WO2023093977A1 - Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage - Google Patents

Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage Download PDF

Info

Publication number
WO2023093977A1
WO2023093977A1 PCT/EP2021/082748 EP2021082748W WO2023093977A1 WO 2023093977 A1 WO2023093977 A1 WO 2023093977A1 EP 2021082748 W EP2021082748 W EP 2021082748W WO 2023093977 A1 WO2023093977 A1 WO 2023093977A1
Authority
WO
WIPO (PCT)
Prior art keywords
swarm
monitoring devices
monitoring
surveillance system
vector
Prior art date
Application number
PCT/EP2021/082748
Other languages
English (en)
Inventor
Samy NAOUAR
Mark DEN HARTOG
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
Priority to PCT/EP2021/082748 priority Critical patent/WO2023093977A1/fr
Publication of WO2023093977A1 publication Critical patent/WO2023093977A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • 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
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19639—Details of the system layout
    • G08B13/19641—Multiple cameras having overlapping views on a single scene
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19639—Details of the system layout
    • G08B13/19645—Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over

Definitions

  • the invention concerns a method for managing a surveillance system, wherein the surveillance system comprises a plurality of monitoring devices.
  • Interconnected devices are widely used in different technigue fields and often summarised as industry 4.0.
  • the devices are connected wireless or cable based. With increasing number of interconnected devices, it becomes increasingly difficult and time consuming to perform system administrative tasks manually.
  • the current way to manage the growing number of devices in a network is to assign every device to one or more virtual group. Usually these groups can be nested by creating a hierarchical directive group of groups and devices. Each level of abstraction ads removes and/or modifies some aspects of system administration.
  • the document DE 10 2018 203 179 A1 discloses a device for surveillance and management of a plurality machines with a communication unit in order to communicate with the machines.
  • a processing unit is configured to provide signals based on swarm information.
  • the invention concerns a method for managing a surveillance system with the features of claim 1 . Furthermore, the invention concerns a surveillance system, a computer program and a storage medium with the computer program. Preferred and advantages embodiments are described in the sub claims, the description and the figures.
  • the invention describes a method for managing a surveillance system.
  • the method is especially adapted and/or configured for software implementation and/or running on the surveillance system and/orthe devices of the surveillance system.
  • the method is especially configured for organising, structuring and/or ordering the components of the surveillance system.
  • the surveillance system comprises a plurality of monitoring devices.
  • the monitoring devices are for example adapted and/or configured as cameras.
  • the monitoring device may comprise and/or are adapted as sensors, microphones and/or devices to capture information’s and/or measurements.
  • the surveillance system comprises at least 10, preferably at least 50 and especially at least 500 monitoring devices.
  • the monitoring devices of the surveillance system are interconnected, for example interconnected using Wi-Fi, Bluetooth and/or optical communication.
  • the monitoring devices are preferably forming and/or building a network.
  • the monitoring devices are adapted and/or configured to exchange information, messages and/or data.
  • the state feature vector comprises a plurality of components.
  • the state feature vector is especially to be understood as an abstract vector and not as a geometrical vector.
  • the state feature vectors of the different monitoring devices are build and/or structured in the same way, for example same components at same positions.
  • the components of the state feature vector comprise at least one device parameter of the monitoring device, device information for the monitoring device and/or a component explanation for a component of the state feature vector.
  • a swarm is defined, determined or generated.
  • the swarm comprises a subset of the plurality of monitoring devices, especially a subset of more than one monitoring devices.
  • the swarm is defined, determined and/or generated based on a swarm specification, wherein the swarm specification is specific for each swarm.
  • the swarm specification comprises and/or includes a subset of the vector components and/or a subset of vector components defined with specific values and/or configuration. With other words, the swarm specification chooses some components of the state feature vectors to check if specific requirements and/or values are met.
  • a deviation also called distance, between its vector components and the equivalent swarm specification is determined.
  • the deviation is determined as the difference of the component of the state feature vector and the value of the equivalent swarm specification.
  • the swarm specification includes as a vector component of a position, wherein as deviation between the vector components defining the position of the state feature vector and the swarm specification is determined.
  • the deviation is a number.
  • Monitoring devices having a deviation less than a threshold are added to the swarm.
  • the threshold is for example user defended. Especially the threshold is specific for the swarm and/or the vector components. Monitoring devices having a deviation equal or greater than the threshold are not edit to this swarm and/or are removed from this swarm.
  • the invention proposes a framework for dynamically grouping of interconnected monitoring devices in a large network, based on non-hirachieal, context-specific criteria.
  • assigning a state feature vector to each of the monitoring devices the swarm can be easily determined and/or generated.
  • These swarms can used for interactions with human stakeholders like system administrators.
  • the swarm can act and/or can be used as device independent network application.
  • the state feature vector comprises the monitoring device's location, pose and/or orientation, e.g. of a monitoring device adapted as a camera.
  • the location is preferably a 3D-position.
