# US 2021/0243386 A1 · Artificial intelligence display device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0243386 A1 - Document ID: US20210243386A1 - Status: Published application - Kind: A1 - Application number: 16/939,017 - Filed: 2020-07-26 - Published: 2021-08-05 - Earliest claimed: 2020-01-31 - Assignees: LG Electronics Inc. - Applicants: LG Electronics Inc. - Inventors: Chanyong PARK; Yunsuk KANG; Wonseok KANG - Web page: https://patentgrep.com/patent/US20210243386A1 ## CPC - H04N 5/2628: {Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation} - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - H04N 5/265: Mixing - H04N 7/181: {for receiving images from a plurality of remote sources} - H04N 23/698: for achieving an enlarged field of view, e.g. panoramic image capture - H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An artificial intelligence display device is disclosed. The artificial intelligence display device includes a display, and a processor configured to generate a monitoring image by using a plurality of images captured by a plurality of cameras, respectively, and control the display to display the monitoring image, in which the plurality of images includes a first image and a second image adjacent to the first image, and the processor is configured to generate a first corrected image obtained by compressing a first overlapped region overlapping the second image in the first image, generate a second corrected image obtained by compressing a second overlapped region overlapping the first image in the second image, and connect the first corrected image and the second corrected image. ## Claims ### Claim 1 An artificial intelligence device comprising: a plurality of cameras configured to capture a plurality of images, respectively, wherein the plurality of images includes at least a first image capturing a first portion of a space and a second image capturing a second portion of the space adjacent to the first portion of the space; a display; and a processor configured to: generate a first corrected image obtained by compressing a first overlapping region in the captured first image, wherein the first overlapping region overlaps the second captured image with respect to the first captured image; generate a second corrected image obtained by compressing a second overlapping region in the captured second image, wherein the second overlapping region overlaps the first captured image with respect to the second captured image; generate a monitoring image by associating the generated first corrected image and the generated second corrected image; and cause, on the display, a display of the generated monitoring image. ### Claim 2 (depends on 1) The artificial intelligence device of claim 1, wherein the first corrected image is generated by cropping a first partial region from the first image captured by a first camera from the plurality of cameras, and the second corrected image is generated by cropping a second partial region from the second image captured by a second camera from the plurality of cameras. ### Claim 3 (depends on 2) The artificial intelligence device of claim 2, wherein the corrected first image and the corrected second image are generated such that a first angle of view corresponding to the first image and a second angle of view corresponding to the second image correspond to a preset reference height. ### Claim 4 (depends on 3) The artificial intelligence device of claim 3, wherein the first overlapping region and the second overlapping region are compressed based at least in part on the preset reference height. ### Claim 5 (depends on 4) The artificial intelligence device of claim 4, wherein a first compression ratio of the first overlapping region increases toward an edge of the first image, and wherein a second compression ratio of the second overlapping region increases toward an edge of the second image. ### Claim 6 (depends on 1) The artificial intelligence device of claim 1, wherein the first camera and the second camera have an interval determined by a first angle of view corresponding to the first camera and a second angle of view corresponding to the second camera such that the first angle and the second angle correspond to a preset reference height, wherein the interval corresponds to a distance between the first camera and the second camera. ### Claim 7 (depends on 1) The artificial intelligence device of claim 1, wherein the plurality of cameras are arranged at regular intervals on a ceiling of the space to capture images of the space in a vertical direction such that image sensors from the plurality of cameras are positioned perpendicular to a floor, and wherein the monitoring image corresponds to a representation of the space in a plan view. ### Claim 8 (depends on 1) The artificial intelligence device of claim 1, wherein the monitoring image includes an object appearing in an unseparated form, wherein the object is positioned at a boundary between the first corrected image and the second corrected image. ### Claim 9 (depends on 1) The artificial intelligence device of claim 1, wherein compressing the first overlapping region and compressing the second overlapping region is based at least in part on associating a first moving speed of an object moving in a non-overlapping region of the first corrected image and a second moving speed of the object moving from the first corrected image to the second corrected image as a same speed. ### Claim 10 (depends on 1) The artificial intelligence device of claim 1, wherein the monitoring image includes an object positioned at a non-overlapping region of the first corrected image being a same size as the size of the object positioned at a boundary between the first corrected image and the second corrected image. ### Claim 11 (depends on 1) The artificial intelligence device of claim 1, wherein the processor is further configured to perform object tracking for an object appearing in the monitoring image by using the monitoring image. ### Claim 12 (depends on 11) The artificial intelligence device of claim 11, wherein the processor is further configured to: generate an averaged image obtained by averaging a plurality of frames for a predetermined time of the monitoring image, and generate an object image indicating a difference of the generated averaged image and a current frame, wherein the object tracking is performed using the generated object image. ### Claim 13 (depends on 12) The artificial intelligence device of claim 12, wherein the plurality of frames correspond to latest frames in the predetermined time. ### Claim 14 (depends on 12) The artificial intelligence device of claim 12, wherein the object tracking is performed by using a color distribution of an object appearing in the generated object image. ### Claim 15 A method comprising: capturing, by a plurality of cameras, a plurality of images, respectively, wherein the plurality of images includes at least a first image capturing a first portion of a space and a second image capturing a second portion of the space adjacent to the first portion of the space; generating a first corrected image obtained by compressing a first overlapping region in the captured first image, wherein the first overlapping region overlaps the second captured image with respect to the first captured image; generating a second corrected image obtained by compressing a second overlapping region in the captured second image, wherein the second overlapping region overlaps the first captured image with respect to the second captured image; generating a monitoring image by associating the generated first corrected image and the generated second corrected image; and displaying, on the display, the generated monitoring image. ### Claim 16 (depends on 15) The method of claim 15, wherein the first corrected image is generated by cropping a first partial region from the first image captured by a first camera from the plurality of cameras, and the second corrected image is generated by cropping a second partial region from the second image captured by a second camera from the plurality of cameras. ### Claim 17 (depends on 16) The method of claim 16, wherein the corrected first image and the corrected second image are generated such that a first angle of view corresponding to the first image and a second angle of view corresponding to the second image correspond to a preset reference height ### Claim 18 (depends on 17) The method of claim 17, wherein the first overlapping region and the second overlapping region are compressed based at least in part on the preset reference height. ### Claim 19 (depends on 15) The method of claim 15, wherein the plurality of cameras are arranged at regular intervals on a ceiling of the space to capture images of the space in a vertical direction such that image sensors from the plurality of cameras are positioned perpendicular to a floor, and wherein the monitoring image corresponds to a representation of the space in a plan view.