Canon Kabushiki Kaisha

Kuniaki Sugitani

Yasuyuki Suzuki

Takumi Takehara

Hideyuki Hamano

Akihiko Kanda

Minoru Hirose

Naoki Iwasaki

Kengo Takeuchi

Satoshi Kimoto

Yu Inagaki

Takayuki Akaguma

Ryotaro Takahashi

Maiko Takao

There is provided an inference apparatus. An inference unit performs inference with use of a machine learning model based on a subject region including a subject within an image obtained through shooting, and on a plurality of distance information pieces detected from a plurality of focus detection regions inside the subject region, thereby generating an inference result indicating a distance information piece corresponding to the subject or a distance information range corresponding to the subject. The machine learning model is a model that has been trained to suppress a contribution made to the inference result by one or more distance information pieces that are not based on the subject among the plurality of distance information pieces.

Inference apparatus, image capturing apparatus, training apparatus, inference method, training method, and storage medium

An image capturing apparatus includes a memory device that stores a set of instructions, and at least one processor that executes the set of instructions to function as, a first detection unit configured to detect a position of a gazing point in an image based on a line-of-sight of a user, a first setting unit configured to set an object detection range based on the position of the gazing point and an image capturing condition, a second detection unit configured to detect a feature area from the image, and a second setting unit configured to set a focus detection area based on a position of the feature area included in the object detection range.

Image capturing apparatus and control method thereof

A device includes a focus detection unit configured to detect a defocus amount based on a focus detection signal output from an image capturing device, an object detection unit configured to detect a specific object based on image data output from the image capturing device, and a processing unit configured to perform first obstacle detection processing detecting an obstacle based on characteristics of the defocus amount on the specific object, and to perform second obstacle detection processing detecting an obstacle higher in spatial frequency than the specific object.

Control device, image capturing apparatus, and control method for detecting obstacle

A microcomputer estimates information corresponding to an image plane position of an object based on a sequential identification method using a focus detection result. Moreover, the microcomputer predicts information corresponding to a future image plane position of the object based on the estimated information corresponding to the image plane position of the object. The microcomputer controls driving of a focus lens based on the predicted information corresponding to the future image plane position of the object. In accordance with information corresponding to a motion of the object, the microcomputer selects by which of a first Kalman filter and a second Kalman filter the information corresponding to the future image plane position of the object is predicted by using the estimated information corresponding to the image plane position of the object.

Lens control apparatus and method for controlling the same

A lens apparatus including a focus lens is attachable to and detachable from an image capturing apparatus. An image sensor photoelectrically converts an optical image formed through the lens apparatus. An image generation unit generates an image based on an image signal output from the image capturing apparatus. An image magnification variation correction control unit receives information about a variation in focal length from the lens apparatus by a lens communication control unit configured to control communication with the lens apparatus, and the image magnification variation correction control unit corrects a magnification of the image based on the received information.

A control apparatus () includes a focus detection unit () that detects a defocus amount, a control unit () that automatically changes a parameter relating to a tracking operation during the tracking operation depending on an image capturing state, and a focusing unit () that preforms focusing based on the defocus amount and the parameter.

Control apparatus, image capturing apparatus, and non-transitory computer-readable storage medium

Based on information corresponding to a state of an object at a first time, information corresponding to the state of the object at a second time after the first time is estimated. The information corresponding to the state of the object at the second time is calculated by correcting the estimated information corresponding to the state of the object at the second time based on a focus detection result detected by a focus detection unit at the second time. Based on the information corresponding to the state of the object at the second time and information of time from the second time to a third time after the second time, an image plane position at the third time is predicted. Based on the image plane position predicted by a first prediction unit, driving of a focus lens is controlled.

Lens control apparatus and control method for tracking moving object

An imaging apparatus that performs continuous imaging, includes: a focus detection unit that perform focus detection and calculates an amount of defocus in each of a plurality of imaging operations; a position detection unit that detects an image plane position corresponding to a subject position using the amount of defocus; an estimation unit that estimates a next image plane position using a plurality of pairs of data regarding the image plane position and a time at which the amount of defocus has been detected; and a turnabout determination unit that determines whether a subject is a turnabout subject, which is a subject that moves towards the imaging apparatus, changes direction of movement, and then moves away from the imaging apparatus. The number of pairs of data used for the estimation decreases based on a ratio of a highest image plane speed in past scenes to a current image plane speed.

Growing community of inventors

Kawasaki, Japan

Kuniaki Sugitani