EP3499473A1 - Détection automatisée de situations dangereuses - Google Patents

Détection automatisée de situations dangereuses Download PDF

Info

Publication number
EP3499473A1
EP3499473A1 EP18211299.5A EP18211299A EP3499473A1 EP 3499473 A1 EP3499473 A1 EP 3499473A1 EP 18211299 A EP18211299 A EP 18211299A EP 3499473 A1 EP3499473 A1 EP 3499473A1
Authority
EP
European Patent Office
Prior art keywords
dangerous situation
alarm
optical flow
unit
ofd
Prior art date
Legal status (The legal status 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 status listed.)
Withdrawn
Application number
EP18211299.5A
Other languages
German (de)
English (en)
Inventor
Andreas Heiko Schmidt
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens Mobility GmbH
Original Assignee
Siemens Mobility 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 Siemens Mobility GmbH filed Critical Siemens Mobility GmbH
Publication of EP3499473A1 publication Critical patent/EP3499473A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • 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
    • G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion

Definitions

  • the invention relates to a method for automated detection of a dangerous situation in a surveillance area.
  • characteristic movement patterns are recognized in video or image material.
  • the invention relates to an alerting method.
  • the invention relates to a monitoring system.
  • the invention relates to an alarm system.
  • the invention also relates to a passenger transport vehicle.
  • Video data is used for evidence and for purposes of investigation and for real-time monitoring.
  • an automated monitoring is increasingly used.
  • emergency situations such as violent crimes, can usually only be documented retrospectively, whereas alerting and timely intervention to save the potential victim is often not possible.
  • An approach to automated surveillance in public space using video data is aimed at detecting specific patterns of movement of persons who may be associated with hazardous situations.
  • Special requirements are the hazard detection in trains and buses.
  • For here there is the problem of delimiting the movement pattern of persons attributable to dangerous situations from movement patterns produced by the movement of the vehicles themselves, which are caused by light, shadow and the surroundings.
  • This object is achieved by a method for automated detection of a dangerous situation in a surveillance area according to claim 1, an alerting method according to claim 6, a surveillance system according to claim 8, an alarm system according to claim 9 and a passenger transport vehicle according to claim 10.
  • video data is continuously detected by the surveillance area. Then the video data is converted to optical flow data.
  • the optical flow data represent the optical flow of an image sequence of temporally successive frames, which are obtained from the recorded video data.
  • the optical flux comprises a vector field of the velocity of visible points of the object space projected into the image plane in the reference system of the imaging optics of the image acquisition unit used.
  • vectors are generated via the position difference of prominent points from the image sequence or image sequence. These vectors represent a direction of movement and a step size.
  • a classifier trained on the basis of relevant movement patterns is applied to the optical flow data in real time. The classifier comprises the definition of the movement patterns to be recognized.
  • the shape of the classifier depends on the type of training method and may include, for example, vector matrices.
  • the training of the classifier can preferably take place with the aid of reference image data, which are assigned to different situations, including specific dangerous situations, and which comprise the relevant movement patterns characterizing the respectively assigned situations.
  • the classifier is therefore the result of an applied training process.
  • the "relevant" movement patterns comprise movement patterns that are associated with typical movements that are correlated with specific situations, in particular dangerous situations. Finally, it is determined on the basis of a classification result whether a dangerous situation exists.
  • a type of dangerous situation can also be determined on the basis of the classification result.
  • Hazardous situations can advantageously be detected in a much more reliable automated manner in real time and in comparison to conventional approaches. Due to the real-time detection, it may be possible to intervene in good time by suitably provided auxiliary personnel, before a person gets hurt. If a specific type of dangerous situation is also detected, it is possible to target suitably suitable personnel who can react particularly effectively to the specific danger situation. Due to the higher reliability of the method, the number of false alarms can be reduced.
  • the process steps of image acquisition, data conversion, classification and hazard identification are advantageously carried out automatically, so that no personnel is required for hazard identification.
  • the method can be used particularly advantageously for hazard detection in public areas, such as in trains or buses, in which due to the complexity of a hazard detection by personnel is difficult or at least very complex.
  • the method according to the invention for automatically detecting a dangerous situation in a monitoring area is first of all carried out.
  • an automated triggering of an alarm occurs in the event that a dangerous situation has been detected.
  • the manner of the alarm and the assistants addressed by the alarm may depend on the recognition result.
  • an alarm for example, an optical or acoustic signal, in the simplest case, a signal light can be generated, which confirms the victim that the alarm has taken place, and causes a possibly existing offender to abort his act, as this monitoring by a monitoring system and the triggering of the alarm is clarified.
  • the alerting method shares the advantages of the method according to the invention for the automated detection of a dangerous situation in a surveillance area.
  • the monitoring system according to the invention comprises a video recording unit for continuously acquiring video data from a surveillance area.
  • Part of the monitoring system according to the invention is a conversion unit for converting the video data into optical flow data.
  • the monitoring system comprises a classification unit which is set up to apply a classifier trained on the basis of relevant movement patterns to the optical flow data in real time.
  • Part of the monitoring system according to the invention is also a hazard determination unit for determining a dangerous situation on the basis of a classification result.
  • the monitoring system according to the invention shares the advantages of the method according to the invention for the automated detection of a dangerous situation in a monitoring area.
  • the alarm system according to the invention comprises the monitoring system according to the invention as well as an alarm unit for the automated triggering of an alarm as a function of a danger situation detected by the monitoring system.
  • the alarm system according to the invention shares the advantages of the monitoring system according to the invention.
  • the passenger transport vehicle according to the invention comprises the alarm system according to the invention.
  • the detection of danger in the passenger transport vehicle according to the invention is automated and in real time, so that timely countermeasures can be initiated.
  • Some components of the monitoring system according to the invention may be designed, possibly after supplementing certain hardware elements, such as a video camera, for the most part in the form of software components. This applies in particular to parts of the conversion unit, the classification unit and the hazard determination unit.