  • the state feature vector comprises as a component a current field of view, wherein the monitoring device is for example a camera.
  • the current field of view of a monitoring device can be defined as the area or volume it can imagine.
  • the current field of view may comprise information of parts and/or objects to remove.
  • the state feature vector comprises preferably as a component the monitoring device's current time, for example to use it for time synchronization of the devices.
  • the state feature vector comprises as a component and/or components the current image and/or videos captured by the monitoring device and/or the captured sensor data.
  • the monitoring device is configured to analyse the data, images, and/or videos captured by the monitoring device, wherein the state feature vector for example comprises a feature vector of the objects that are currently being tracked by the monitoring device.
  • the state feature vector may also comprise as component a number of persons, objects and/or events in the field of view, sensor information’s, like temperature or audio files and/or additional technical data.
  • the swarm specification comprise a geolocation, especially as a swarm locus.
  • the geolocation is preferably a coordinate, especially a 3D coordinate.
  • the geolocation is the location within a building, for example given as floor and room number.
  • the geolocation may be in a preferred embodiment an object or event, especially its position.
  • a dynamic object for example a tracked person or object, gives the geolocation.
  • the geolocation may be a dynamic location.
  • the swarm locus is especially adapted to define the local position of the swarm and/or an area for the swarm.
  • the swarm specification comprise a brand of manufacturer of the device, a firm version of the device, security patterns of the device, e.g. missed attempts for Login, information of a direct line of sight to an area object or position and/or a strength of Wi-Fi-Signal.
  • the deviation is a determined as a distance, determined based on a metric and/or based on a norm.
  • a distance measure is needed for determining which devices are part of the swarm, e.g. are inside the field of influence or inside the swarm value.
  • the distance, metric and/or norm is for example a function that takes the state feature vector, especially the geolocation and the equivalent subset of the swarm specification, as an input and outputs for example a positive or zero value. This output may be used for comparison with a threshold value, for example to check, if the distance is larger or smaller than the threshold value.
  • the distance function could be any function, especially with the property of giving an output with the positive or zero value.
  • distance function a distance measure like currently used in maths or computer signs could be used, for example the Euclidean distance or the L-Infinity norm.
  • the distance function can also simply inforce that parameter values are in a certain range of a swarm locus parameter. E.g., assigning zero-distance if all components or parameters are within the range and infinity if they are not in the range can be used as distance function, norm or metric.
  • the distance especially the distance function, may contain additionally stochastic elements, that make the distance measure less deterministic.
  • the monitoring devices are able and/or configured the participate in more than one swarm, for example to participate in two, three or more swarms in parallel.
  • the monitoring devices are configured to participate in a limited number of swarms, for example to participate max six or ten swarms.
  • each device is adapted with a counter which may be used to inform the system and/or other devices if they can or can't still participate another swarm. If a device should participate another swarm, but the limited number of swarms is already reached, the device has to be removed from a swarm before the device can join the new swarm.
  • the swarm is generated, configured and/or acting as a virtual device in the network.
  • the group of devices inside the swarm can managed, configured and/or used together as the virtual device.
  • a message, configuration and/or action can be send and/or used to the virtual device, wherein preferably the message and/or the actions are transmitted to all devices inside the swarm and/or inside the virtual device.
  • the swarm vector comprises components, especially comprises features of the swarm, a priority of the swarm and/or state information of the swarm.
  • the swarm vector may be used to see the swarm as a device, especially as the virtual device. For instance, the swarm could be given a unique identification by using the swarm vector in order to make it easier to track the swarm.
  • the priority within the swarm vector allows a swarm to get precedence over other swarms when asking for a network resource.
  • the components e.g.
  • the swarm parameters, of the swarm vector can be linked to parameter of the monitoring devices, for example as top-down, especially forthe swarm to influence the monitoring devices state.
  • the swarm vector implies that these devices are allowed to intercommunicate.
  • bottom-up for the components of the swarm vectors and the parameters of the device is disclosed, wherein for example the state of the monitoring devices dictate and/or influence the swarm parameter.
  • An example is object tracking, where all individual swarm devices are used to aggregate the detections of the monitoring devices to predict the objects current location and/or trajectories.
  • the swarm vector, the swarm participants, the swarm specification and/or additional information of the swarm are stored centrally. E.g., on a server or a cloud, alternatively and/or additionally they are stored in at least one of the monitoring devices, preferably on the monitoring devices that are participating the swarm and/or they are stored in all monitoring devices of the network.
  • At least one swarm host is defined and/or determined for the swarm.
  • the swarm host is adapted and/or configured as one of the monitoring devices of the swarm.
  • the monitoring device which is next to the swarm locus is determined and/or chosen as the swarm host.
  • the monitoring device with the largest storage or processing resources is chosen and/or determined as the swarm host.
  • the swarm host is for example configured for managing the communication between the swarm and other network devices and/or within the network.
