WO2023180362A1 - Ensemble de surveillance avec autorisation d'accès, procédé, programme informatique et support de stockage - Google Patents

Ensemble de surveillance avec autorisation d'accès, procédé, programme informatique et support de stockage Download PDF

Info

Publication number
WO2023180362A1
WO2023180362A1 PCT/EP2023/057284 EP2023057284W WO2023180362A1 WO 2023180362 A1 WO2023180362 A1 WO 2023180362A1 EP 2023057284 W EP2023057284 W EP 2023057284W WO 2023180362 A1 WO2023180362 A1 WO 2023180362A1
Authority
WO
WIPO (PCT)
Prior art keywords
module
objects
designed
evaluation
image
Prior art date
Application number
PCT/EP2023/057284
Other languages
German (de)
English (en)
Inventor
Christoph BURGER-SCHEIDLIN
Original Assignee
Robert Bosch Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Robert Bosch Gmbh filed Critical Robert Bosch Gmbh
Publication of WO2023180362A1 publication Critical patent/WO2023180362A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H04N21/4318—Generation of visual interfaces for content selection or interaction; Content or additional data rendering by altering the content in the rendering process, e.g. blanking, blurring or masking an image region
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
    • H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
    • H04N21/234318—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by decomposing into objects, e.g. MPEG-4 objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
    • H04N21/2347—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving video stream encryption
    • H04N21/23476—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving video stream encryption by partially encrypting, e.g. encrypting the ending portion of a movie
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/4408—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving video stream encryption, e.g. re-encrypting a decrypted video stream for redistribution in a home network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/454—Content or additional data filtering, e.g. blocking advertisements
    • H04N21/4545—Input to filtering algorithms, e.g. filtering a region of the image
    • H04N21/45455—Input to filtering algorithms, e.g. filtering a region of the image applied to a region of the image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/462—Content or additional data management, e.g. creating a master electronic program guide from data received from the Internet and a Head-end, controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
    • H04N21/4627—Rights management associated to the content
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/4728—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for selecting a Region Of Interest [ROI], e.g. for requesting a higher resolution version of a selected region
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Definitions

