MLchartDataset catalogue

Patent · US2011043602A1 · A1 · US

Camera-based facial recognition or other single/multiparty presence detection as a method of effecting telecom device alerting

(11) Publication number
US2011043602A1
(21) Application number
12/828,423
(22) Filing date
2010-07-01
(30) Priority date
2009-08-21
(43) Publication date
2011-02-24
(51) IPC
H04L 45/02; H04L 45/586; H04M 3/42; H04N 7/15; G06F 3/01
(52) CPC
  • G06F Electric digital data processing: 9/543, 16/972, 2009/45562, 2009/4557, 3/048, 9/451, 9/452, 9/45533
  • H04L Transmission of digital information, e.g. telegraphic communication: 12/28, 12/66, 41/0803, 45/02, 45/586, 61/45, 61/4523, 65/1066, 65/1104, 65/1106, 65/403, 65/80, 67/04, 67/08, 67/104, 67/1095, 67/1097, 67/14, 67/306, 67/34, 67/51, 67/54, 69/24
  • H04M Telephonic communication: 7/0057, 7/0081
  • H04N Pictorial communication, e.g. television: 7/15
  • H04W Wireless communication networks: 36/0022, 36/14, 4/02, 4/16, 64/00, 88/06
(73) Assignee
Avaya Inc
(72) Inventors
Vandy Lee
(54) Title
Camera-based facial recognition or other single/multiparty presence detection as a method of effecting telecom device alerting
(57) Abstract

A camera can be associated with each conference participant endpoint. The camera, either frame or video-based, can monitor and detect one or more of gestures, facial recognition, emotions, and movements of the conference participant. Based on the detection of one or more of these triggering events, a correlation to an action corresponding the triggering event can be evoked. For example, if a participant raises their hand, e.g., a triggering event, the system can recognize that this is a request to speak. The participant can then be queued in the system based, for example, relative to other participants' requests. When the other participants have finished speaking, and it is the time for the user who raised their hand to speak, the system can optionally queue the user by modifying the endpoint with which they are associated.

Full text
View on Google Patents

Claims (1)

  1. A conferencing method in a conferencing environment which includes a plurality of conference participants comprising: detecting at least one triggering event at least one participant endpoint; correlating the at least one triggering event to one or more actions; and queuing the one or more actions within the conference. 2. The method of claim 1, further comprising determining if a conflict exists between the one or more actions and one or more other detected or scheduled actions. 3. The method of claim 1, further comprising updating a dynamic agenda based on the at least one triggering event. 4. The method of claim 1, wherein the dynamic agenda is distributable to one or more of the plurality of conference participants. 5. The method of claim 1, further comprising notifying a conference endpoint of a status of a requested action. 6. The method of claim 1, wherein the one or more actions control one or more aspects of the conferencing environment. 7. The method of claim 1, wherein the at least one triggering event includes one or more of an emotion, gesture, change in facial expression, and movements of the conference participant. 8. The method of claim 1, further comprising resolving conflicts based on one or more of rules, job position, moderator preferences, ranking, priority, and title. 9. One or more means for performing the steps of claim 1. 10. A non-transitory computer-readable medium comprising processor executable instructions that, if executed, perform the steps of claim 1. 11. A conferencing system in a conferencing environment which includes a plurality of conference participants comprising: one or more of a gesture recognition module and facial recognition module that that detect at least one triggering event at least one participant endpoint; a triggering event module that correlates the at least one triggering event to one or more actions; and a queuing module that queues the one or more actions within the conference. 12. The system of claim 11, wherein the queuing module further determines if a conflict exists between the one or more actions and one or more other detected or scheduled actions. 13. The system of claim 11, further comprising a dynamic agenda module that updates a dynamic agenda based on the at least one triggering event. 14. The system of claim 11, wherein the dynamic agenda is distributable to one or more of the plurality of conference participants. 15. The system of claim 11, further comprising a conference agent module that notifies a conference endpoint of a status of a requested action. 16. The system of claim 11, wherein the one or more actions control one or more aspects of the conferencing environment. 17. The system of claim 11, wherein the at least one triggering event includes one or more of an emotion, gesture, change in facial expression, and movements of the conference participant. 18. The system of claim 11, wherein the queuing module resolves conflicts based on one or more of rules, job position, moderator preferences, ranking, priority, and title. 19. The system of claim 11, wherein a participant endpoint includes a camera, a display and a communications endpoint. 20. The system of claim 11, wherein: a combination of triggering events can be detected, with a certain sequence of triggering events within a certain time frame being correlatable to one or more functions; triggering actions from one or more participants are weighed to determine an action for the conference as a whole; or the one or more triggering events are correlatable to a request to initiate a running of one or more applications.

