarded to a processing platform (7), wherein the processing platform (7) is designed similarly to a cloud service (CLD) and is configured to perform the following steps: assigning (S2) two-dimensional image components and determining (S3) corresponding recording characteristics in a computer-implemented manner in a secure processing environment.
20. A computer program product comprising machine-readable instructions which, when processed by one or more processor devices of a processing environment (CLD), cause the execution of one or all method steps of the method according to any one of claims 1 to 19.
21. An apparatus (1) for performing the method according to any one of claims 1 to 19, comprising: A camera device (3, 4) for generating a video stream (VS) of the industrial plant (2); a storage device (9) for providing a three-dimensional (3D) model of the plant (2), in which corresponding object properties (XYZ) are assigned to the plant objects (A', B', C', D'); a processing device (10, 11) for assigning two-dimensional image components (PT) of the video stream (VS) to plant objects by means of the 3D model (10) and for determining the recording characteristics; and comprising a display device (8) for outputting the video stream (VS) and the determined object characteristics and / or recording characteristics; The camera device (3, 4), the storage device (9), the processing device (10, 11) and the display device (8) are communicatively coupled to each other.