  • the invention relates to a monitoring arrangement for image-based monitoring of a monitoring area.
  • the invention further relates to a method, a computer program and a storage medium.
  • Image-based and/or camera-based surveillance of areas is used in both the private and commercial sectors to monitor buildings or outdoor areas, especially for monitoring airports, train stations or authorities.
  • image data, images and/or videos of the area to be monitored are recorded by distributed cameras and further processed and/or analyzed for the respective monitoring purpose.
  • sensitive and/or personal data is necessarily collected, which must be particularly protected and/or must be particularly protected during transmission and/or storage or provision to other devices.
  • US 2019 018830A1 describes a method for applying a GAN (Generative Adversarial Network) to image data in order to alienate sensitive image areas.
  • GAN Geneative Adversarial Network
  • the invention relates to a monitoring arrangement with the features of claim 1.
  • a method, a computer program and a data carrier are also proposed.
  • Preferred and/or advantageous embodiments result from the subclaims, the description and the attached figures.
  • a monitoring arrangement for image-based monitoring of a surveillance area is proposed.
  • image-based surveillance is understood to mean surveillance based on images or videos of the surveillance area.
  • image in particular input image, evaluation image or image data
  • video can also be understood as video, with the video comprising a stream of images.
  • the monitoring arrangement is designed and/or set up to allow application-specific, user-specific and/or adaptable monitoring of the monitoring area, for example by using different and/or interchangeable evaluation applications.
  • the surveillance area can include an indoor area and/or an outdoor area.
  • the monitoring arrangement comprises at least one camera, in particular the monitoring arrangement comprises at least ten cameras.
  • the camera can be designed as a stationary or mobile camera, in particular as a pivotable and/or zoomable camera.
  • the camera is designed and/or set up to record and/or provide image data.
  • the image data includes at least one input image and/or a video comprising the input image.
  • the input image shows and/or includes a section of the surveillance area recorded by the respective camera.
  • the input image shows a scene, where the scene includes at least one object.
  • the scene includes a background and/or a stationary environment in the sense of a background.
  • Objects of the scene are understood to mean, in particular, moving and/or temporarily existing objects in the scene, for example people, vehicles or personal items such as suitcases.
  • the objects preferably belong to different object classes and/or can be assigned to different object classes, for example person, animal or physical object.
  • the objects can be assigned to a scene event.
  • the scene event is formed by a contextual context of the assigned objects and optionally in addition to the background and/or the stationary environment.
  • the scene event can be, for example, an accident event, a fire event, or a Display application-specific events in the monitoring area or scene.
  • the scene event includes the objects involved.
  • the scene event is an accident event with two cars as involved objects.
  • the monitoring arrangement includes a detection module.
  • the detection module can be designed as a hardware module or as a software module. Particularly preferably, the detection module is part of the camera and/or connected directly to the camera.
  • the image data, in particular the input image and/or video, are provided to the detection module.
  • the detection module is preferably designed for object recognition, object detection, object classification and/or object tracking.
  • the detection module works in particular on the basis of digital image processing.
  • the detection module detects, tracks, classifies and/or localizes the at least one object as a detected object based on the input image. In particular, based on the input image, all objects in the scene are detected, classified, localized and/or tracked as detected objects by the detection module.
  • the detection module is designed to distinguish between the input image in the background (no object) and an object external to the background (object) as part of the detection of the object.
  • the monitoring arrangement includes a removal module.
  • the distance module is part of the camera and/or forms a common unit with the detection module.
  • the removal module can be designed as a hardware or a software module.
  • the distance module is provided with the image data, in particular the input image, as well as the objects detected by the detection module and/or the at least one detected object.
  • the distance module is designed to determine the at least one detected object as an authorized object or as an unauthorized object. In a default mode it can be provided that all detected objects are determined as unauthorized objects without further input. Alternatively, a set of rules for determining unauthorized objects can be provided.
  • the detection module communicates to the monitoring arrangement and/or to the distance module which object classes and/or objects of a scene event it can detect. In particular, the detection module assigns the detected objects to an object class and/or a scene event.
  • the removal module has the function of removing the unauthorized objects in the input image in order to generate a cleaned evaluation image. This means, for example, that after all of the detected objects have been removed, only the stationary background is output as a cleaned evaluation image. Removal is understood to mean, in particular, removal of the information content of the respective object or partial areas thereof. Removal can be accomplished by blackening, covering, blurring, etc. It is also possible to completely cut out the respective object or partial area, so that unfilled, in particular white or black, areas are present in the evaluation image.
