Information processing device configured to detect a subject from an image and extract a feature point from the subject, information processing method, program and electronic apparatus
AssigneeSony Corporation
InventorHideaki Ishioka
Life of this patent
Estimating the term…
Abstract
An information processing device, method, program, and electronic apparatus are provided for operating an information processing device without a sense of discomfort regardless of a distance between the information processing device and a user. The information processing device, method, program, and electronic apparatus detect a subject from an image and extract a feature point from the subject. The feature point is converted into a coordinate point based on a movement distance of the subject and an image distance. The image distance being a distance between the subject and where the image is captured.
Claims14
An information processing device comprising:
- an image processing device configured to detect an image distance and a 3D position (x, y, z) of a subject from an image and extract a feature point from the subject in an (x, y) plane perpendicular to an image distance z-axis, wherein the image distance is a distance between the subject and where the image is captured;
- and
- a coordinate conversion unit configured to convert the feature point into a coordinate point in a coordinate space based on the image distance and a movement distance of the subject, wherein the coordinate conversion unit determines a conversion coefficient for converting the feature point into the coordinate point, and wherein the conversion coefficient is determined based on the image distance, and wherein the conversion coefficient is proportional to the image distance divided by a reference distance;
- wherein equal subject movement distances at different image distances correspond to a same coordinate movement distance in the coordinate space that includes the coordinate point.
An information processing method comprising:
- detecting an image distance and a 3D position (x, y, z) of a subject from an image;
- extracting a feature point from the subject in an (x, y) plane perpendicular to an image distance z-axis, wherein the image distance is a distance between the subject and where the image is captured;
- and
- converting, by a coordinate conversion unit, the feature point into a coordinate point in a coordinate space based on the image distance and a movement distance of the subject;
- and
- determining a conversion coefficient for converting the feature point into the coordinate point, wherein the conversion coefficient is determined based on the image distance, and wherein the conversion coefficient is proportional to the image distance divided by a reference distance;
- wherein equal subject movement distances at different image distances correspond to a same coordinate movement distance in the coordinate space that includes the coordinate point.
A non-transitory computer readable storage medium storing a computer program, the computer program causing an apparatus to:
- detect an image distance and a 3D position (x, y, z) of a subject from an image;
- extract a feature point from the subject in an (x, y) plane perpendicular to an image distance z-axis, wherein the image distance is a distance between the subject and where the image is captured;
- and
- convert the feature point into a coordinate point in a coordinate space based on the image distance and a movement distance of the subject;
- and
- determine a conversion coefficient for converting the feature point into the coordinate point, wherein the conversion coefficient is determined based on the image distance, and wherein the conversion coefficient is proportional to the image distance divided by a reference distance;
- wherein equal subject movement distances at different image distances correspond to a same coordinate movement distance in the coordinate space that includes the coordinate point.
An electronic apparatus comprising:
- an information processing device including:
- an image processing device configured to detect an image distance and a 3D position (x, y, z) of a subject from an image and extract a feature point from the subject in an (x, y) plane perpendicular to an image distance z-axis, wherein the image distance is a distance between the subject and where the image is captured;
- and
- a coordinate conversion unit configured to convert the feature point into a coordinate point in a coordinate space based on the image distance and a movement distance of the subject, wherein the coordinate conversion unit determines a conversion coefficient for converting the feature point into the coordinate point, and wherein the conversion coefficient is determined based on the image distance, and wherein the conversion coefficient is proportional to the image distance divided by a reference distance;
- wherein equal subject movement distances at different image distances correspond to a same coordinate movement distance in the coordinate space that includes the coordinate point.
Dependencies are inferred from the claim text.