WO2009059346A1 - Procédé de détection et/ou d'évaluation de séquences de mouvements - Google Patents

Procédé de détection et/ou d'évaluation de séquences de mouvements Download PDF

Info

Publication number
WO2009059346A1
WO2009059346A1 PCT/AT2008/000406 AT2008000406W WO2009059346A1 WO 2009059346 A1 WO2009059346 A1 WO 2009059346A1 AT 2008000406 W AT2008000406 W AT 2008000406W WO 2009059346 A1 WO2009059346 A1 WO 2009059346A1
Authority
WO
WIPO (PCT)
Prior art keywords
pixels
events
detection
counted
pixel
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.)
Ceased
Application number
PCT/AT2008/000406
Other languages
German (de)
English (en)
Inventor
Richard Hopf
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Publication of WO2009059346A1 publication Critical patent/WO2009059346A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30236—Traffic on road, railway or crossing

Definitions

  • the invention relates to a method for detecting and / or evaluating motion sequences using a digitally recording optical recording device wherein the characteristics of one or more pixels of the digital camera, such as e.g. the coordinates in the image plane, the color, the intensity and / or the contrast of adjacent pixels are used for the detection and / or evaluation.
  • each vehicle contains a corresponding identification module with a communication interface, in particular a transmitter, which communicates with receiving modules at predetermined intervals and in this way announces the identity of the passing motor vehicle.
  • a communication interface in particular a transmitter
  • Such a device stores vehicle-specific and thus indirectly also person-specific data, whereby the recording of such data is subject to restrictions due to applicable legal provisions.
  • the invention now aims to provide a method of the type mentioned, in which on the detection and storage of specific, an individual or a single consumer or even a single vehicle associated data is avoided and the possibility is created here to allow a completely anonymous collection and evaluation.
  • the invention further aims to make such detection and evaluation as easy as possible and to get along with simple hardware requirements.
  • the invention aims to eliminate the possibility of tracking individual customer-specific features with certainty, while maintaining anonymity while maintaining high accuracy.
  • the inventive method using a digitally recording optical recording device essentially consists in the fact that the coordinates of pixels in time intervals are compared with each other and a deviation from a default value as an event and / or at a subsequent unchanged position of the pixel or pixels counted as event duration and / or evaluated.
  • Digital cameras record images in the form of pixels on corresponding sensors, for example CCDs, wherein these sensors each contain a predetermined number of pixels with defined coordinates on the sensor, which can be read out separately.
  • the color can be additionally or separately evaluated as a criterion, with digital cameras also allow measurements of the intensity and / or the contrast of adjacent pixels in a simple manner.
  • the default values can be formed in a particularly simple manner from a digital video image corresponding to the region to be detected, and preferably updated at time intervals. The choice of the respective time intervals can be selected depending on the speed of the movements to be detected.
  • a higher frame rate ensures that in fact all events are detected and that individual events do not fall in the idle times between the acquisition of two consecutive images.
  • 1.5 to 4 images per second can be detected and evaluated accordingly at the pixel level.
  • the counted events and / or the duration of the events can be visualized on a visual display.
  • the type of optical display is sufficient here from bar charts to standard statistical images using standard gray scales or color scales.
  • the representation can be chosen such that a color and / or intensity-coded 3-dimensional representation is selected as the visual display.
  • the frequency i. the temporal frequency of individual events is represented as a peak or elevation from the level and thus as an intensity
  • the residence time of a consumer which is counted as an event duration
  • the method can be carried out so that when a definable threshold value of events is exceeded, a signal is generated.
  • This signal may be, for example, a pop-up window in the monitoring software, e.g. draw the attention of the end user to a large crowd of people or be coupled with the department store to be monitored in such a way that evasion routes are proposed in the event of an overloaded gear or light and / or sound effects draw the attention of the customers to disregarded goods racks ,
  • the method can be carried out in this case in such a way that a plurality of digital video cameras are directed to mutually different detection areas and events in the overlapping region of the imaging optics of the video cameras are computationally compensated.
  • the quality of the representation and in particular the elimination of image disturbances or events which could lead to misinterpretation can in this case be carried out in a simple manner so that relevant areas for the detection or evaluation are filtered out by image masks.
  • appropriate mathematical filters can be used in addition to such image masks in order to increase the significance of the individual events.
  • the procedure according to the invention is of course suitable not only for shopping centers and / or areas in which vehicles are moved, such as car parks or parking garages, but also for museums and other public facilities, for which a correspondingly correct statistics for future planning the best conditions supplies.
  • FIG. 1 a shows a photograph of a digital camera which shows the starting position of a digital camera. ation for the further recordings.
  • Fig. Ib are counted the events and in Fig. Ic the dwell time.
  • FIGS. 2a, 2b, 2c, 3a, 3b, 3c, 4a, 4b, 4c, 5a, 5b, 5c represent subsequent recordings, FIGS. 2b-5b also showing the events in FIGS Residence time is counted.
  • an object having a size of 4 pixels moves from Fig. 1a to Fig. 2a one pixel to the right, from Fig.2a to Fig. 3a one pixel to the top right, from Fig. 3a to Fig. 4a, it stays in the same place, and in Fig. 5a, the object continues to move one pixel to the top right, with another object appearing in the lower left corner.
  • FIGS. 6a to 10a show the same movement of the object, wherein in FIGS. 6b to 10b the direction of motion is evaluated for each pixel, and in FIGS. 6c to 10c the individual directions of movement of the pixels are combined into flow diagrams.
  • each individual event is observed, and as soon as an event is triggered in an adjacent pixel, each pixel having eight such pixels in question, a vector is added to the pixel in the appropriate direction, with each direction initially summing up separately and evaluated. For each evaluation, it is therefore possible to assign several directions of movement to one pixel. This can be seen particularly clearly in FIG. 8b, in which the formerly upper right pixel of the object and now lower left pixel of the object are assigned three directions of movement.
  • FIGS. 6c to 10c show the gradual structure of the main flow directions, wherein it is clearly evident that, for correct statistical evaluation, a plurality of comparison data naturally has to be recorded. In Fig.10c can be seen but a tendency to move.
  • these embodiments relate to a pixel-precise evaluation in which a plurality of mutually moving pixels can be combined to form an object that can jointly trigger an event, whereby the number of combined pixels depends on the size of the objects to be analyzed on the digital image is.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

