WO2006060889A1 - Procede et systeme permettant d'evaluer l'ensemble de spectateurs d'un média - Google Patents

Procede et systeme permettant d'evaluer l'ensemble de spectateurs d'un média Download PDF

Info

Publication number
WO2006060889A1
WO2006060889A1 PCT/CA2005/000109 CA2005000109W WO2006060889A1 WO 2006060889 A1 WO2006060889 A1 WO 2006060889A1 CA 2005000109 W CA2005000109 W CA 2005000109W WO 2006060889 A1 WO2006060889 A1 WO 2006060889A1
Authority
WO
WIPO (PCT)
Prior art keywords
gaze
information
audience
algorithm
suitably selected
Prior art date
Application number
PCT/CA2005/000109
Other languages
English (en)
Other versions
WO2006060889A8 (fr
Inventor
Colby James Magee Smith
Original Assignee
Cmetrics Media Inc.
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 Cmetrics Media Inc. filed Critical Cmetrics Media Inc.
Publication of WO2006060889A1 publication Critical patent/WO2006060889A1/fr
Publication of WO2006060889A8 publication Critical patent/WO2006060889A8/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
    • H04H60/45—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for identifying users
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/113—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/117—Identification of persons
    • A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
    • A61B5/1176—Recognition of faces
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/56—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54
    • H04H60/59—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54 of video
    • 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
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213—Monitoring of end-user related data
    • H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program