  • the detection module and/or the distance module is in particular designed to assign objects to an object class and/or a scene event, so that the assignment is made to the distance module.
  • the monitoring arrangement includes an evaluation module.
  • the evaluation module can be designed as a software or hardware module.
  • the evaluation module can be part of the camera, alternatively the evaluation module is assigned to a cloud module, an evaluation center or a peripheral device.
  • the evaluation module is designed and/or set up to execute and/or use at least one evaluation application.
  • the evaluation application is applied to the evaluation image.
  • different and/or interchangeable evaluation applications can be executed and/or used on the application module, the evaluation applications being available, for example, from an app store.
  • the application module and/or the evaluation application does not have direct access and/or no direct data connection to the original input image.
  • the evaluation module is not only supplied with a single evaluation image, but also with a video stream of evaluation images.
  • Access authorization includes and/or the evaluation application Access authorization is assigned and/or can be assigned.
  • the access authorization is based, for example, on the origin of the evaluation application and/or the type of evaluation application, for example facial recognition application or application for recognizing license plates.
  • the access authorization describes and/or concerns, for example, an authorization of the evaluation application for detected objects of an object class and/or a scene event and/or can include a definition of authorized object classes and/or authorized scene events.
  • an evaluation application for facial recognition has the access authorization for the authorization to relate detected objects with faces.
  • the detected objects of the authorized object class and/or the authorized scene event are determined to be authorized objects by the removal module, in particular for this evaluation application, so that the removal module does not remove these authorized objects from the input image to generate the cleaned evaluation image.
  • the access authorization or relevant information is transferred to the removal module.
  • the evaluation image with the authorized objects is then provided to the evaluation module with the evaluation application for evaluation.
  • the access authorization or access authorization data is communicated to the removal module and/or the detection module.
  • the captured input images contain a variety of information and also sensitive information. Particularly when the input images are evaluated by a third-party evaluation application, it is difficult for data protection reasons to provide the input images to the evaluation application without protecting the sensitive data. On the other hand, it is difficult for the evaluation application, especially from a third-party provider, to perform a high-quality evaluation if all objects in the input images are removed. For example, facial recognition or license plate recognition is simply not possible. Because the evaluation application is granted access authorization, it can be ensured via the distance module, taking the access authorization into account, that the evaluation application only uses the evaluation image with the detected ones Objects for which the evaluation application is also authorized. This makes it possible to meet data protection requirements and at the same time carry out high-quality evaluations.
  • the evaluation module is provided with metadata which describes which areas in the evaluation image were removed and/or modified by the removal of the unauthorized objects.
  • This metadata can simplify the evaluation of the evaluation application by, for example, ignoring these areas during the evaluation.
  • the access authorization is designed as an authorization certificate, in particular a ticket.
  • the authorization certificate includes an application certificate, in particular specific for the evaluation application.
  • the authorization certificate in particular the application certificate, describes, for example, which authorization the evaluation application has and in particular which detected objects of object classes and/or scene events are to be provided to the evaluation module with the evaluation application.
  • the authorization certificate can, for example, be created and monitored by the manufacturer of the monitoring arrangement, with the manufacturer issuing corresponding authorization certificates to the third-party provider.
  • the detection module and/or the distance module are arranged in the camera.
  • the evaluation module is arranged in a separate peripheral device. This means that not only is the responsibility for the software in the monitoring arrangement shared between the manufacturer and a third-party provider, but the responsibility for the hardware can also be taken over by the manufacturer on the camera side and by a third-party provider on the evaluation application side.
  • the monitoring arrangement has a transmission module, the transmission module being arranged in the camera. Furthermore, the monitoring arrangement has a receiving module, the receiving module being arranged in the peripheral device. A data connection can be established between the receiving module and the transmitting module. For example, the receiving module and the transmitter module are connected to each other via a network (wireless or wired).
  • the transmitting module is designed to provide the evaluation image based on one or the authorization certificate; the evaluation image is provided to the receiving module in a cryptographic and/or encrypted manner based on the authorization certificate.
  • the cryptographic and/or encrypted representation is based on and/or by means of the authorization certificate.
  • the encrypting and/or cartographic provision is based on the authorization certificate and the exchange of keys between the receiving module and the sending module.
  • the detection module has a detection submodule for detecting the objects in the input image as detected objects and an event detection submodule.