La présente invention concerne un procédé de détection et/ou d'évaluation de séquences de mouvements par utilisation d'un appareil de prise de vue optique à enregistrement numérique. Selon l'invention, des propriétés d'un ou de plusieurs points d'image (pixels) de la caméra numérique, par ex. les coordonnées dans le plan d'image, la couleur, l'intensité et/ou le contraste de points d'image voisins, sont utilisées pour la détection et/ou l'évaluation, et les coordonnées de points d'image sont comparés entre elles à intervalles de temps réguliers, et, lors d'une divergence par rapport à une valeur de référence, comptabilisées et/ou évaluées sous la forme d'un événement, et/ou dans le cas d'une position suivante inchangée du ou des points d'images, comptabilisées et/ou évaluées sous la forme d'un événement persistant.
PCT/AT2008/000406 2007-11-09 2008-11-10 Procédé de détection et/ou d'évaluation de séquences de mouvements Ceased WO2009059346A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
ATA1811/2007 2007-11-09
ATA1811/2007A AT506051B1 (de) 2007-11-09 2007-11-09 Verfahren zum erfassen und/oder auswerten von bewegungsabläufen

Publications (1)

Publication Number Publication Date
WO2009059346A1 true WO2009059346A1 (fr) 2009-05-14

Family

ID=40394537

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/AT2008/000406 Ceased WO2009059346A1 (fr) 2007-11-09 2008-11-10 Procédé de détection et/ou d'évaluation de séquences de mouvements

Country Status (2)

Country Link
AT (1) AT506051B1 (fr)
WO (1) WO2009059346A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111815980A (zh) * 2019-04-11 2020-10-23 浙江百康光学股份有限公司 道路群组管理方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1024666A2 (fr) * 1999-01-29 2000-08-02 Hitachi, Ltd. Appareil d'enregistrement et réproduction d'images dans un système de surveillance
US20010024513A1 (en) * 1999-12-27 2001-09-27 Takafumi Miyatake Surveillance apparatus and recording medium recorded surveillance program
US20030025599A1 (en) * 2001-05-11 2003-02-06 Monroe David A. Method and apparatus for collecting, sending, archiving and retrieving motion video and still images and notification of detected events
US20040032494A1 (en) * 2002-08-13 2004-02-19 Wataru Ito Object-detection-condition modifiable object detection method and object detection apparatus using the method
US20050046699A1 (en) * 2003-09-03 2005-03-03 Canon Kabushiki Kaisha Display apparatus, image processing apparatus, and image processing system
US20050163346A1 (en) * 2003-12-03 2005-07-28 Safehouse International Limited Monitoring an output from a camera

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102005008131A1 (de) * 2005-01-31 2006-08-03 Daimlerchrysler Ag Objektdetektion auf Bildpunktebene in digitalen Bildsequenzen
KR20070119018A (ko) * 2005-02-23 2007-12-18 크레이그 써머스 3ｄ 카메라 및 3ｄ비디오를 위한 자동 씬 모델링

