# US 2018/0293457 A1 · System and method for background subtraction in video content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0293457 A1 - Document ID: US20180293457A1 - Status: Published application - Kind: A1 - Application number: 15/485,010 - Filed: 2017-04-11 - Published: 2018-10-11 - Earliest claimed: 2017-04-11 - Assignees: Sony Corporation - Applicants: Sony Corporation - Inventors: Pingshan LI - Web page: https://patentgrep.com/patent/US20180293457A1 ## CPC - G06T 7/11: Region-based segmentation - G06F 18/2321: using statistics or function optimisation, e.g. modelling of probability density functions - G06T 7/136: involving thresholding - G06T 7/143: involving probabilistic approaches, e.g. Markov random field [MRF] modelling - G06T 7/194: involving foreground-background segmentation - G06T 7/215: Motion-based segmentation - G06V 10/462: {Salient features, e.g. scale invariant feature transforms [SIFT]} - G06V 10/763: {Non-hierarchical techniques, e.g. based on statistics of modelling distributions} - G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) - G06T 2207/10016: Video; Image sequence - G06T 2207/10024: Color image - G06T 2207/30221: Sports video; Sports image - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Various aspects of a system and a method for background subtraction in video content are disclosed herein. The system includes an electronic device, which generates an optical flow image of an image frame from a sequence of image frames. A first distribution is determined based on pixel values of a plurality of pixels of the generated optical flow image. A second distribution is determined based on pixel values of a set of pixels of the plurality of pixels of the generated optical flow image. The set of pixels correspond to pixels that touch one or more borders of the image frame. A third distribution is further determined based on the determined first distribution and the determined second distribution. One or more peak values corresponding to one or more background regions in the generated optical flow image, are determined within a specified threshold range in the determined third distribution. ## Claims ### Claim 1 A system for background subtraction in video content, said system comprising: one or more circuits in an electronic device configured to: generate an optical flow image of an image frame from a sequence of image frames of said video content; determine a first distribution based on pixel values of a plurality of pixels of said generated optical flow image; determine a second distribution based on pixel values of a set of pixels of said plurality of pixels of said generated optical flow image, wherein said set of pixels corresponds to pixels that touch one or more borders of said image frame; determine a third distribution based on said determined first distribution and said determined second distribution; and determine one or more peak values within a specified threshold range in said determined third distribution, wherein said determined one or more peak values correspond to one or more background regions in said generated optical flow image. ### Claim 2 (depends on 1) The system according to claim 1, wherein said one or more circuits are configured to capture said sequence of image frames of said video content. ### Claim 3 (depends on 1) The system according to claim 1, wherein said set of pixels corresponds to a plurality of pixels in said one or more background regions in said generated optical flow image. ### Claim 4 (depends on 1) The system according to claim 1, wherein said generated optical flow image further includes at least a background region comprising pixels that touches said one or more borders of said image frame. ### Claim 5 (depends on 4) The system according to claim 4, wherein said one or more circuits are further configured to subtract said one or more background regions from said generated optical flow image for detection of at least said foreground region. ### Claim 6 (depends on 5) The system according to claim 5, wherein said one or more circuits are further configured to reduce noise in at least said detected foreground region based on a determined threshold value. ### Claim 7 (depends on 5) The system according to claim 5, wherein said one or more circuits are further configured to configured to flatten a background in said optical flow image before said subtraction of said one or more background regions when pixels values in said background in said optical flow image exhibit a gradual change, wherein said flattening is done by using an estimated gradient value of said background. ### Claim 8 (depends on 1) The system according to claim 1, wherein one or more parameters are associated with a plurality of pixels in said one or more background regions in said generated optical flow image. ### Claim 9 (depends on 8) The system according to claim 8, wherein a type of each of said one or more background regions is based on said one or more parameters. ### Claim 10 (depends on 8) The system according to claim 8, wherein said one or more parameters correspond to intrinsic factors associated with said generated optical flow image and extrinsic factors associated with said electronic device. ### Claim 11 A method for background subtraction in video content, said method comprising: in one or more circuits: generating an optical flow image of an image frame from a sequence of image frames of said video content; determining a first distribution based on pixel values of a plurality of pixels of said generated optical flow image; determining a second distribution based on pixel values of a set of pixels of said plurality of pixels of said generated optical flow image, wherein said set of pixels corresponds to pixels that touch one or more borders of said image frame; determining a third distribution based on said determined first distribution and said determined second distribution; and determining one or more peak values within a specified threshold range in said determined third distribution, wherein said determined one or more peak values correspond to one or more background regions in said generated optical flow image. ### Claim 12 (depends on 11) The method according to claim 11, further comprising capturing said sequence of image frames of said video content. ### Claim 13 (depends on 11) The method according to claim 11, wherein said set of pixels corresponds to a plurality of pixels in said background in said generated optical flow image. ### Claim 14 (depends on 11) The method according to claim 11, wherein said generated optical flow image further includes at least a background region comprising pixels that touches said one or more borders of said image frame. ### Claim 15 (depends on 14) The method according to claim 14, further comprising subtracting said one or more background regions from said generated optical flow image for detecting at least said foreground region. ### Claim 16 (depends on 15) The method according to claim 15, further comprising reducing noise in at least said detected foreground region based on a determined threshold value. ### Claim 17 (depends on 11) The method according to claim 11, wherein one or more parameters are associated with a plurality of pixels in said one or more background regions in said generated optical flow image. ### Claim 18 (depends on 17) The method according to claim 17, wherein a type of each of said one or more background regions is based on said one or more parameters. ### Claim 19 (depends on 17) The method according to claim 17, wherein said one or more parameters correspond to intrinsic factors associated with said generated optical flow image and extrinsic factors associated with said electronic device. ### Claim 20 A non-transitory computer-readable storage medium having stored thereon, a set of computer executable instructions, for causing a system to perform steps comprising: generating an optical flow image of an image frame from a sequence of image frames of said video content; determining a first distribution based on pixel values of a plurality of pixels of said generated optical flow image; determining a second distribution based on pixel values of a set of pixels of said plurality of pixels of said generated optical flow image, wherein said set of pixels corresponds to pixels that touch one or more borders of said image frame; determining a third distribution based on said determined first distribution and said determined second distribution; and determining one or more peak values within a specified threshold range in said determined third distribution, wherein said determined one or more peak values correspond to one or more background regions in said generated optical flow image.