  • these components can also be partly, in particular when it comes to very fast calculations, in the form of software-supported hardware, for example FPGAs or the like, be realized.
  • the required interfaces for example, if it is only about a transfer of data from other software components, be designed as software interfaces.
  • they can also be configured as hardware-based interfaces, which are controlled by suitable software.
  • a largely software-based implementation has the advantage that already existing computer systems for monitoring an area can be retrofitted in a simple manner by means of a software update in order to work in the manner according to the invention.
  • the object is also achieved by a corresponding computer program product with a computer program which can be loaded directly into a memory device of such a computer system, with program sections to execute all the steps of the method according to the invention when the computer program is executed in the computer system.
  • Such a computer program product may contain, in addition to the computer program, additional components, e.g. a documentation and / or additional components, also hardware components, such as e.g. Hardware keys (dongles, etc.) for using the software include
  • a computer-readable medium for example a memory stick, a hard disk or other transportable or permanently installed data carrier may be used, on which the computer program readable and executable program sections of a computer system are stored.
  • the computer system may e.g. for this purpose have one or more cooperating microprocessors or the like.
  • a recognizer using a classifier is trained, which is subsequently able to recognize corresponding patterns.
  • a recognizer is a program or library that uses the classifier to detect relevant patterns of movement.
  • the classifier can be flexibly adapted to individual application areas without being fixed to a rigid, computationally expensive model.
  • the automated learning method comprises a machine learning method.
  • Such machine learning methods can be used to train motion pattern recognition classification methods. Examples of classification methods for movement pattern recognition are svm or Haarcascade use.
  • the method svm support vector machine is a mathematical method for pattern recognition based on vector matrices.
  • Hair cascade includes an image extraction method, also called hair feature method, which includes abstraction patterns, so-called Haar wavelets, with which images are decomposed into individual parts and are resolved differently.
  • the automated learning method may also include a deep learning method, which is considered to be a special case of machine learning.
  • Deep learning refers to a class of optimization methods based on the application of neural networks.
  • the neural networks used in this case comprise numerous intermediate layers between the input layer and the output layer and thus have an internal structure. Deep Learning can process a larger amount of basic data with the support of potent hardware and procedures than with simpler approaches.
  • FIG. 1 a flowchart 100 is shown which describes a method for automated detection of a hazardous situation.
  • the surveillance area UB may include the compartment of a train in which passengers are staying for a certain time.
  • step 1.I video data VD is continuously detected by the monitoring area ÜB.
  • the captured video data VD is converted into optical flow data OFD in step 1.II.
  • step 1.III a classifier K trained on the basis of relevant movement patterns is applied to the optical flow data OFD in real time.
  • step 1.IV it is then determined whether a dangerous situation GS exists and, if so, what kind of dangerous situation is. This determination is based on a classification result KE. In the event that it was determined in step 1.IV that a dangerous situation GS exists, which is in FIG. 1 is marked with "j", then it goes to step 1.V, in which an alarm is triggered by competent authorities.
  • the alarm message AL to an auxiliary team or auxiliary instance such as the police or private security services, are transmitted, which can provide timely assistance to the person concerned. If no dangerous situation GS has been determined in step 1.IV, which is marked with "n", then the process moves to step 1.I and the monitoring process is continued in real time.
  • FIG. 2 a flowchart 200 is shown which illustrates method steps for training a classifier K.
  • the steps mentioned can be carried out, for example, in advance of a deployment of the in FIG. 1 illustrated method taking into account the specific application area or a known monitoring area.
  • step 2.I first video data VD B are read in with exemplary movement patterns which are assigned to a known dangerous situation GS.
  • the video data VD B are converted to optical flow data OFD B in step 2.II.
  • the classifier K is trained by means of an automated learning method on the basis of the optical flow data OFD B provided with exemplary movement patterns.
  • FIG. 3 a block diagram is shown which illustrates an alarm system 1 with a monitoring system 10 according to an embodiment of the invention.
  • Part of the alarm system 1 is in addition to the mentioned monitoring system 10 and an alarm unit 15, can be set with the auxiliary forces of a dangerous situation GS in a monitoring area ÜB in knowledge.
  • the monitoring system 10 further comprises a video capture unit 11 with a video camera which serves to continuously record video data VD from the surveillance area UB.
  • the video data VD is forwarded to a conversion unit 12, which converts the received video data VD into optical flow data OFD.
  • the optical flow data OFD are transmitted to a classification unit 13 which applies a classifier K trained on the basis of relevant movement patterns to the optical flow data OFD in real time and optionally assigns the optical flow data OFD to predetermined movement patterns.
  • the classification result KE is then forwarded to a hazard determination unit 14 which, based on the classification result KE, optionally determines a dangerous situation GS.
  • this message is forwarded to the alerting unit 15, which, as already mentioned, alerts suitable assistants.
  • the monitoring system 10 also comprises units 16, 17, 18 for training the classifiers K used in the classification unit 13.
  • a training database 16 provides exemplary video data VD B in the context of a training process, for which the classification results KE R are known.
  • the exemplary video data VD B are forwarded to the conversion unit 12 as part of the training process.
  • the conversion unit 12 converts the exemplary video data VD B into exemplary optical flow data OFD B.
  • the exemplary optical flow data OFD B are subsequently classified by the classification unit 13 and the classification result KE is transmitted to a comparison unit 17.
  • the comparison unit 17 compares the classification result KE with a reference classification result KE R made available by the training database 16 and determines a comparison result VE.
  • a correction unit 18 carries out a correction of the classifier K and transmits the changed classifier K to the classification unit 13.
  • the training process can now be continued with the new classifier K and the process can be aborted, for example, if the classification result KE deviates from the corresponding reference quantity KE R only by a predetermined threshold size.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Alarm Systems (AREA)
EP18211299.5A 2017-12-15 2018-12-10 Détection automatisée de situations dangereuses Withdrawn EP3499473A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102017222898.9A DE102017222898A1 (de) 2017-12-15 2017-12-15 Automatisiertes Detektieren von Gefahrensituationen

