Image generation device, imaging device, image generation method, and program for generating a new image from a captured image
An image generating device has a camerawork information extracting unit ( 315 ) that extracts imaging information of a captured image, a composition information calculating unit ( 316 ) that decides a cut-out frame for cutting out a new image from the imaging information and the captured image based on a constraint condition, and a composition information shaping unit ( 317 ) that cuts out the new image from the captured image by using the cut-out frame and converts a size of the new image to a predetermined size. With this configuration, the new image generated from the captured image becomes a favorable image that is easy to see for a viewer, without requiring skilled imaging techniques during capturing.
1. An image generating device comprising:
a human detector implemented by a processor that detects a human from a captured image captured by an imaging system;
a motion detector implemented by the processor that identifies a motion between frames from the captured image, each of the frames being a unit of an image;
a cut-out frame decider implemented by the processor that decides a cut-out frame for cutting out a new image from the detected human and the identified motion based on a constraint condition regarding camerawork between the frames of the imaging system during capturing of the image; and
a composition information shaper that cuts out the new image from the captured image by using the cut-out frame, and converts a size of the new image to a predetermined size.
2. The image generating device according to claim 1 , wherein the constraint condition includes at least one of a horizontal moving time, a vertical moving time, a zoom-out time, and a zoom-in time of the imaging system during capturing of the image.
3. An imaging device comprising:
the imaging system according to claim 1 ; and
the image generating device according to claim 1 .
4. An image generating method comprising:
detecting, using a processor, a human from a captured image captured by an imaging system;
identifying, using the processor, a motion between frames from the captured image, each of the frames being a unit of an image;
deciding, using the processor, a cut-out frame for cutting out a new image from the detected human and the identified motion based on a constraint condition regarding camerawork between the frames of the imaging system during capturing of the image; and
cutting out the new image from the captured image by using the cut-out frame, and converting a size of the new image to a predetermined size.
5. A non-transitory computer-readable recording medium storing a program for enabling a computer to perform steps comprising:
detecting a human from a captured image captured by an imaging system;
identifying a motion between frames from the captured image, each of the frames being a unit of an image;
deciding a cut-out frame for cutting out a new image from the detected human and the identified motion based on a constraint condition regarding camerawork between the frames of the imaging system during capturing of the image; and
cutting out the new image from the captured image by using the cut-out frame, and converting a size of the new image to a predetermined size.