  • the event detection submodule can be designed as a hardware module or as a software module. Particularly preferably, the event detection submodule is part of the camera and/or connected directly to the camera.
  • the event detection module is designed to detect objects involved in a scene event as detected objects.
  • the function of detecting the objects in the input image as detected objects in particular through object segmentation and object detection against a static background, and the function of detecting objects involved in a scene event as detected objects are broken down into two different submodules.
  • the detection module or in particular the detection submodule is designed in particular to classify the detected objects into object classes.
  • the object classes can be defined arbitrarily. For example, it is conceivable that an object class is formed by people, non-people, objects, vehicles, pets, etc. In principle, any classification that can be distinguished using digital image processing is possible.
  • the assignment is communicated to the distance module.
  • the object class is communicated to the detection module or the detection submodule about the access authorization.
  • the event detection submodule is designed in particular to detect the events Assign objects to a scene event.
  • the assignment is communicated to the distance module
  • objects which are determined as objects of an object class as unauthorized objects according to the definition of the access authorization of the object classes but are passed on by the removal module as objects of a scene event according to the definition of the access authorization as authorized objects.
  • a person can initially be determined as an unauthorized object. However, if this person is an object of a scene event, e.g. theft, which is an authorized scene event according to the access authorization, this object/person is determined as a possible thief of the scene event as an authorized object.
  • the event detection submodule performs detection based on the input image.
  • the input image has the highest information content, so that particularly good detection results can be expected.
  • the detected objects optionally with the assignment to the scene event, can then be forwarded to the distance module.
  • the event detection submodule can also be designed as a third-party module. This again raises the data protection issue of the correct use of sensitive data in the input image.
  • the event detection submodule carries out the detection based on an intermediate output image, the intermediate output image being generated, for example, by the distance module. In the intermediate output image, at least some objects or object areas are removed by the distance module.
  • the event detection submodule can have a further access authorization in which the authorization for detected objects for the purpose of event detection is defined. In this way, it is possible to also equip an evaluation module close to the camera with such access authorization.
  • the removal module comprises and/or forms a generative adversarial neural network, wherein the generative neural network is designed and/or set up to detect the unauthorized object(s) by means of of the generative neural network and thereby remove it.
  • the generative neural network is in particular designed to replace the unauthorized objects in such a way that they are provided to a user in a distorted form, in particular for further image evaluation and/or analysis, but still essentially have an optical and/or intuitive similarity to the original ones objects.
  • the removal module is designed to implement the removal of the unauthorized objects by replacing them with an object representative.
  • an unauthorized object showing a person's face is replaced by a "sample face" as an object representative and/or a license plate in the input image is replaced by a "sample license plate.”
  • No unauthorized objects are shown in the evaluation image, but content that is intuitively understandable and/or comprehensible for a human user and/or further evaluations.
  • Another subject relates to a method for operating the monitoring arrangement as described above, wherein the evaluation application has access authorization for objects of an object class and/or a scene event, wherein the distance module determines detected objects of the authorized object class and/or the authorized scene event as authorized objects and removes unauthorized objects in the input image.
  • a further subject of the invention relates to a computer program which is designed to carry out the method described above when it runs on a computer, a device, in the cloud and/or on the monitoring arrangement as described above.
  • Another subject of the invention relates to a storage medium with the computer program.
  • Figure 1 is a schematic block representation of a monitoring arrangement as an exemplary embodiment of the invention
  • Figure 2 is a schematic block representation of a monitoring arrangement as a further exemplary embodiment of the invention.
  • Figure 3 shows a schematic block representation of a monitoring arrangement as a further exemplary embodiment of the invention.
  • Figure 4 is a schematic block representation of a monitoring arrangement as a further exemplary embodiment of the invention.
  • FIG. 1 shows a monitoring arrangement 1 as an exemplary embodiment of the invention in a schematic block representation.
  • the monitoring arrangement 1 is used to monitor a monitoring area 2, in particular using digital image processing.
  • the monitoring area 2 can be designed as an open and/or closed area, for example in a building and/or in an open space.
  • the monitoring arrangement 1 has at least or exactly one camera 3, the camera 3 being designed to monitor the monitoring area 2 or a portion thereof.
  • the camera 3 provides an input image 4, wherein the input image can show a scene 5 with at least one object 6, 7, 8, 9.
  • Objects 6, 7, 8, 9 can be assigned to an object class.
  • the object class can relate to objects, such as object 6, vehicles, such as object 7, or people, such as object 8.