  • the swarm host is for example for configuring and/or managing the devices within the swarm.
  • the method is configured for generating, publishing and/or providing a swarm event to the network, other devices and/or external use.
  • the swarm event is for example the creation of a new swarm, the destruction of a swarm, a change within a swarm, for example adding or removing a monitoring device.
  • the swarm event is for example to give the network and/or participants in the network an overview of the swarm and/or the arrangement of the monitoring devices, e.g. the assigning of devices to swarms.
  • a further object of the invention is a surveillance system, wherein the surveillance system is adapted and/or configured for executing and/or implementing the method for managing the surveillance system.
  • the surveillance system comprises a plurality of monitoring devices, for example a plurality of cameras as monitoring devices.
  • the monitoring devices are interconnected and/or forming a network.
  • the surveillance system comprises a configuration module, wherein the configuration module is for example a software module or a hardware module.
  • the configuration module is part of a central device, e.g. a server or a cloud.
  • the configuration module is comprised by at least one or all monitoring devices.
  • the configuration module is adapted and/or configured to define, determine or generate a swarm comprising a subset of the monitoring devices.
  • Each of the monitoring devices comprises a state feature vector and/or to each of the monitoring devices a state feature vector is assigned.
  • the configuration module is configured and/or adapted to define, determine or generate the swarm based on a swarm specification, wherein the swarm specification comprises a subset of vector components and/or equivalent components to the vector components of the state feature vector.
  • the configuration module is configured and/or adapted to add the monitoring devices having a deviation less than a threshold to the swarm and/or to remove monitoring devices having a deviation larger or equal than the threshold from the swarm.
  • the deviation is especially determined and/or calculated by the configuration module, wherein the deviation is a deviation between vector components of the state feature vector of the monitoring device and equivalent components of the swarm specification.
  • a further subject of the invention is a computer program, wherein the computer program is adapted and/or configured to be executed on the computer or the monitoring system.
  • the computer program is adapted and/or configured to run, execute and/or implement the method for managing the surveillance system.
  • a further subject of the invention is a storage medium, especially a machine readable and/or computer readable storage medium, wherein the computer program is stored on the storage medium.
  • Figure 1 an example of a surveillance system
  • Figure 2 grouping of monitoring devices into a plurality of swarms
  • Figure 3 a functionally layered surveillance system
  • Figure 4 an example of a dynamic swarm
  • FIG. 1 shows an example of the surveillance system.
  • the surveillance system is adapted and/or configured for surveillance and/or monitoring of a surveillance area 1 , for example rooms 2a, b, and c of the building.
  • the surveillance system comprises a plurality of monitoring devices 3.
  • the monitoring devices 3 are adapted and/or comprising cameras for capturing pictures, images and/or videos.
  • the monitoring devices 3 are interconnected, especially for a data exchange.
  • the interconnected monitoring devices 3 form a network and/or are part of a network. In order to monitor an event, object or and specific part of the surveillance area 1 , for example the room 2a, it is useful to group the monitoring devices 3 into a swarm 4.
  • the surveillance system is adapted and/or configured to assign a state feature vector to each monitoring device 3.
  • the surveillance system uses a swarm specification and the state feature vector to define, create and/or destruct a swarm 4 of monitoring devices 3.
  • the surveillance system uses a method for managing a surveillance system, which is adapted and/or configured for dynamically grouping interconnected monitoring devices 3 in a large network, based on non-hierarchical, context specific criteria, without the need of a central authority. This is achieved by assigning additional unique, context specific properties and features to each of these groupings and thus allowing the groupings to have life cycles independent of the constituent devices.
  • the groupings are called swarms 4 and become effectively autonomous virtual devices themselves. These swarms 4 makes interaction with human stakeholders (endusers, system administrators, installers, programmers, etc.) more natural and allow for the implementation of complex, distributed, mutli-device, network applications.
  • the monitoring device 3 is for example a camera or more generally defined as the smallest semantically autonomous entity (physical or virtual) consisting of multiple sensors/actuators, a central computer and optional additional dedicated hardware to accelerate computations.
  • Each device 3 is connected to a common network allowing, in principle, exchange of information with all other monitoring devices 3 connected to the same network.
  • Each monitoring device 3 is able to summarize and communicate its state using a finite set of parameters called a state feature vector.
  • This state feature vector can contain any information the monitoring device 3 deems relevant, as long as the other monitoring devices 3 are able to interpreted the semantical meaning of its parameters. The latter does not imply that the state feature vector structure should be limited to some known common data model, merely that an interpretation can be provided, either by attaching the interpretation to each instance of the state feature vector or providing this information upon request by providing a service API.
  • elements also called component of a state feature vector a monitoring device 3 could be: monitoring device’s 3 current location, pose, field of view (i.e. the frustrum/volume it can image, possible with parts removed, due to occlusions); the current time; a feature vector of the objects that are currently being tracked; the number of persons in the field of view; additional sensorial information; like current temperature, and/or additional technical meta data like the devices model and current firmware version.
