Localization apparatus and method

A localization method comprising:

• training a deep learning model for semantic segmentation by using a plurality of combinations of training image data in which position coordinates desired to be detected on an image obtained by imaging a subject is specified and teacher image data in which a pixel group representing a circular or polygonal shape centered on the position coordinates desired to be detected, which is configured with the same pixel value, is formed on a uniformly labeled image as a background, at a position relative to the subject at the position coordinates desired to be detected on the combined training image data;
• calculating position coordinates desired to be obtained in an image of a new subject by using inference image data obtained by inputting the image of the new subject of which the position coordinates are desired to be obtained to the deep learning model by a position coordinate calculation unit including a process of obtaining a connected component of the inference image data and a center of gravity of the connected component;
• and
• calculating, in a reliability calculation unit, a reliability of the position coordinates calculated by the position coordinate calculation unit that is not a peak value, by using information of a pixel group of the inference image data output from the deep learning model;
• and
• selecting position coordinates by referring to the calculated reliability.

A localization apparatus comprising:

• a deep learning model for semantic segmentation trained by using a plurality of combinations of training image data in which position coordinates desired to be detected on an image obtained by imaging a subject is specified and teacher image data in which a pixel group representing a circular or polygonal shape centered on the position coordinates desired to be detected, which is configured with the same pixel value, is formed, on a uniformly labeled image as a background, at a position relative to the subject at the position coordinates desired to be detected on the combined training image data;
• a position coordinate calculation unit calculating position coordinates desired to be obtained in an image of a new subject by using inference image data obtained by inputting the image of the new subject of which the position coordinates are desired to be obtained to the deep learning model, the position coordinate calculation unit including a process of obtaining a connected component of the inference image data and a center of gravity of the connected component;
• and
• a reliability calculation unit calculating reliability of the position coordinates calculated by the position coordinate calculation unit by using information about the pixel group of the inference image data output from the deep learning model, wherein the reliability calculation unit includes a process of quantifying global information of the pixel group of the inference image data.