US 12,406,460 B2
Image processing apparatus, image processing method, and storage medium
Michihiko Ono, Kanagawa (JP)
Assigned to Canon Kabushiki Kaisha, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Jan. 17, 2023, as Appl. No. 18/155,243.
Claims priority of application No. 2022-019591 (JP), filed on Feb. 10, 2022.
Prior Publication US 2023/0252753 A1, Aug. 10, 2023
Int. Cl. G06V 10/25 (2022.01); G06T 7/70 (2017.01); G06V 20/52 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01)
CPC G06V 10/25 (2022.01) [G06T 7/70 (2017.01); G06V 20/52 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01); G06T 2207/30196 (2013.01); G06T 2207/30232 (2013.01)] 13 Claims
OG exemplary drawing
 
1. An image processing apparatus comprising:
at least one processor or circuit configured to function so as to perform:
(1) detecting a plurality of subjects from an image that has been captured;
(2) detecting an independent subject from among the plurality of subjects that have been detected, wherein the independent subject includes a subject for which other subjects are not present in a predetermined range of the subject;
(3) measuring a residence time of the plurality of subjects that have been detected;
(4) determining a degree of priority for the plurality of subjects that have been detected such that the degree of priority becomes higher for a subject that is independent and that has a relatively longer residence time, based on (a) results of a detection in the independent subject detecting, and (b) measurement results that have been measured in the residence time measuring;
(5) performing predetermined image processing on the plurality of subjects up to a predetermined upper limit for a number of subjects in order from those with a higher degree of priority, wherein the predetermined image processing includes pose estimation processing that estimates poses for the plurality of subjects; and
(6) causing a warning to be generated in a case in which a predetermined behavior has been detected, and halting at least a part of the predetermined image processing for a subject that triggered the warning after the warning is generated.