  • a swarm specification is set, wherein the swarm specification is adapted and/or configured as specific subset of chosen parameter, wherein these parameters is given an initial value.
  • This swarm specification defines and/or comprises a swarm locus.
  • a swarm locus could choose as subset all parameters related to the geolocation state of the monitoring device 3. This is no more or less that a specific point in space as the swarm locus.
  • a test for swarm membership is executed.
  • a distance measure is needed, the ‘swarm distance’. This is especially a function that takes the swam locus or the swarm specification and the equivalent subset from the target device’s state feature vector as input and outputs a positive (or zero) value. If the ‘swarm distance’ is less or equal to one, the monitoring device 3 becomes member of the swarm 4, if the distance is larger than one, it is either rejected for swam membership, or its membership is revoked.
  • a swam 4 might be defined by geolocation parameters and initialized by the location of a detected object (the swarm locus).
  • the swarm distance function As the Euclidean distance, divided by 10 meter, all devices in the swarm volume (i.e. all devices within a sphere of 10 meters around the object) will be found.
  • Another example is a swam 4 consisting of all monitoring devices 3 that have a certain brand and firmware version in a building.
  • the swarm locus is the combination of brand, the firmware version and the device’s 3 geolocation.
  • the distance measure now checks if all parameters are within range. This would allow selecting all devices 3 allegeable for update upgrade.
  • swam 4 consisting of all parameters that indicates specific network security related patterns, such as logon attempts, connection failures, most frequently used destination IP address, etc.. If a known network attacks can characterized by specific combination/values of these parameters, this will define the swarm locus. The distance measure is how similar the observer patterns are to a given pattern. This allows the identification of all monitoring devices 3 involved in some network attack.
  • a swarm 4 consisting of all monitoring devices 3 are adapted as cameras and having a direct line of site to a sensitive location, allowing to enforce restrictive policies to the who is allowed to access the data streams of swarm devices 3.
  • the swarm locus is now a position in space, and the distance measure the direction cameras are pointing to.
  • Another example might be a swarm 4 with all monitoring device 3 with the highest Wi-Fi signal strengths as measured by a mobile device 3 (swam locus).
  • Figure 2 shows an example of grouping monitoring devices 3 into swarms 4. Once a swarm 4 is defined, it can be generated and destroyed dynamically and have additional properties detached from the individual devices 3. These emergent properties together with the swarm specification and the distance measure can itself be seen as a swarm vector, allowing them to be seen as devices themselves. For instance, a swarm 4 could be given a unique identification, making them easier to track.
  • the surveillance system of figure 2 comprises the monitoring devices 3a-p, wherein the monitoring devices 3a-p are grouped into swarms 4a-e.
  • Monitoring devices 3a-p may be part of one or more swarms 4.
  • Some swarm 4 may demand exclusivity, either full or partly, or priority by tweaking their distance measures.
  • monitoring device 3g is part of swarm 4f and might alter its state in such a way that the distance to swarm 4d becomes larger than one, forcing it to give-up its membership of swarm 4f.
  • the state feature vector could explicitly contain a mutual exclusivity Boolean parameter for the given swam type(s).
  • Another example how to use the distances dynamically is in the case of a monitoring device 3 adapted as a moving camera currently tracking an object. It will than penalizing new ‘object tracking swarm membership’ request when an new object gets in its vicinity, by inflating the ‘distances’ to the new swarm locus and/or swarm specification. This would allow the monitoring device 3 to switch object, providing the priority of the new object is high enough (i.e. it distance measure make is). For instance, the distance measure for tracking of lost luggage at an airport might have be less aggressive than the distance measure for tracking terrorists. The distance measure could also have hysteresis, where the distance for acquiring membership is different than loosing memberships.
  • a Swarm 4 may be defined statically, which is particularly suitable for decomposing security risk scenarios, based for instance on a specific environment e.g. stadium, airports.
  • FIG 3 illustrates a layered security installation, in such a way that multiple swarms 4a, b, c allow very different security applications and policies to coexist and collaborate.
  • Monitoring devices 3 belonging to any given swarm 4 are able to share, application-level knowledge e.g. computer vision feature vectors, video frames, geo-location coordinates, system properties, security policy characteristics.
  • application-level knowledge e.g. computer vision feature vectors, video frames, geo-location coordinates, system properties, security policy characteristics.
  • swarm 4a is configured for running area intrusion detection applications
  • swarm 4b is configured for running face recognition applications
  • swarm 4c is configured for running tracking applications e.g. Pan, Tilt, Zoom.
  • FIG. 4 shows an example of a dynamically defined swarm 4.
  • Dynamic swarms 4 are particularly suitable for tracking use-cases.
  • the swarm 4 is constantly being updated according to a specific target’s geo-location.
  • the surveillance system comprises monitoring devices 3a-p, wherein the swarm 4 is constantly being updated according to a given target’s geolocation.
  • tracking swarm 4 comprises the monitoring devices 3k, I, o, p.
  • all monitoring devices 3 which belong the tracking swarm 4 set to dynamically share a target’s geolocation coordinates information regarding.
  • Especially the set of monitoring devices 3 in the swarm 4 can overlap (Sets can intersect), inflate/shrink (Total number of monitoring devices 3 can be increased/decreased.
  • tracking swarm 4 can include second order in addition to first order elements), split (Big set into several smaller sets) and/or aggregated (sets can be joined up).