Description

An exemplary aspect is directed toward facilitating communications. Even more particularly, an exemplary aspect is directed toward use of one or more of facial and gesture recognition to trigger events, such as a desire to speak, and enqueuing these events based on other meeting participants' request. Another exemplary aspect is directed toward a dynamic agenda based on the one or more triggering events.

Teleconferences allow one or more parties to exchange information via a communications network. This information can include one or more of audio information, video information, and multimedia information. Traditionally, telephone conferences have been phone-based between two or more parties that may or may not be collocated in the same geographic area. These teleconferences allow any party on the conference to interject information as they see fit. Certain enhancements to more sophisticated teleconference environments also allow the moderator to regulate certain aspects of the conference, such as muting certain channels, amplifying certain channels, allowing the use of whisper channels, and the like.

However, in a conference environment, it can be difficult to determine who is speaking, who desires to speak, and what gestures should trigger (if any) certain events to occur. For example, in a multiparty conference, with several individuals who desire to speak, there is a need to organize and structure the speakers in accordance with that desire. Today, there can be overlapping speakers with no ability to determine who is speaking, nor who should speak next.

Citations (32)

  • US5491743A
  • US5852656A
  • US5594469A
  • US6160899A
  • US6301370B1
  • US7018211B1
  • US6272231B1
  • US6894714B2
  • US7231423B1
  • US7984099B1
  • US7225227B2
  • US7761505B2
  • US6920942B2
  • US7607097B2
  • US7999843B2
  • US8351586B2
  • US7598942B2
  • US20070100986A1
  • US20070115348A1
  • US20090187935A1
  • US20080227438A1
  • US20090015659A1
  • US20090079813A1
  • US8325214B2
  • US8295462B2
  • US8503654B1
  • US20100013905A1
  • US20100131866A1
  • US8417551B2
  • US20100220172A1
  • US20100253689A1
  • US20110029893A1
Record as JSON
{
  "publication_number": "US2011043602A1",
  "country": "US",
  "kind": "A1",
  "title": "Camera-based facial recognition or other single/multiparty presence detection as a method of effecting telecom device alerting",
  "abstract": "A camera can be associated with each conference participant endpoint. The camera, either frame or video-based, can monitor and detect one or more of gestures, facial recognition, emotions, and movements of the conference participant. Based on the detection of one or more of these triggering events, a correlation to an action corresponding the triggering event can be evoked. For example, if a participant raises their hand, e.g., a triggering event, the system can recognize that this is a request to speak. The participant can then be queued in the system based, for example, relative to other participants' requests. When the other participants have finished speaking, and it is the time for the user who raised their hand to speak, the system can optionally queue the user by modifying the endpoint with which they are associated.",
  "claims": [
    "1. A conferencing method in a conferencing environment which includes a plurality of conference participants comprising: detecting at least one triggering event at least one participant endpoint; correlating the at least one triggering event to one or more actions; and queuing the one or more actions within the conference. 2. The method of claim 1, further comprising determining if a conflict exists between the one or more actions and one or more other detected or scheduled actions. 3. The method of claim 1, further comprising updating a dynamic agenda based on the at least one triggering event. 4. The method of claim 1, wherein the dynamic agenda is distributable to one or more of the plurality of conference participants. 5. The method of claim 1, further comprising notifying a conference endpoint of a status of a requested action. 6. The method of claim 1, wherein the one or more actions control one or more aspects of the conferencing environment. 7. The method of claim 1, wherein the at least one triggering event includes one or more of an emotion, gesture, change in facial expression, and movements of the conference participant. 8. The method of claim 1, further comprising resolving conflicts based on one or more of rules, job position, moderator preferences, ranking, priority, and title. 9. One or more means for performing the steps of claim 1. 10. A non-transitory computer-readable medium comprising processor executable instructions that, if executed, perform the steps of claim 1. 11. A conferencing system in a conferencing environment which includes a plurality of conference participants comprising: one or more of a gesture recognition module and facial recognition module that that detect at least one triggering event at least one participant endpoint; a triggering event module that correlates the at least one triggering event to one or more actions; and a queuing module that queues the one or more actions within the conference. 