Image composition apparatus, image composition method, and program

An image composition method comprising:

• a step of obtaining a first image and a second image obtained by imaging a target object and an obstacle which is closer to an imaging apparatus than the target object is by the imaging apparatus from a first direction and a second direction;
• a step of displaying the first image and the second image on a display screen;
• a step of specifying a target object region by receiving a region designation indicating the target object region in which the target object is captured and the obstacle is not captured on the first image and the second image displayed on the display screen;
• a step of obtaining correspondence point information indicating correspondence points between the first image and the second image;
• a step of obtaining geometric transformation information used in a case of geometrically transforming the target object region of the second image with respect to the first image based on the correspondence point information;
• a step of geometrically transforming the target object region of the second image based on the geometric transformation information;
• and
• a step of generating a composite image by compositing the target object region of the first image with the geometrically transformed target object region of the second image.

A computer-readable, non-transitory tangible recording medium which records a program for causing a computer to perform the functions of:

• obtaining a first image and a second image obtained by imaging a target object and an obstacle which is closer to an imaging apparatus than the target object is by the imaging apparatus from a first direction and a second direction;
• displaying the first image and the second image on a display screen;
• specifying a target object region by receiving a region designation indicating the target object region in which the target object is captured and the obstacle is not captured on the first image and the second image displayed on the display screen;
• obtaining correspondence point information indicating correspondence points between the first image and the second image;
• obtaining geometric transformation information used in a case of geometrically transforming the target object region of the second image with respect to the first image based on the correspondence point information;
• geometrically transforming the target object region of the second image based on the geometric transformation information;
• and
• generating a composite image by compositing the target object region of the first image with the geometrically transformed target object region of the second image.