摘要 |
An image processing device (10) for tracking a photographic subject in a first image into a second image captured after the first image, the image processing device (10) being provided with: a segmentation unit (11) for dividing the first image into multiple segments on the basis of the similarities between pixel values; an indication unit (12) for indicating the position of the photographic subject in the first image; a region setting unit (13) for setting, as a target region, a region containing at least an indicated segment which is a segment that is in the indicated position; an extraction unit (14) for extracting the feature amount from the set target region; and a tracking unit (15) for tracking the photographic subject by searching for a region that is similar to the target region within the second image by using the extracted feature amount. |