Definitions

  • the present invention relates to a passive method and system for determining the proportion of an audience that is viewing a given medium. Further, the invention provides a passive method for determining the demographics of the audience that is viewing a given medium.
  • Advertising is a very important aspect of marketing products. It is, however, very expensive, and often not very effective. There are many ways of attempting to assess the effectiveness of a given medium, ranging from providing coupons in newspapers, to offering complimentary products in radio and TV ads. While it is known that a written ad will be read if it attracts the eye, and hence, all that is required is to attract the eye, the same cannot be said for TV ads. Viewers will often walk away, change the channel or mute the ad, and therefore, the ad may never be seen.
  • the proportion of the pre-registered audience that is deemed to be watching the TV can also be used to extrapolate and estimate the proportion of the general population that is watching a given program or advertisement.
  • a related technology is eye tracking. This method can be used for accurately determining where on the screen the viewer is looking and has been applied to studies of TV
  • eye tracking can determine whether or not a specific user is viewing the TV or not, on the basis of determining the location on the display that is being viewed. In this context, it is superior to face recognition. However, the environment is highly artificial and in most cases the subject has to wear restrictive head gear. Such obtrusive
  • the method is not designed to determine whether or not there is an audience. In other words, it is assumed that the audience is there. Still further, the method is almost always constrained to one viewer.
  • the preferred application of the technology does not relate to determining viewership, and is better applied to studies that determine where on a screen a viewer is looking.
  • eye tracking can be used to help design better hypermedia such as web pages.
  • the assumption is that the audience member is always looking at the screen. This is a valid assumption because the implementation of this technology requires a highly
  • the data that result are used to provide a gauge to the effectiveness of the content in a particular coordinate of the media display.
  • Eye tracking can be used to determine the optimum placement of an advertisement on a web page, the optimum ratio of links versus white space, and for example, what arrangement of words on the page works best. This, of course, relies upon generating a data set either on a set
  • a passive method for determining the number of viewers of a display in a natural environment within an audience comprises selecting a field of view, capturing information in the field of view with a suitably selected capturing device, searching the information for an audience, using an algorithm to determine an audience, tracking movement of each member of an audience in the field of view, generating a datum for each member of an audience and storing the datum as part of a data set, forwarding said information representing a verified member of the audience to a gaze analysis algorithm, determining each viewer within the audience, providing a datum for each viewer and storing the datum as part of the data set.
  • the suitably selected capturing device is an electromagnetic wavelength detector.
  • the method further comprises an algorithm to determining the statistical confidence of the determination of a viewer.
  • the method further comprises capturing information as an at least one image and digitizing said at least one image.
  • the method further comprises retrieving the data set.
  • the method further comprises generating a history from the repeating of the method.
  • the method further comprises at least partially rotating the image to assist in determining an audience.
  • the method further comprises reviewing the data set for anomalies.
  • the anomalies are static.
  • the anomalies change their identity.
  • the suitably selected capture device is a camera.
  • the suitably selected capture device is a video camera.
  • the suitably selected capture device is a still camera.
  • the suitably selected capture device is selected from the group consisting of a near infrared camera, an infrared camera and a thermal camera.
  • the method further comprises querying the data set.
  • the method further comprises sending said information to a demographic determination algorithm and ascribing demographics to said information.
  • the method further comprises sending said information to a face recognition algorithm and ascribing an identity to said information from a pre-determined enrolment list of users.
  • the method further comprises determining the demographics of said viewers.
  • the demographics are selected from the group consisting of age, sex, race, profession, income, activities, family structure and citizenship.
  • the method further comprises gaze tracking.
  • the method further comprises spawning a thread for each viewer.
  • the method further comprises concurrent analysis of a number of threads.
  • the method further comprises destroying the images following storing data for each audience member.
  • a system to passively determine an audience and viewers of a display in a natural environment for use with a display comprises: a suitably selected image capturing device; a computer to receive images from the image capturing device and to determine an audience and viewers in an audience, the computer having an algorithm to determine an audience, a gaze analysis algorithm and storage to store information for each member of an audience and a datum for each viewer as part of a data set.
  • system further comprises a suitably selected output device, such that in use, data can be retrieved from the data set.
  • system further comprises an algorithm to determine the statistical confidence of the determination of a viewer.
  • system further comprises a timer, such that in use, a temporal component is added to the data for a viewer.
  • system further comprises a reviewer, such that in use, the data are reviewed for anomalies.
  • the suitably selected capture device is a camera.
  • the suitably selected capture device is a video camera.
  • the suitably selected capture device is a still camera.