  • object 6, 7, 8, 9 can be assigned to a scene event.
  • object 8 shows a scene event in the form of a combination of a person and a dog.
  • Other scene events can also be provided, such as entering a restricted area, the behavior of people in the surveillance images, etc Example of running or fighting, or the burning of a vehicle if the object 7 also shows flames, etc.
  • the monitoring arrangement 1 has a detection module 10, wherein the detection module 10 is designed to detect the at least one object 6, 7, 8, 9 as a detected object based on the input image 4.
  • the detection module 10 is arranged in the camera 3.
  • the monitoring arrangement 1 has a removal module 11, the removal module 11 being designed to remove at least one of the detected objects 6, 9 in the input image 4 in order to generate a cleaned evaluation image 12.
  • the object 6, 7, 8, 9 can be removed, for example, as shown in FIG.
  • object 6 could be replaced by a stylized bucket, object 7 by an image of any vehicle, object 8 by a drawn group of people and dogs, or object 9 by a general image of a flower and thereby removed.
  • the distance module 11 is designed to assign the detected objects 6, 7, 8, 9 to object classes and/or scene events.
  • the distance module 11 can comprise a generative neural network, whereby the respective objects 6, 7, 8, 9 are optionally replaced by an object representative which is generated by the generative neural network.
  • This last-mentioned embodiment means that a human viewer in particular can better perceive the content of the scene 5, although the objects 6, 7, 8, 9 are no longer in their actual form, but are removed and represented by an anonymized art form.
  • the distance module 11 is arranged in the exemplary embodiment in FIG. 1 of the camera 3.
  • the monitoring arrangement 1 has an evaluation module 13, the evaluation module 13 being designed to apply an evaluation application to the evaluation image 12.
  • the evaluation module 13 only receives those objects which have not been removed as authorized objects 7, 8 by the removal module 11.
  • the unauthorized objects 6, 9 have been removed.
  • the evaluation application 13 has an access authorization 14.
  • the access authorization 14 can be formed, for example, as an authorization certificate, with the authorized object classes and/or scene events being defined by the access authorization 14.
  • the access authorization 14 is made accessible to the removal module 11, so that the removal module 11 can classify the detected objects 6, 7, 8, 9 accordingly.
  • This structure makes it possible for evaluation applications from third-party providers to be integrated into the monitoring arrangement 1, with the access authorization 14 ensuring that the evaluation application only receives the data from the input image 4 for which the evaluation application has the access authorization 14.
  • the access authorization 14 ensuring that the evaluation application only receives the data from the input image 4 for which the evaluation application has the access authorization 14.
  • the pixel information of the detected, unauthorized objects 6, 9 for which the evaluation application in the evaluation module 13 is not authorized via the access authorization 14 is removed from the input image.
  • FIG. 2 shows a modified exemplary embodiment of the monitoring arrangement 1, with reference being made to the previous description with regard to the functions of the individual components.
  • the monitoring arrangement has a peripheral device 15, with the evaluation module 13 being arranged in the peripheral device 15.
  • the camera 3 has a transmission module 16, the peripheral device 15 has a reception module 17.
  • a data connection 18, for example via a network, is provided between the transmitting module 16 and the receiving module 17.
  • the evaluation image 12 is routed to the peripheral device 15 and thus to the evaluation module 13 via the data connection 18.
  • the access authorization 14 is also routed to the removal module 11 via a or the data connection 18, so that the corresponding authorizations are present in the removal module 11.
  • the data connection 18 can be cryptographically encrypted for transmitting the evaluation image 12 and/or for transmitting the access authorization 14.
  • the evaluation module 13 and the receiving module 16 can also be arranged in a cloud (not shown) or on a server
  • FIG. 3 shows a further exemplary embodiment of the invention, which has the same apparatus structure as the exemplary embodiment in FIG. 2, so that reference is made to the previous description.
  • the detection module 10 is formed by an event detection module 19 and a detection submodule 20.
  • the event detection submodule 19 is designed to detect the objects 6, 7, 8, 9 as objects of a scene event and to supply the detected objects to the distance module 11.
  • the detection submodule 20 is designed to generally detect objects in the input image 4.
  • the event detection submodule 19 works on the input image 4, i.e. without objects 6, 7, 8, 9 having already been removed.
  • FIG. 4 shows an exemplary embodiment of the invention, wherein the detection submodule 19 first detects the objects 6, 7, 8, 9 as detected objects.
  • the removal module 11 some of the detected objects 6, 7, 8, 9 are already removed and an intermediate output image is formed.
  • This intermediate output image with at least one removed object 6, 7, 8, 9 is fed to the event detection submodule 19 for detecting objects that are assigned to a scene event.
  • the event detection submodule 19 then detects the objects based on the intermediate output image.
  • This exemplary embodiment has the advantage that the event detection submodule 19 can also be provided by a third party, for example, and sensitive data can be protected by removing some or all objects 6, 7, 8, 9.
  • the event detection submodule 19 it is also possible for the event detection submodule 19 to have a corresponding additional access authorization, which defines which objects may be forwarded to the event detection submodule 19 as authorized objects or objects belonging to an authorized object class.

