US 12,243,265 B2
Image processing apparatus that tracks object and image processing method
Hiroyasu Katagawa, Kanagawa (JP); Yasushi Ohwa, Tokyo (JP); Takahiro Usami, Tokyo (JP); Hiroyuki Yaguchi, Chiba (JP); Tomotaka Uekusa, Kanagawa (JP); Yukihiro Kogai, Tokyo (JP); and Toru Aida, Tokyo (JP)
Assigned to Canon Kabushiki Kaisha, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Mar. 24, 2022, as Appl. No. 17/703,611.
Claims priority of application No. 2021-053344 (JP), filed on Mar. 26, 2021.
Prior Publication US 2022/0309706 A1, Sep. 29, 2022
Int. Cl. G06T 7/73 (2017.01); G06V 10/42 (2022.01); G06V 10/72 (2022.01); G06V 10/80 (2022.01)
CPC G06T 7/74 (2017.01) [G06V 10/42 (2022.01); G06V 10/72 (2022.01); G06V 10/80 (2022.01); G06T 2207/20076 (2013.01)] 13 Claims
OG exemplary drawing
 
1. An image processing apparatus comprising:
at least one processor and a memory holding a program which makes the processor function as:
an analysis unit configured to analyze an image;
an extraction unit configured to extract a reference image corresponding to a specific object; and
a first correlation calculation unit and a second correlation calculation unit configured to estimate an area having a high correlation in an input image by using the reference image,
wherein the first correlation calculation unit is a correlation calculation unit configured to execute presumption based on components including a direct current (DC) component,
wherein the second correlation calculation unit is a correlation calculation unit configured to execute presumption based on an alternate current (AC) component, from which the DC component is eliminated,
wherein estimation of the area is performed by switching the first correlation calculation unit and the second correlation calculation unit based on at least any one of a detection result of the specific object, a feature amount of the specific object, and an analysis result of an imaging scene acquired by the analysis unit, and
wherein the first correlation calculation unit uses any one of a sum of absolute difference, a sum of squared difference, and a normalized correlation coefficient, and the second correlation calculation unit uses any one of a zero-mean sum of absolute difference, a zero-mean sum of squared difference, and a zero-mean normalized correlation coefficient.