  • the suitably selected capture device is selected from the group consisting of a near infrared camera, an infrared camera and a thermal camera.
  • system further comprises a means of querying a data set.
  • system further comprises a demographic determination algorithm. In another aspect of the invention, the system further comprises a face recognition algorithm.
  • system further comprises an enrolment list of pre-determined users.
  • system further comprises a tracker, such that in use, a gaze of a viewer can be tracked.
  • system further comprises thread spawning means.
  • system further comprises means for analyzing of a number of threads.
  • system further comprises an algorithm to determine the statistical confidence of the determination of the gaze.
  • Another embodiment of the invention provides a passive method for tracking a gaze of a viewer viewing a display in a natural environment.
  • the passive method comprises selecting a field of view, capturing information in the field of view with a suitably selected capturing device, sending said information to an algorithm to determine a face, sending the information to a gaze analysis algorithm, using a gaze analysis algorithm to analyze the information to determine a gaze, transforming the information into data and storing the data as part of a data set.
  • the information is collected as images, the method further comprising capturing and digitizing the images.
  • the display is a screen.
  • the method further comprises sending information on the location and movement of said gaze to a PASS/FAIL algorithm.
  • the screen is a computer screen.
  • the method further comprises assessing the location and movement of the gaze on a PASS/FAIL basis.
  • the method further comprises allowing a request when said location and movement of said gaze is assessed as PASS and denying a request when said location and movement of said gaze is assessed as FAIL
  • the method allows determination the statistical confidence of the determination of the gaze.
  • the methods allows for tracking the gaze.
  • a system to passively track a gaze of a viewer viewing a display in a natural environment comprises: a suitably selected information capturing device, a computer to receive information from the information capturing device, transform the information into data and storing the data as part of a data set., said computer comprising a face detection algorithm, gaze analysis algorithm and storage.
  • system further comprises a PASS/FAIL algorithm for assessing the location and movement of said gaze on a PASS/FAIL basis.
  • the suitably selected capture device is a camera.
  • the suitably selected capture device is a video camera.
  • the suitably selected capture device is a still camera.
  • system comprises a gaze tracker.
  • system comprises an analyzer to determine the statistical confidence of the determination of the gaze.
  • Figure 1 is a perspective view of members of an audience viewing a display in accordance with an embodiment of the invention.
  • FIG. 2 is a flow chart in accordance with an embodiment of the invention.
  • Pie-enrolment Takes a picture of a face, encodes that face to create a template and stores that template into a database (or file system).
  • Pre-determination Determines a user by selecting them to view a display. This is used in eye tracking.
  • Face recognition Identifies pre-enrolled audience members watching a given medium. The technology assumes that any audience member who is identified is indeed watching the medium. It can be used in monitoring TV users. Recognition attempts to determine the identity of the individual against a candidate list. You always need face detection to invoke face recognition but the reverse is not true. This is referred to as a compliance method, as it requires that the subject to participate in the process leading to data collection. It is unobtrusive.
  • Eye tracking Records eye movements, such as eye fixations, eye movements and pupil dilations. This has been used to collect information from pre-enrolled TV users, but is more frequently used to collect data about where on a display a viewer is directing their attention. This is a compliance method and is obtrusive, as the environment is highly artificial.
  • Face detection Determines the population that is facing a given medium. No pre- registration is required. No pre-enrolment is needed, and it is applicable to many different forms of media. Face detection does not require face recognition. This is a non-compliance method of collecting information, as the population need not even be aware that detection is occurring. Further, it is unobtrusive.
  • Gaze tracking Determines if and where a gaze is directed. Also determines which of the faces detected in face detection arc actually viewing the given medium. This is a non- compliance method of collecting information, as the population need not even be aware that detection is occurring. Further, it is unobtrusive.
  • Passive information collection Methods that can be unobtrusive and do not necessarily require compliance. In other words, methods that can take place without altering the environment in which the data arc being collected and without involving the audience in the data collection.
  • Audience The sum total of people who are exposed at any given time to a display.
  • Viewer The segment of the audience that is viewing a display at any given time.
  • Face detection and gaze analysis can be used to determine the segment of an audience that is viewing a display.
  • the display can be a media display, for example advertising and can be static, for example, printed medium, or dynamic, for example, a TV or plasma screen.
  • the display is directed toward the intended audience in a normal, natural and unaffected environment as shown in Figure 1.
  • face detection and gaze analysis in the present invention is a passive process.
  • At least one information capturing device for example, a video camera is pointing outward from the display toward the same target audience.
  • the video camera(s) are connected to one or more computers.
  • the video is digitized (if not already in a digital form) and the software analyzes the video.
  • the video is immediately discarded after analysis and is not stored or copied externally.
  • AoI areas of interest
  • analysis methods such as motion detection, pattern recognition, color histogram analysis or optical flow