Abstract

L'invention concerne un ensemble de surveillance (1) pour une surveillance basée sur une image d'une région surveillée (2), comprenant une caméra (3), la caméra (3) étant conçue pour fournir au moins une image d'entrée (4), ladite image d'entrée (4) étant capable d'afficher une scène (5) comprenant au moins un objet (6, 7, 8, 9), et le ou les objets (6, 7, 8, 9) pouvant être atffectés à une classe d'objet et/ou à un événement de scène ; un module de détection (10) qui est conçu pour détecter le ou les objets (6, 7, 8, 9) en tant qu'objet détecté sur la base des données d'entrée (4) ; un module de retrait (11) qui est conçu pour identifier le ou les objets détectés (6,7,8, 9) en tant qu'objet autorisé (7, 8) ou en tant qu'objet non autorisé (6, 9) et retirer l'objet non autorisé (6, 9) dans l'image d'entrée (4) afin de générer une image d'analyse corrigée (12) ; et un module d'analyse (13) qui est conçu pour appliquer une application d'analyse à l'image d'analyse (12), ladite application d'analyse ayant une autorisation d'accès (14) qui décrit ou se rapporte à une autorisation pour des objets (6, 7, 8, 9) d'une classe d'objet et/ou d'un événement de scène en tant qu'objets autorisés (7, 8).
PCT/EP2023/057284 2022-03-25 2023-03-22 Ensemble de surveillance avec autorisation d'accès, procédé, programme informatique et support de stockage WO2023180362A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102022202943.7 2022-03-25
DE102022202943.7A DE102022202943A1 (de) 2022-03-25 2022-03-25 Überwachungsanordnung mit Zugriffsberechtigung, Verfahren, Computerprogramm und Speichermedium

Publications (1)

Publication Number Publication Date
WO2023180362A1 true WO2023180362A1 (fr) 2023-09-28

Family

ID=85778881

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2023/057284 WO2023180362A1 (fr) 2022-03-25 2023-03-22 Ensemble de surveillance avec autorisation d'accès, procédé, programme informatique et support de stockage

Country Status (2)

Country Link
DE (1) DE102022202943A1 (fr)
WO (1) WO2023180362A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170039387A1 (en) * 2015-08-03 2017-02-09 Agt International Gmbh Method and system for differentiated privacy protection
US20190018830A1 (en) 2016-03-24 2019-01-17 Alibaba Group Holding Limited Mixed view display method and device
US20210192816A1 (en) * 2018-04-12 2021-06-24 Panasonic Intellectual Property Management Co., Ltd. Video processing device, video processing system, and video processing method
US20210227271A1 (en) * 2020-01-22 2021-07-22 Microsoft Technology Licensing, Llc Privacy-preserving video analytics
US20210383018A1 (en) * 2020-06-09 2021-12-09 Axis Ab Method and device for partially unmasking an object in a video stream