Publications (1)

Publication Number Publication Date
EP3499473A1 true EP3499473A1 (fr) 2019-06-19

Family

ID=64664136

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18211299.5A Withdrawn EP3499473A1 (fr) 2017-12-15 2018-12-10 Détection automatisée de situations dangereuses

Country Status (2)

Country Link
EP (1) EP3499473A1 (fr)
DE (1) DE102017222898A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3101827A1 (fr) * 2019-10-15 2021-04-16 Transdev Group Innovation Dispositif électronique et procédé de génération d’un signal d’alerte, système de transport et programme d’ordinateur associés
CN113591711A (zh) * 2021-07-30 2021-11-02 沭阳县华源米业股份有限公司 一种基于人工智能的粮仓危险源安全监测方法及系统
EP4112420A1 (fr) * 2021-07-01 2023-01-04 Siemens Mobility GmbH Procédé de détection d'un événement relatif à la sécurité à l'intérieur d'une cabine de passagers d'un véhicule ferroviaire

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021206618A1 (de) 2021-06-25 2022-12-29 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zur Erhöhung der Erkennungsgenauigkeit eines Überwachungssystems

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060045354A1 (en) * 2004-07-28 2006-03-02 Keith Hanna Method and apparatus for improved video surveillance through classification of detected objects
DE102007031302A1 (de) * 2007-07-05 2009-01-08 Robert Bosch Gmbh Vorrichtung zur Erkennung und/oder Klassifizierung von Bewegungsmustern in einer Bildsequenz von einer Überwachungsszene, Verfahren sowie Computerprogramm
WO2010139495A1 (fr) * 2009-06-05 2010-12-09 Siemens Aktiengesellschaft Procédé et dispositif pour le classement de situations