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1024666A2 (fr) * 1999-01-29 2000-08-02 Hitachi, Ltd. Appareil d'enregistrement et réproduction d'images dans un système de surveillance
US20010024513A1 (en) * 1999-12-27 2001-09-27 Takafumi Miyatake Surveillance apparatus and recording medium recorded surveillance program
US20030025599A1 (en) * 2001-05-11 2003-02-06 Monroe David A. Method and apparatus for collecting, sending, archiving and retrieving motion video and still images and notification of detected events
US20040032494A1 (en) * 2002-08-13 2004-02-19 Wataru Ito Object-detection-condition modifiable object detection method and object detection apparatus using the method
US20050046699A1 (en) * 2003-09-03 2005-03-03 Canon Kabushiki Kaisha Display apparatus, image processing apparatus, and image processing system
US20050163346A1 (en) * 2003-12-03 2005-07-28 Safehouse International Limited Monitoring an output from a camera

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JAMES BLACK ET AL: "Hierarchical database for a multi-camera surveillance system", PATTERN ANALYSIS AND APPLICATIONS, SPRINGER-VERLAG, LO, vol. 7, no. 4, 1 December 2004 (2004-12-01), pages 430 - 446, XP019381474, ISSN: 1433-755X *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111815980A (zh) * 2019-04-11 2020-10-23 浙江百康光学股份有限公司 道路群组管理方法

Also Published As

Publication number Publication date
AT506051B1 (de) 2013-02-15
AT506051A1 (de) 2009-05-15

Similar Documents

Publication Publication Date Title
DE4410406C2 (de) Optoelektronische Vorrichtung zum Überwachen der Umgebung eines Fahrzeugs
EP0986912B1 (fr) Procede pour surveiller une zone de surveillance predefinie
EP1210680B1 (fr) Procede et dispositif pour detecter et analyser le comportement en reception de personnes
EP2467801A1 (fr) Dispositif pour détecter une file d'objets, procédé et programme informatique associés
WO2002007106A1 (fr) Dispositif de detection
EP3044760A1 (fr) Procédé d'analyse de la distribution d'objets dans des files d'attente libres
DE4430016C2 (de) Bewegungsmelder und ein Verfahren zur Bewegungsmeldung
DE10102884A1 (de) Seitenüberwachungsvorrichtung für ein Kraftfahrzeug
EP1346330B1 (fr) Systeme de detection de fumee base sur la video
DE102008029413A1 (de) Parkraummanagement
DE102020133506A1 (de) Parkplatzsteuerungssystem, Parkplatzsteuerungsverfahren und Programm
DE10042935B4 (de) Verfahren zum Überwachen eines vorbestimmten Bereichs und entsprechendes System
EP2819113B1 (fr) Installation de mesure destinée à l'enregistrement d'une plaque d'immatriculation d'un véhicule lors du passage d'une section de mesure
EP1026632B1 (fr) Systeme et procede d'evaluation d'image
DE10049366A1 (de) Verfahren zum Überwachen eines Sicherheitsbereichs und entsprechendes System
EP3688660A1 (fr) Procédé de détection d'un bord de feuille, procédé pour le traitement ciblé de plantes au moyen d'un agent foliaire et utilisation d'un capteur d'images à base d'évènements pour la détection d'un bord de feuille
DE3843093A1 (de) Einrichtung zum erfassen von kundenlaufdaten in selbstbedienungsanlagen
AT506051A1 (de) Verfahren zum erfassen und/oder auswerten von bewegungsabläufen
EP3822899A1 (fr) Enregistrement et évaluation anonymes du comportement de consommateurs
DE19904093A1 (de) Verfahren zur automatischen Erfassung von Parkplatzbelegungen
WO2020169340A1 (fr) Dispositif d'analyse, dispositif de surveillance pourvu du dispositif d'analyse et procédé de détermination d'une image d'arrière-plan en conformité avec la sphère privée
EP1306824B1 (fr) Procédé pour détecter un véhicule avancant sur une route, en particulière sur une autoroute, et pour déterminer des données spécifiques au véhicule
EP1701291B1 (fr) Procédé et dispositif destinés à l'observation et l'évaluation du comportement de personnes
DE202009011048U1 (de) Vorrichtung zur Ermittlung der Anzahl einen Durchgang durchquerender Personen
DE19744694A1 (de) Videobewegungsmeldeeinrichtung

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: 08848429

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 08848429

Country of ref document: EP

Kind code of ref document: A1