# US 2019/0318496 A1 · Preventing intrusion during video recording or streaming > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318496 A1 - Document ID: US20190318496A1 - Status: Published application - Kind: A1 - Application number: 15/950,228 - Filed: 2018-04-11 - Published: 2019-10-17 - Earliest claimed: 2018-04-11 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Fang Lu; Dan Zhang; Jing Ran Yang; Ye Xu; Ke Huan Yin; Tai Mei Zhang - Web page: https://patentgrep.com/patent/US20190318496A1 ## CPC - G06V 20/30: in albums, collections or shared content, e.g. social network photos or video - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06V 10/143: Sensing or illuminating at different wavelengths - 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) - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/172: {Classification, e.g. identification} - G06T 2207/10016: Video; Image sequence - G06T 2207/20224: Image subtraction - G06T 2207/30242: Counting objects in image - H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract According to one or more embodiments, a method, a computer program product, and a computer system for preventing intrusion during video recording or streaming are provided. According to the method, at first, a camera of a device may capture a scene into a video, then the device may store frame-series images of the video into a cache. The device may then detect whether there is at least one intruder in the scene, and then in response to the at least one intruder being detected in the scene, the device may eliminate the at least one intruder from the cached frame-series images. ## Claims ### Claim 1 A method for preventing intrusion during video recording or streaming, the method comprising: capturing, by a camera of a device, a scene into a video; storing, by the device, frame-series images of the video into a cache; detecting, by the device, whether there is at least one intruder in the scene; and eliminating, by the device, the at least one intruder from the cached frame-series images in response to the at least one intruder being detected in the scene. ### Claim 2 (depends on 1) The method of claim 1, further comprising: enabling, by the device, the cached frame-series images without the intruder to be viewed. ### Claim 3 (depends on 1) The method of claim 1, wherein there is an infrared camera on the device, and frame-series images for the scene taken by the infrared camera is used to detect whether there is at least one intruder in the scene. ### Claim 4 (depends on 1) The method of claim 1, wherein the detecting, by the device, whether there is at least one intruder in the scene comprise: determining, by the device, a reference image in the frame-series images in which there is at least one object to be included in the scene; determining, by the device, a first count of the object(s) to be included in the scene for the reference image; determining, by the device, a second count of object(s) included in the scene for a second image in the frame-series images; and determining, by the device, there is at least one intruder in the second image in response to the second count being bigger than the first count. ### Claim 5 (depends on 1) The method of claim 1, wherein the eliminating, by the device, the at least one intruder from the cached frame-series images comprising: for an image to be processed in the cached frame-series images, wherein there is at least one intruder in the image to be processed: determining, by the device, a reference image in which there is no intruder; determining, by the device, at least one contour of the at least one intruder in the image to be processed; determining, by the device, at least one area covering the at least one contour respectively; determining, by the device, at least one location associated with the at least one area; and replacing, by the device, pixels in the at least one location in the image to be processed with pixels in the at least one location in the reference image. ### Claim 6 (depends on 1) The method of claim 1, wherein the eliminating, by the device, the at least one intruder from the cached video comprising: for an image to be processed in the cached frame-series images, wherein there is at least one intruder in the image to be processed: determining, by the device, at least one contour of the at least one intruder in the image to be processed; determining, by the device, a region excluding the at least one contour in the image to be processed; and generating, by the device, a new image based on image in the region. ### Claim 7 A computing system for preventing intrusion during video recording or streaming, the computer system comprising a computer processor coupled to a computer-readable memory unit, said memory unit comprising instructions that when executed by the computer processor implements a method comprising: capturing a scene into a video; storing frame-series images of the video into a cache; detecting whether there is at least one intruder in the scene; and eliminating the at least one intruder from the cached frame-series images in response to the at least one intruder being detected in the scene. ### Claim 8 (depends on 7) The computer system of claim 7, the method further comprising: enabling, by the device, the cached frame-series images without the intruder to be viewed. ### Claim 9 (depends on 7) The computer system of claim 7, wherein there is an infrared camera on the device, and frame-series images for the scene taken by the infrared camera is used to detect whether there is at least one intruder in the scene. ### Claim 10 (depends on 7) The computer system of claim 7, wherein the detecting, by the device, whether there is at least one intruder in the scene comprise: determining, by the device, a reference image in the frame-series images in which there is at least one object to be included in the scene; determining, by the device, a first count of the object(s) to be included in the scene for the reference image; determining, by the device, a second count of object(s) included in the scene for a second image in the frame-series images; and determining, by the device, there is at least one intruder in the second image in response to the second count being bigger than the first count. ### Claim 11 (depends on 7) The computer system of claim 7, wherein the eliminating the at least one intruder from the cached frame-series images comprising: for an image to be processed in the cached frame-series images, wherein there is at least one intruder in the image to be processed: determining, by the device, a reference image in the cached frame-series images in which there is no intruder; determining, by the device, at least one contour of the at least one intruder in the image to be processed; determining, by the device, at least one area covering the at least one contour respectively; determining, by the device, at least one location associated with the at least one area; and replacing, by the device, pixels in the at least one location in the image to be processed with pixels in the at least one location in the reference image. ### Claim 12 (depends on 7) The computer system of claim 7, wherein the eliminating the at least one intruder from the cached video comprising: for an image to be processed in the cached frame-series images, wherein there is at least one intruder in the image to be processed: determining, by the device, at least one contour of the at least one intruder in the image to be processed; determining, by the device, a region excluding the at least one contour in the image to be processed; and generating, by the device, a new image based on image in the region. ### Claim 13 A computer program product for preventing intrusion during video recording or streaming, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform an operation comprising: capturing a scene into a video; storing frame-series images of the video into a cache; detecting whether there is at least one intruder in the scene; and eliminating the at least one intruder from the cached frame-series images in response to the at least one intruder being detected in the scene. ### Claim 14 (depends on 13) The computer program product of claim 13, the operation further comprising: enabling, by the device, the cached frame-series images without the intruder to be viewed. ### Claim 15 (depends on 13) The computer program product of claim 13, wherein there is an infrared camera on the device, and frame-series images for the scene taken by the infrared camera is used to detect whether there is at least one intruder in the scene. ### Claim 16 (depends on 13) The computer program product of claim 13, wherein the detecting, by the device, whether there is at least one intruder in the scene comprise: determining, by the device, a reference image in the frame-series images in which there is at least one object to be included in the scene; determining, by the device, a first count of the object(s) to be included in the scene for the reference image; determining, by the device, a second count of object(s) included in the scene for a second image in the frame-series images; and determining, by the device, there is at least one intruder in the second image in response to the second count being bigger than the first count. ### Claim 17 (depends on 13) The computer program product of claim 13, wherein the eliminating the at least one intruder from the cached frame-series images comprising: for an image to be processed in the cached frame-series images, wherein there is at least one intruder in the image to be processed: determining, by the device, a reference image in the cached frame-series images in which there is no intruder; determining, by the device, at least one contour of the at least one intruder in the image to be processed; determining, by the device, at least one area covering the at least one contour respectively; determining, by the device, at least one location associated with the at least one area; and replacing, by the device, pixels in the at least one location in the image to be processed with pixels in the at least one location in the reference image. ### Claim 18 (depends on 13) The computer program product of claim 13, wherein the eliminating the at least one intruder from the cached video comprising: for an image to be processed in the cached frame-series images, wherein there is at least one intruder in the image to be processed: determining, by the device, at least one contour of the at least one intruder in the image to be processed; determining, by the device, a region excluding the at least one contour in the image to be processed; and generating, by the device, a new image based on image in the region.