  • face detection algorithm determines if there are human faces in the field of view. Each face is stored as an object.
  • the algorithms being applied to a captured image are processor intensive; therefore 0 the re-use of data is important. If a face has been found and its gaze determined it can be assumed that the state of the face will have changed little in the next frame (typically 1/30 of a second apart). As a result of this assumption the processing required can be reduced by isolating the areas of interest in the FOV. Also, passing the last known state of the face object to the algorithms increases the speed of the overall process. 25
  • the analysis of the captured images provides a data set that is time sliced into discrete intervals, typically 1/10 of a second.
  • the data are stored in a format that allows complex queries against it (typically a relational database). From this data set, inferences upon the effectiveness of the media on its viewers are made. For example, it is possible to 0 determine on average what percentage of individuals in the field of view viewed more than 40% of a 30 second time interval without breaking gaze more than twice.
  • the number of computers required is dependent on the size of the display, the maximum number of audience members and the processing requirements of the gaze analysis algorithm.
  • the computer determines how many faces are in a given frame and then how many of those faces are actually viewing the display.
  • the steps of the process can be broadly divided into three stages: data capture; data upload; and data analysis.
  • the steps of the data capture process are outlined in Figure 2.
  • Live video is captured and digitized, as needed.
  • the frame is searched for Areas of Interest (AOI) in the Field of View (FOV) using a suitable face detection algorithm.
  • AOI Areas of Interest
  • FOV Field of View
  • an object For each face found, an object is created that represents that face and the object keeps track of the state of that face by determining: i. Its location in the FOV (Field of View); ii. Its path through the FOV; iii. The statistical confidence that the algorithm associates with determining that this is a face; iv. All other subsequent processing on the object (Step 4 & 6); and v. The object is then spawned in a separate thread. 4.
  • Each object identified as a face is forwarded to a gaze analysis algorithm. a. It is determined whether or not the gaze is directed at the display. b. The statistical confidence of the gaze is then determined. c. The history of the gaze and path for this object is recorded.
  • the object is passed to a face recognition algorithm that can: a. Determine the identity of the individual from an enrollment list; b. Record the statistical confidence of this recognition determination; and c. Record the history of the recognition for this object.
  • a face demographics determination algorithm that can: a. Determine the age, sex and race of the individual; b. Record the statistical confidence of this determination;and c. Record the history of the demographics determination for this object.
  • Step 7 the stored data are reviewed for anomalies such as: a. ⁇ subject in the FOV that has not moved for a long period of time; b. A face that is found and lost in exact reoccurring intervals; c. An object that has changed its identity; and d. An object that has changed its demographics. Data Upload
  • the environment data describe the setting that the invention is placed in, the target audience and (optionally) the identities and demographics of the individuals most likely to watch the media display.
  • Collected Data are data resulting from the data capture process. These data are uploaded in preset time intervals (typically 30 minutes). The content of these data is described in the above section describing the data capture process.
  • All data from all collection sites can be stored at a central location. In order to then gather statistics and inferences the data that results from analysis need to be organized and categorized and stored in a relational database. Typically, after that, the server will respond to queries that will provide detailed information on the target audience and the media content in question.
  • An example query that utilizes face recognition and the resultant demographic information would be: How many Hispanic females between the ages of 12 and 14 watched more than 50% of the program ⁇ yz at time and date mm::hh::dd::year with less than 10 breaks in gaze.
  • the information capturing device may include video cameras, still cameras, near infrared cameras, digital cameras, electromagnetic wavelength detectors and combinations thereof.
  • the method may also include determining race, age or gender by using facial characterization in the absence of face recognition (i.e. without pre-enrolment). There are also many different applications of the technology.
  • a display may be, for example, but not meant to be limiting, a video in an airport, a sculpture in an art gallery, a TV screen, a billboard, a computer screen, a cockpit display in a plane, a control panel in a truck.
  • the invention also provides for numerous methods. For example, but not meant to be limiting, detecting and tracking a gaze can be used independent from face detection in applications wherein a specific viewer is being tracked. This may be a person watching TV, a pilot, a driver or a computer user.
  • the invention for example provides for a method to track the gaze to ensure that documents are scanned in their entirety. Legal documents, for example licensing agreements on web pages that must be accepted in order for the user to access the site, are frequently not read by the user.
  • Tracking the gaze of the user could ensure that the document is scanned, by simply blocking the user from proceeding if the gaze does not move over the entire document.
  • the gaze would be assessed and given a PASS or FAIL rating by using a PASS/FAIL algorithm. This could be used in addition to the presently used "accept the terms" button.
  • displays can be analyzed for their effectiveness by monitoring the part of the display that attracts the gaze. For example, the effectiveness of specific parts of a webpage, a TV screen or a static ad can be monitored.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Eye Examination Apparatus (AREA)

