# US 12,223,664 B2 · Image processing apparatus, image processing method, and non-transitory computer-readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,664 B2 - Document ID: US12223664B2 - Status: Granted - Kind: B2 - Application number: 17/743,530 - Filed: 2022-05-13 - Published: 2022-12-01 - Granted: 2025-02-11 - Earliest claimed: 2021-06-01 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Toshiya Komata - Web page: https://patentgrep.com/patent/US12223664B2 ## CPC - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06T 7/254: involving subtraction of images - G06T 7/248: {involving reference images or patches} - G06T 2207/10016: Video; Image sequence - G06T 2207/20224: Image subtraction - G06T 2207/30196: Human being; Person - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An image processing apparatus comprises an acquisition unit configured to acquire reference information which indicates at least one of a number of objects detected from a frame, a density of an object in a frame, or a frame rate, and a tracking unit configured to track an identical object between frames. The tracking unit determines that each of objects for which a difference in a detection position between the frames is smaller than a threshold value corresponding to the reference information is an identical object, and does not determine that each of objects for which a difference in the detection position between the frames is equal to or larger than the threshold value is an identical object. ## Claims ### Claim 1 An image processing apparatus comprising: at least one processor; and at least one memory having stored thereon instructions which, when executed by the at least one processor, cause the image processing apparatus at least to: acquire reference information which indicates at least one of a number of objects detected from a frame, a density of an object in a frame, or a frame rate; and track an identical object between frames, wherein the tracking determines that each of objects for which a difference in a detection position between the frames is smaller than a threshold value corresponding to the reference information is an identical object, and does not determine that each of objects for which a difference in the detection position between the frames is equal to or larger than the threshold value is an identical object. ### Claim 2 (depends on 1) The image processing apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, further cause the image processing apparatus at least to: set the threshold value in accordance with the reference information. ### Claim 3 (depends on 2) The image processing apparatus according to claim 2, wherein a threshold value set in a case where the number is a first number is larger than a threshold value set in a case where the number is a second number larger than the first number. ### Claim 4 (depends on 2) The image processing apparatus according to claim 2, wherein a threshold value set in a case where the density is a first density is larger than a threshold value set in a case where the density is a second density higher than the first density. ### Claim 5 (depends on 2) The image processing apparatus according to claim 2, wherein a threshold value set in a case where the frame rate is a first frame rate is larger than a threshold value set in a case where the frame rate is a second frame rate higher than the first frame rate. ### Claim 6 (depends on 1) The image processing apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, further cause the image processing apparatus at least to: determine, in accordance with the threshold value, a size of a region that is set on the frame and in which detection and tracking of an object are performed. ### Claim 7 (depends on 6) The image processing apparatus according to claim 6, wherein the determining determines the size of the region such that the size of the region increases consistently with the threshold value being larger and that the size of the region decreases consistently with the threshold value being smaller. ### Claim 8 (depends on 1) The image processing apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, further cause the image processing apparatus at least to: acquire, as the frame, an image of each frame in a moving image or a still image periodically or aperiodically captured. ### Claim 9 (depends on 1) The image processing apparatus according to claim 1, wherein the object is a moving object. ### Claim 10 (depends on 1) The image processing apparatus according to claim 1, wherein the threshold value is a maximum distance that the object is allowed to move between frames. ### Claim 11 An image processing method performed by an image processing apparatus, the image processing method comprising: acquiring reference information which indicates at least one of a number of objects detected from a frame, a density of an object in a frame, or a frame rate; and tracking an identical object between frames, wherein in the tracking, each of objects for which a difference in a detection position between the frames is smaller than a threshold value corresponding to the reference information is determined to be an identical object, and each of objects for which a difference in the detection position between the frames is equal to or larger than the threshold value is not determined to be an identical object. ### Claim 12 A non-transitory computer-readable storage medium in which a computer program is stored, the computer program causing a computer to: acquire reference information which indicates at least one of a number of objects detected from a frame, a density of an object in a frame, or a frame rate; and track an identical object between frames, wherein the tracking determines that each of objects for which a difference in a detection position between the frames is smaller than a threshold value corresponding to the reference information is an identical object, and does not determine that each of objects for which a difference in the detection position between the frames is equal to or larger than the threshold value is an identical object.