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008007199A1 (de) 2008-02-01 2009-08-06 Robert Bosch Gmbh Maskierungsmodul für ein Videoüberwachungssystem, Verfahren zur Maskierung von selektierten Objekten sowie Computerprogramm
EP3672244B1 (fr) 2018-12-20 2020-10-28 Axis AB Procédés et dispositifs de codage et de décodage d'une séquence de trames d'images dans lesquelles la confidentialité d'un objet est protégée
DE102020203473A1 (de) 2020-03-18 2021-09-23 Robert Bosch Gesellschaft mit beschränkter Haftung Anonymisierungseinrichtung, Überwachungsvorrichtung, Verfahren, Computerprogramm und Speichermedium
DE102020203475A1 (de) 2020-03-18 2021-09-23 Robert Bosch Gesellschaft mit beschränkter Haftung Anonymisierungseinrichtung, Überwachungsvorrichtung, Verfahren, Computerprogramm und Speichermedium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170039387A1 (en) * 2015-08-03 2017-02-09 Agt International Gmbh Method and system for differentiated privacy protection
US20190018830A1 (en) 2016-03-24 2019-01-17 Alibaba Group Holding Limited Mixed view display method and device
US20210192816A1 (en) * 2018-04-12 2021-06-24 Panasonic Intellectual Property Management Co., Ltd. Video processing device, video processing system, and video processing method
US20210227271A1 (en) * 2020-01-22 2021-07-22 Microsoft Technology Licensing, Llc Privacy-preserving video analytics
US20210383018A1 (en) * 2020-06-09 2021-12-09 Axis Ab Method and device for partially unmasking an object in a video stream

Also Published As

Publication number Publication date
DE102022202943A1 (de) 2023-09-28

Similar Documents

Publication Publication Date Title
EP1454285B1 (fr) Systeme de surveillance video avec masquage d'objets
DE102008007199A1 (de) Maskierungsmodul für ein Videoüberwachungssystem, Verfahren zur Maskierung von selektierten Objekten sowie Computerprogramm
DE112012005074T5 (de) Vorrichtung, Verfahren und Programm zum Management privater Informationen
DE112019001879T5 (de) Videoverarbeitungsvorrichtung, videoverarbeitungssystem undvideoverarbeitungsverfahren
DE102022107735A1 (de) Personenbezogene informationen in verschlüsselten datenströmen
DE102018006747A1 (de) Verfahren zur Auswertung von Daten aus einem Fahrzeug
WO2020083732A1 (fr) Module de certification pour données de capteur
DE202018000407U1 (de) Vorrichtung zum Aktualisieren von Gesichtserkennungsvorlagen
DE102020122171A1 (de) Verfahren und System zum kooperativen Sammeln von Videodaten von Fahrtenschreibern
WO2023180362A1 (fr) Ensemble de surveillance avec autorisation d'accès, procédé, programme informatique et support de stockage
DE102020115697A1 (de) Verfahren und Vorrichtung zur natürlichen Gesichtsanonymisierung in Echtzeit
DE102019211089A1 (de) Vorrichtung und Verfahren zum Ergreifen von Gegenmaßnahmen gegen einen unbefugten Zugriff auf ein Fahrzeug
DE102018121110A1 (de) Verfahren und Vorrichtung zur Dokumentation eines Status eines autonomen Roboters
DE102022211513A1 (de) System und Verfahren zum Verarbeiten einer Datensubjekt-Rechteanforderung unter Verwendung von biometrischem Datenabgleich
DE102008018026A1 (de) Verfahren zur Wahrung von Persönlichkeitsrechten bei einer Erfassung von Aufnahmen von Personen
Sultan et al. Metadata based need-to-know view in large-scale video surveillance systems
WO2009124819A1 (fr) Procédé de protection des droits de la personnalité lors de l'acquisition de prises de vue de personnes
WO2023180361A1 (fr) Ensemble de surveillance, procédé de surveillance, programme informatique et support de données
DE102016109125B3 (de) Überwachungs- und Verschlüsselungsverfahren
DE102020004792A1 (de) Verfahren und Vorrichtung zur Erkennung und Meldung von Parkunfällen für Fahrzeuge
EP2462557B1 (fr) Procédé d'analyse vidéo
DE102021122154A1 (de) Bildverarbeitungsvorrichtung, bildverarbeitungsverfahren und bildverarbeitungsprogramm
US20230368629A1 (en) A computer implemented method, apparatus and computer program for privacy masking video surveillance data
DE102019220309A1 (de) Verfahren, Computerprogramm und Vorrichtung zur Verarbeitung von durch ein Fortbewegungsmittel erfassten Sensoraufnahmen
DE102023111269A1 (de) Methoden und systeme zum verwalten personenbezogener daten im zusammenhang mit einer bildverarbeitung

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23713875

Country of ref document: EP

Kind code of ref document: A1