Abstract

L'invention concerne un procédé et un système permettant de déterminer le nombre de spectateurs d'un affichage à l'intérieur d'une audience. Ledit procédé consiste à rechercher une zone dans un champ de vision, puis à capturer et numériser l'audience dans des trames à l'aide d'un dispositif de capture sélectionné de manière appropriée. La vidéo numérique est analysée trame par trame afin de déterminer des zones d'intérêt qui peuvent être des visages humains. On utilise un algorithme de détection de visage pour déterminer si un visage humain se trouve dans la zone d'intérêt et une indication de fiabilité de cet algorithme pour déterminer le visage. Lorsqu'on trouve un visage, on détermine de regard du sujet à l'aide d'un algorithme de détection de regard approprié qui renvoie l'angle de regard et une valeur de fiabilité associée à une précision de détermination de cet angle. On crée des données qui permettent de suivre toutes les informations pertinentes sur le spectateur et on les stocke.
PCT/CA2005/000109 2004-12-09 2005-01-27 Procede et systeme permettant d'evaluer l'ensemble de spectateurs d'un média WO2006060889A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US63505504P 2004-12-09 2004-12-09
US60/635,055 2004-12-09

Publications (2)

Publication Number Publication Date
WO2006060889A1 true WO2006060889A1 (fr) 2006-06-15
WO2006060889A8 WO2006060889A8 (fr) 2006-10-26

Family

ID=36577621

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CA2005/000109 WO2006060889A1 (fr) 2004-12-09 2005-01-27 Procede et systeme permettant d'evaluer l'ensemble de spectateurs d'un média

Country Status (1)

Country Link
WO (1) WO2006060889A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007128057A1 (fr) * 2006-05-04 2007-11-15 National Ict Australia Limited Systeme médiatique electronique
WO2010060146A1 (fr) * 2008-11-27 2010-06-03 Seeing Machines Limited Métrique de quantification d'attention et applications de celle-ci
EP2210354A2 (fr) * 2007-09-11 2010-07-28 Wavebreak Technologies Ltd. Détecteur de presence et procédé d'estimation d'un auditoire
CN102081810A (zh) * 2010-11-15 2011-06-01 中国电信股份有限公司 户外媒体远程监测方法和系统
US8965042B2 (en) * 2007-03-20 2015-02-24 International Business Machines Corporation System and method for the measurement of retail display effectiveness
EP2989528A4 (fr) * 2013-04-26 2016-11-23 Hewlett Packard Development Co Détection d'un utilisateur attentif pour présenter un contenu personnalisé sur un affichage

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4075657A (en) * 1977-03-03 1978-02-21 Weinblatt Lee S Eye movement monitoring apparatus
US5550928A (en) * 1992-12-15 1996-08-27 A.C. Nielsen Company Audience measurement system and method
US6393136B1 (en) * 1999-01-04 2002-05-21 International Business Machines Corporation Method and apparatus for determining eye contact
WO2003050658A2 (fr) * 2001-12-12 2003-06-19 Eyetools Technique pour faciliter l'utilisation de donnees de poursuite oculaire
WO2004084054A2 (fr) * 2003-03-21 2004-09-30 Queen's University At Kingston Procedes et appareil pour la communication entre des personne et des dispositifs

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4075657A (en) * 1977-03-03 1978-02-21 Weinblatt Lee S Eye movement monitoring apparatus
US5550928A (en) * 1992-12-15 1996-08-27 A.C. Nielsen Company Audience measurement system and method
US6393136B1 (en) * 1999-01-04 2002-05-21 International Business Machines Corporation Method and apparatus for determining eye contact
WO2003050658A2 (fr) * 2001-12-12 2003-06-19 Eyetools Technique pour faciliter l'utilisation de donnees de poursuite oculaire
WO2004084054A2 (fr) * 2003-03-21 2004-09-30 Queen's University At Kingston Procedes et appareil pour la communication entre des personne et des dispositifs