12. The system of claim 11, wherein the queuing module further determines if a conflict exists between the one or more actions and one or more other detected or scheduled actions. 13. The system of claim 11, further comprising a dynamic agenda module that updates a dynamic agenda based on the at least one triggering event. 14. The system of claim 11, wherein the dynamic agenda is distributable to one or more of the plurality of conference participants. 15. The system of claim 11, further comprising a conference agent module that notifies a conference endpoint of a status of a requested action. 16. The system of claim 11, wherein the one or more actions control one or more aspects of the conferencing environment. 17. The system of claim 11, wherein the at least one triggering event includes one or more of an emotion, gesture, change in facial expression, and movements of the conference participant. 18. The system of claim 11, wherein the queuing module resolves conflicts based on one or more of rules, job position, moderator preferences, ranking, priority, and title. 19. The system of claim 11, wherein a participant endpoint includes a camera, a display and a communications endpoint. 20. The system of claim 11, wherein: a combination of triggering events can be detected, with a certain sequence of triggering events within a certain time frame being correlatable to one or more functions; triggering actions from one or more participants are weighed to determine an action for the conference as a whole; or the one or more triggering events are correlatable to a request to initiate a running of one or more applications."
  ],
  "description_excerpt": "An exemplary aspect is directed toward facilitating communications. Even more particularly, an exemplary aspect is directed toward use of one or more of facial and gesture recognition to trigger events, such as a desire to speak, and enqueuing these events based on other meeting participants' request. Another exemplary aspect is directed toward a dynamic agenda based on the one or more triggering events.\n\nTeleconferences allow one or more parties to exchange information via a communications network. This information can include one or more of audio information, video information, and multimedia information. Traditionally, telephone conferences have been phone-based between two or more parties that may or may not be collocated in the same geographic area. These teleconferences allow any party on the conference to interject information as they see fit. Certain enhancements to more sophisticated teleconference environments also allow the moderator to regulate certain aspects of the conference, such as muting certain channels, amplifying certain channels, allowing the use of whisper channels, and the like.\n\nHowever, in a conference environment, it can be difficult to determine who is speaking, who desires to speak, and what gestures should trigger (if any) certain events to occur. For example, in a multiparty conference, with several individuals who desire to speak, there is a need to organize and structure the speakers in accordance with that desire. Today, there can be overlapping speakers with no ability to determine who is speaking, nor who should speak next.",
  "cpc": [
    "G06F 9/543",
    "G06F 16/972",
    "G06F 2009/45562",
    "G06F 2009/4557",
    "G06F 3/048",
    "G06F 9/451",
    "G06F 9/452",
    "G06F 9/45533",
    "H04L 12/28",
    "H04L 12/66",
    "H04L 41/0803",
    "H04L 45/02",
    "H04L 45/586",
    "H04L 61/45",
    "H04L 61/4523",
    "H04L 65/1066",
    "H04L 65/1104",
    "H04L 65/1106",
    "H04L 65/403",
    "H04L 65/80",
    "H04L 67/04",
    "H04L 67/08",
    "H04L 67/104",
    "H04L 67/1095",
    "H04L 67/1097",
    "H04L 67/14",
    "H04L 67/306",
    "H04L 67/34",
    "H04L 67/51",
    "H04L 67/54",
    "H04L 69/24",
    "H04M 7/0057",
    "H04M 7/0081",
    "H04N 7/15",
    "H04W 36/0022",
    "H04W 36/14",
    "H04W 4/02",
    "H04W 4/16",
    "H04W 64/00",
    "H04W 88/06"
  ],
  "ipc": [
    "H04L 45/02",
    "H04L 45/586",
    "H04M 3/42",
    "H04N 7/15",
    "G06F 3/01"
  ],
  "assignees": [
    "Avaya Inc"
  ],
  "inventors": [
    "Vandy Lee"
  ],
  "filing_date": "2010-07-01",
  "publication_date": "2011-02-24",
  "priority_date": "2009-08-21",
  "application_number": "US-82842310-A",
  "family_id": "43085839",
  "cited_by_count": 60,
  "citations": [
    "US5491743A",
    "US5852656A",
    "US5594469A",
    "US6160899A",
    "US6301370B1",
    "US7018211B1",
    "US6272231B1",
    "US6894714B2",
    "US7231423B1",
    "US7984099B1",
    "US7225227B2",
    "US7761505B2",
    "US6920942B2",
    "US7607097B2",
    "US7999843B2",
    "US8351586B2",
    "US7598942B2",
    "US20070100986A1",
    "US20070115348A1",
    "US20090187935A1",
    "US20080227438A1",
    "US20090015659A1",
    "US20090079813A1",
    "US8325214B2",
    "US8295462B2",
    "US8503654B1",
    "US20100013905A1",
    "US20100131866A1",
    "US8417551B2",
    "US20100220172A1",
    "US20100253689A1",
    "US20110029893A1"
  ]
}

Record 5,402 of 8,000 in Patents full text (MLC-0201). Request the full dataset.