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060045354A1 (en) * 2004-07-28 2006-03-02 Keith Hanna Method and apparatus for improved video surveillance through classification of detected objects
DE102007031302A1 (de) * 2007-07-05 2009-01-08 Robert Bosch Gmbh Vorrichtung zur Erkennung und/oder Klassifizierung von Bewegungsmustern in einer Bildsequenz von einer Überwachungsszene, Verfahren sowie Computerprogramm
WO2010139495A1 (fr) * 2009-06-05 2010-12-09 Siemens Aktiengesellschaft Procédé et dispositif pour le classement de situations

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3101827A1 (fr) * 2019-10-15 2021-04-16 Transdev Group Innovation Dispositif électronique et procédé de génération d’un signal d’alerte, système de transport et programme d’ordinateur associés
EP3809382A1 (fr) * 2019-10-15 2021-04-21 Transdev Group Innovation Dispositif électronique et procédé de génération d'un signal d'alerte, système de transport et programme d'ordinateur associés
EP4112420A1 (fr) * 2021-07-01 2023-01-04 Siemens Mobility GmbH Procédé de détection d'un événement relatif à la sécurité à l'intérieur d'une cabine de passagers d'un véhicule ferroviaire
CN113591711A (zh) * 2021-07-30 2021-11-02 沭阳县华源米业股份有限公司 一种基于人工智能的粮仓危险源安全监测方法及系统
CN113591711B (zh) * 2021-07-30 2022-07-19 沭阳县华源米业股份有限公司 一种基于人工智能的粮仓危险源安全监测方法及系统

Also Published As

Publication number Publication date
DE102017222898A1 (de) 2019-06-19

Similar Documents

Publication Publication Date Title
EP3499473A1 (fr) Détection automatisée de situations dangereuses
DE60005380T2 (de) Überwachungssystem
DE102012215544A1 (de) Überwachung einer Bahnstrecke
WO2009003793A2 (fr) Dispositif pour identifier et/ou classifier des modèles de mouvements dans une séquence d'images d'une scène de surveillance, procédé et programme informatique
DE102014215057A1 (de) Bestimmung einer Kollisionswahrscheinlichkeit auf Basis einer Kopforientierung eines Fußgängers
DE102012218870A1 (de) Verbessertes Erkennen herrenloser Objekte unter Verwendung des Erfassens von Fussgängern
DE102020203473A1 (de) Anonymisierungseinrichtung, Überwachungsvorrichtung, Verfahren, Computerprogramm und Speichermedium
CH706631B1 (de) Akustisches Überwachungssystem, insbesondere für Gleisanlagen für Züge.
DE102020203475A1 (de) Anonymisierungseinrichtung, Überwachungsvorrichtung, Verfahren, Computerprogramm und Speichermedium
WO2020239540A1 (fr) Procédé et dispositif de détection de fumée
EP2483834B1 (fr) Methode et appareil pour la reconnaissance d'une detection fausse d'un objet dans un image
EP3493171A1 (fr) Détection du comportement agressif dans les moyens de transport publics
DE102009024066A1 (de) Verfahren und Vorrichtung zum Klassifizieren von Situationen
DE102009028212A1 (de) Verfahren zum Überwachen eines Bereichs
DE112017007247T5 (de) Bildverarbeitungsvorrichtung
DE102016222134A1 (de) Videoanalyseeinrichtung für eine Überwachungsvorrichtung und Verfahren zur Erzeugung eines Einzelbildes
EP3616858A2 (fr) Procédé et dispositif de documentation d'un état d'un robot autonome
DE102019134813A1 (de) Ereignis-Überwachung in einem räumlichen Bereich
DE102017219269A1 (de) Klassifizierung mit automatischer Auswahl aussichtsreicher Lerndaten
WO2021083463A1 (fr) Système de détection d'un événement homme à la mer
DE102009043080B4 (de) Verfahren zur Detektion von Rauch und/oder Flammen und Detektionssystem
DE102020004792A1 (de) Verfahren und Vorrichtung zur Erkennung und Meldung von Parkunfällen für Fahrzeuge
EP3759644B1 (fr) Identification de sièges inoccupés sur la base de la détection d'une texture répétée
EP2031530A2 (fr) Procédé d'analyse assistée par ordinateur d'un objet
DE102012023473A1 (de) Verfahren und fahrzeugbasierte Vorrichtung zur fahrzeuggestützten Personenkontrolle

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20191220