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
HARITAOGLU I. ET AL: "Attentive Billboards", PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, 26 September 2001 (2001-09-26) - 28 September 2001 (2001-09-28), PALERMO, ITALY, pages 162 - 167 *
HARITAOGLU I. ET AL: "Attentive Billboards:Towards to Video based Customer Behavior Understanding", SIXTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION, 3 December 2002 (2002-12-03) - 4 December 2002 (2002-12-04), ORLANDO, FLORIDA USA, pages 127 - 131 *
HONGO H. ET AL: "Automatic Marketing Information System Sensing Customers'Eye Movements", PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, 5 August 2002 (2002-08-05) - 7 August 2002 (2002-08-07), OSAKA, JAPAN, pages 1 - 6 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007128057A1 (fr) * 2006-05-04 2007-11-15 National Ict Australia Limited Systeme médiatique electronique
US8775252B2 (en) 2006-05-04 2014-07-08 National Ict Australia Limited Electronic media system
US8965042B2 (en) * 2007-03-20 2015-02-24 International Business Machines Corporation System and method for the measurement of retail display effectiveness
EP2210354A2 (fr) * 2007-09-11 2010-07-28 Wavebreak Technologies Ltd. Détecteur de presence et procédé d'estimation d'un auditoire
WO2010060146A1 (fr) * 2008-11-27 2010-06-03 Seeing Machines Limited Métrique de quantification d'attention et applications de celle-ci
CN102081810A (zh) * 2010-11-15 2011-06-01 中国电信股份有限公司 户外媒体远程监测方法和系统
EP2989528A4 (fr) * 2013-04-26 2016-11-23 Hewlett Packard Development Co Détection d'un utilisateur attentif pour présenter un contenu personnalisé sur un affichage
US9767346B2 (en) 2013-04-26 2017-09-19 Hewlett-Packard Development Company, L.P. Detecting an attentive user for providing personalized content on a display

Also Published As

Publication number Publication date
WO2006060889A8 (fr) 2006-10-26

Similar Documents

Publication Publication Date Title
US11509956B2 (en) Systems and methods for assessing viewer engagement
US10089533B2 (en) Identifying visual objects depicted in video data using video fingerprinting
US10346860B2 (en) Audience attendance monitoring through facial recognition
US7814061B2 (en) Method for preserving privacy with image capture
US8155446B2 (en) Characterizing dynamic regions of digital media data
KR101756218B1 (ko) 디지털 광고 시스템
Liciotti et al. Person re-identification dataset with rgb-d camera in a top-view configuration
US9443144B2 (en) Methods and systems for measuring group behavior
US20150082331A1 (en) Methods for identifying video segments and displaying contextually targeted content on a connected television
JP4603975B2 (ja) コンテンツ注目評価装置及び評価方法
US20090217315A1 (en) Method and system for audience measurement and targeting media
US20050088407A1 (en) Method and system for managing an interactive video display system
US20100232644A1 (en) System and method for counting the number of people
CN1589451A (zh) 采用视频原语的视频监视系统
Paul et al. Spatial and motion saliency prediction method using eye tracker data for video summarization
WO2006060889A1 (fr) Procede et systeme permettant d'evaluer l'ensemble de spectateurs d'un média
Yin et al. A study on the effectiveness of digital signage advertisement
Erdélyi et al. Privacy protection vs. utility in visual data: An objective evaluation framework
Tian et al. Intelligent advertising framework for digital signage
Carlson et al. Automated high-frequency observations of physical activity using computer vision
De Pessemier et al. Enhancing recommender systems for TV by face recognition
Elhart et al. Audience monitor: an open source tool for tracking audience mobility in front of pervasive displays
CN201467351U (zh) 基于人脸检测的电视收视率统计装置
Martinet et al. Gaze based quality assessment of visual media understanding
CN118246987B (zh) 基于投放效果分析的广告投放位置管理系统

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 05706435

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 05706435

Country of ref document: EP

Kind code of ref document: A1

WWW Wipo information: withdrawn in national office

Ref document number: 5706435

Country of ref document: EP