# US 8,570,359 B2 · Video region of interest features > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,570,359 B2 - Document ID: US8570359B2 - Status: Granted - Kind: B2 - Application number: 12/185,492 - Filed: 2008-08-04 - Published: 2010-02-04 - Granted: 2013-10-29 - Earliest claimed: 2008-08-04 - Assignees: Microsoft Corporation - Applicants: Walid Ali; Ronald Boskovic - Inventors: Walid Ali; Ronald Boskovic - Web page: https://patentgrep.com/patent/US8570359B2 ## CPC - H04N 7/152: {Multipoint control units therefor} - G06V 40/162: {using pixel segmentation or colour matching} - H04N 7/147: {Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q)} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Embodiments are configured to provide video conferencing functionality including using region of interest (ROI) features to provide a video signal, but the embodiments are not so limited. In an embodiment, components of a video conferencing system can operate to provide a video signal using pixel data associated with a ROI. In one embodiment, a video conference device can include a detector that can be used to detect human flesh tone regions in a video scene as part of providing a video stream to one or more conference participants. ## Claims ### Claim 1 A method of providing a video signal comprising: capturing pixel data associated with a conferencing environment; determining whether a captured pixel is included within a defined region of interest (ROI) defined in part by a number of boundaries comprising at least three boundaries defined in part by three equations including r +g <1 that use red (r) pixel values associated with a normalized red axis and green (g) pixel values associated with a normalized green axis; designating the captured pixel as a ROI pixel if the captured pixel is included within the defined ROI; and, using an augmented detection region associated with the defined ROI to enhance distinguishing participant features as part of allocating more of a bandwidth budget to human participants and less of the bandwidth budget to other visual aspects of a surrounding scene of the conferencing environment. ### Claim 2 (depends on 1) The method of claim 1, further comprising defining the ROI based in part on red-green-blue (RGB) pixel parameter boundaries and quantizing the captured pixel data based in part on a pixel designation. ### Claim 3 (depends on 1) The method of claim 1, further comprising communicating the captured pixel data, including information associated with ROI pixels, for a quantization operation. ### Claim 4 (depends on 1) The method of claim 1, further comprising communicating the captured pixel data, including information associated with ROI pixels, for an encoding operation. ### Claim 5 (depends on 1) The method of claim 1, further comprising allocating processing bandwidth based in part on a pixel designation. ### Claim 6 (depends on 1) The method of claim 1, further comprising redistributing processing operations based in part on a pixel designation. ### Claim 7 (depends on 1) The method of claim 1, further comprising using the augmented detection region as part of augmenting designated ROI pixel data with additional pixel data based in part on an augmentation operation associated with a ROI pixel. ### Claim 8 (depends on 7) The method of claim 7, further comprising quantizing augmented and ROI pixel data based in part on a quantization factor. ### Claim 9 (depends on 1) The method of claim 1, further comprising quantizing the captured pixel data based in part on a flag associated with a ROI pixel. ### Claim 10 (depends on 1) The method of claim 1, further comprising flagging captured pixels with pixel values based in part on whether captured pixel parameters correspond to the ROI. ### Claim 11 (depends on 1) The method of claim 1, further comprising defining the ROI by linear boundaries, each linear boundary comprising a linear equation associated with a normalized RGB space, wherein intersections and the linear boundaries define aspects of the ROI. ### Claim 12 (depends on 1) The method of claim 1, further comprising communicating encoded pixel data associated with the ROI to one or more conference participants. ### Claim 13 (depends on 1) The method of claim 1, wherein the capturing occurs within a camera or computing device. ### Claim 14 A video conference device operable to provide a video stream to one or more participants, the video conference device comprising: a detector operable to: detect if a ROI pixel is included with captured pixel data based in part on whether a captured pixel is associated with a ROI defined in part by a number of region boundaries, wherein the number of region boundaries are associated with a RGB space and comprise at least three region boundaries defined in part by three equations including r +g <1 that use red (r) pixel values associated with a normalized red axis and green (g) pixel values associated with a normalized green axis; identify the captured pixel as the ROI pixel if the captured pixel is included within the ROI; use an augmented detection region associated with the ROI to enhance distinguishing participant features as part of allocating more of a bandwidth budget to human participants and less of the bandwidth budget to other visual aspects of a surrounding scene; and, output the pixel data based in part on an identified ROI pixel. ### Claim 15 (depends on 14) The video conference device of claim 14, further comprising a camera for capturing pixel data. ### Claim 16 (depends on 14) The video conference device of claim 14, further comprising a camera which includes the detector. ### Claim 17 A video conferencing system comprising: a camera to capture pixel data associated with a video scene; a detector operable to: detect ROI pixel data associated with the captured pixel data if the captured pixel data includes a pixel corresponding with a ROI comprising at least three boundaries defined in part by three equations including r +g <1 that use red (r) pixel values associated with a normalized red axis and green (g) pixel values associated with a normalized green axis corresponding to pixel parameters associated with human skin and a RGB space; flag the ROI pixel data to designate the ROI pixel data as corresponding with the ROI, wherein one or more flags can be used for additional processing operations; and, use an augmented detection region associated with the ROI to enhance distinguishing participant features as part of allocating more of a bandwidth budget to human participants and less of the bandwidth budget to other visual aspects of the visual scene. ### Claim 18 (depends on 17) The system of claim 17, further comprising a video engine to process the pixel data based in part on the one or more flags. ### Claim 19 (depends on 17) The system of claim 17, wherein the camera includes the detector. ### Claim 20 (depends on 17) The system of claim 17, wherein the ROI is defined as including one or more color-based boundaries.