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

L'invention concerne un procédé de gestion d'un système de surveillance, le système de surveillance comprenant une pluralité de dispositifs de surveillance (3), la pluralité de dispositifs de surveillance (3) étant interconnectés et/ou formant un réseau, un vecteur de caractéristiques d'état étant attribué à chacun des dispositifs de surveillance (3), le vecteur de caractéristiques d'état comprenant des composantes de vecteur, les composantes de vecteur comprenant un paramètre de dispositif, des informations de dispositif et/ou une explication de composant, un essaim (4) comprenant un sous-ensemble des dispositifs de surveillance (3) étant défini, déterminé et/ou généré sur la base d'une spécification d'essaim, la spécification d'essaim comprenant un sous-ensemble spécifique des composants de vecteur ; pour chaque dispositif de surveillance (3), un écart entre la spécification d'essaim et ses composantes vectorielles équivalentes étant déterminé, des dispositifs de surveillance (3) avec un écart inférieur à un seuil étant ajoutés à l'essaim (4), des dispositifs de surveillance (3) ayant un écart supérieur au seuil n'étant pas ajoutés à l'essaim (4) et/ou sont retirés de l'essaim (4).
PCT/EP2021/082748 2021-11-24 2021-11-24 Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage WO2023093977A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2021/082748 WO2023093977A1 (fr) 2021-11-24 2021-11-24 Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2021/082748 WO2023093977A1 (fr) 2021-11-24 2021-11-24 Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage

Publications (1)

Publication Number Publication Date
WO2023093977A1 true WO2023093977A1 (fr) 2023-06-01

Family

ID=78822165

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2021/082748 WO2023093977A1 (fr) 2021-11-24 2021-11-24 Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage

Country Status (1)

Country Link
WO (1) WO2023093977A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040030451A1 (en) * 2002-04-22 2004-02-12 Neal Solomon Methods and apparatus for decision making of system of mobile robotic vehicles
DE102018203179A1 (de) 2018-03-02 2019-09-05 Robert Bosch Gmbh Vorrichtung, insbesondere Handwerkzeugmaschinen-Verwaltungsvorrichtung, und Verfahren zur Überwachung und/oder zur Verwaltung einer Vielzahl von Gegenständen
US20200220887A1 (en) * 2019-01-04 2020-07-09 Samsung Electronics Co., Ltd. Method and apparatus for organizing and detecting swarms in a network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040030451A1 (en) * 2002-04-22 2004-02-12 Neal Solomon Methods and apparatus for decision making of system of mobile robotic vehicles
DE102018203179A1 (de) 2018-03-02 2019-09-05 Robert Bosch Gmbh Vorrichtung, insbesondere Handwerkzeugmaschinen-Verwaltungsvorrichtung, und Verfahren zur Überwachung und/oder zur Verwaltung einer Vielzahl von Gegenständen
US20200220887A1 (en) * 2019-01-04 2020-07-09 Samsung Electronics Co., Ltd. Method and apparatus for organizing and detecting swarms in a network

Similar Documents

Publication Publication Date Title
Munishwar et al. Coverage algorithms for visual sensor networks
US20220101012A1 (en) Automated Proximity Discovery of Networked Cameras
Piciarelli et al. Dynamic reconfiguration in camera networks: A short survey
SanMiguel et al. Self-reconfigurable smart camera networks
Dautov et al. Stream processing on clustered edge devices
JPWO2006067947A1 (ja) カメラ端末および監視システム
US10834198B2 (en) Edge side dynamic response with context propagation for IoT
RU2554102C2 (ru) Распределенная архитектура системы видеомониторинга леса
KR102344606B1 (ko) 추적 감시 cctv 시스템 및 추적 감시 방법
Nene et al. Algorithm for autonomous reorganization of mobile wireless camera sensor networks to improve coverage
Munishwar et al. Coverage in visual sensor networks with Pan-Tilt-Zoom cameras: The MaxFoV problem
Karakaya et al. Distributed target localization using a progressive certainty map in visual sensor networks
Irfan et al. Crowd analysis using visual and non-visual sensors, a survey
JP2018093401A (ja) 映像監視装置、映像監視方法および映像監視システム
Del Bimbo et al. Towards on-line saccade planning for high-resolution image sensing
WO2023093977A1 (fr) Procédé de gestion d'un système de surveillance, système de surveillance, programme informatique et support de stockage
Dautov et al. Towards a global intelligent surveillance system
Chemodanov et al. Fog Computing to Enable Geospatial Video Analytics for Disaster‐incident Situational Awareness
Del Bimbo et al. Distant targets identification as an on-line dynamic vehicle routing problem using an active-zooming camera
Gui et al. Full-view barrier coverage with rotatable camera sensors
US10152548B2 (en) Locating mobile users
Weerakoon et al. Resilient collaborative intelligence for adversarial IoT environments
Mihailescu et al. A survey and taxonomy on intelligent surveillance from a system perspective
Munishwar et al. Target-oriented coverage maximization in visual sensor networks
KR20220004399A (ko) 사용자 참여형 보안 감시 관제 서비스 제공 프로그램 기록매체

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: 21819791

Country of ref document: EP

Kind code of ref document: A1