# US 12,015,847 B2 · Image processing apparatus for changing a priority category for object detection, image pickup apparatus, image processing method, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,015,847 B2 - Document ID: US12015847B2 - Status: Granted - Kind: B2 - Application number: 17/991,896 - Filed: 2022-11-22 - Published: 2023-03-23 - Granted: 2024-06-18 - Earliest claimed: 2020-02-19 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Hitoshi Ikeda - Web page: https://patentgrep.com/patent/US12015847B2 ## CPC - H04N 23/675: {comprising setting of focusing regions} - H04N 23/61: based on recognised objects - H04N 23/62: Control of parameters via user interfaces - H04N 23/631: {Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters} - H04N 23/667: Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes - H04N 23/695: Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract An image processing apparatus that can easily change the categories of the main object, comprises, an object detection unit for detecting an object categorized as one of at least two categories from an image, a setting unit for setting a first category as a priority category on an object having a predetermined priority among one of the objects detected by the object detection unit; and a region designation unit for designating a predetermined region on an object on a display screen, wherein the setting unit can change the priority category from the first category to a second category different from the first category when the predetermined region of the object designated by the region designation unit is the second category. ## Claims ### Claim 1 An image processing apparatus comprising: at least one processor or circuit configured to function as: an object detection unit configured to detect objects categorized as at least two categories from an image; a setting unit configured to set a first category as a main category so that an object of the main category is to be tracked by a tracking unit; and a region designation unit configured to designate a predetermined region on a display screen as a region including a main object, wherein the setting unit is configured to change the main category from the first category to a second category different from the first category in a case where the object detected by the object detection unit on the predetermined region designated by the region designation unit is the second category, and wherein the setting unit is configured to set the second category as an initial main category in a case where an image pickup operation is started by using a predetermined operation unit after the setting unit changes the main category from the first category to the second category. ### Claim 2 (depends on 1) The image processing apparatus according to claim 1, wherein the region designation unit designates the predetermined region in a case where the predetermined region on the display screen is touched. ### Claim 3 (depends on 1) The image processing apparatus according to claim 1, wherein the region designation unit designates the predetermined region in a case where the predetermined region on the display screen is designated by a pointing device. ### Claim 4 (depends on 1) The image processing apparatus according to claim 1, wherein the region designation unit designates the predetermined region according to setting a focus detection region on the display screen. ### Claim 5 (depends on 4) The image processing apparatus according to claim 4, wherein the region designation unit designates the predetermined region in a case where the focus detection region is set on the display screen and then focus detection is started by operating a predetermined operation unit. ### Claim 6 (depends on 5) The image processing apparatus according to claim 5, wherein the predetermined operation unit includes a shutter release button. ### Claim 7 (depends on 1) The image processing apparatus according to claim 1, wherein the setting unit is configured to set the first category by using a menu selection on the display screen. ### Claim 8 (depends on 1) The image processing apparatus according to claim 1, wherein the at least one processor or circuit is further configured to function as the tracking unit configured to track the object on the predetermined region designated by the region designation unit based on color information or luminance information extracted from the predetermined region. ### Claim 9 (depends on 1) The image processing apparatus according to claim 1, further comprising a display unit configured to display the object corresponding to the main category differently from other object. ### Claim 10 (depends on 9) The image processing apparatus according to claim 9, wherein the display unit is configured to display a frame on the object detected by the object detection unit. ### Claim 11 (depends on 10) The image processing apparatus according to claim 10, wherein the setting unit is configured to set a category for the object corresponding to which the display unit displays the frame. ### Claim 12 (depends on 1) The image processing apparatus according to claim 1, wherein the at least one processor or circuit is further configured to function as the tracking unit that adjusts a focus condition of a focus lens or an exposure condition of a light amount to an image pickup unit on a priority basis with regard to the predetermined region of the object of which category is corresponding to the main category. ### Claim 13 (depends on 1) The image processing apparatus according to claim 1, wherein the object detection unit detects the objects based on learning models generated by a machine learning, and when the setting unit sets the main category on the object, the object detection unit detects the object based on the learning models corresponding to the object. ### Claim 14 (depends on 13) The image processing apparatus according to claim 13, wherein the object detection unit detects the object exclusively using a learning model generated by the machine learning corresponding to the object on which the setting unit sets the main category. ### Claim 15 (depends on 1) The image processing apparatus according to claim 1, wherein the object detection unit is configured to detect a part of the object. ### Claim 16 An image pickup apparatus comprising: at least one processor or circuit configured to function as: an image pickup unit configured to obtain an object image; an object detection unit configured to detect objects categorized as at least two categories from the object image obtained by the image pickup unit; a setting unit configured to set a first category as a main category so that an object of the main category is to be tracked by a tracking unit; and a region designation unit configured to designate a predetermined region on a display screen as a region including a main object; wherein the setting unit is configured to change the main category from the first category to a second category different from the first category in a case where the object detected by the object detection unit on the predetermined region designated by the region designation unit is the second category, and wherein the setting unit is configured to set the second category as an initial main category in a case where an image pickup operation is started by a predetermined operation unit after the setting unit changes the main category from the first category to the second category. ### Claim 17 An image processing method comprising: detecting objects categorized as at least two categories from an image; setting a first category as a main category so that an object of the main category is to be tracked by a tracking unit; and designating a predetermined region on a display screen as a region including a main object; wherein the main category is changed from the first category to a second category different from the first category in a case where the object detected by the detecting on the predetermined region designated by the designating is the second category, and wherein the second category is set as an initial main category in the setting in a case where an image pickup operation is started by a predetermined operation unit after the main category is changed from the first category to the second category. ### Claim 18 A non-transitory computer-readable storage medium that stores a computer program for executing the following: detecting objects categorized as at least two categories from an image; setting a first category as a main category so that an object of the main category is to be tracked by a tracking unit; and designating a predetermined region on a display screen as a region including a main object; wherein the main category is changed from the first category to a second category different from the first category in a case where the object detected by the detecting on the predetermined region designated by the designating is the second category type, and wherein the second category is set as an initial main category in the setting in a case where an image pickup operation is started by a predetermined operation unit after the main category is changed from the first category to the second category.