| 摘要 |
An image-processing device (10) is provided with: a segmentation unit (11) for dividing each of a first image and a third image into a plurality of segments on the basis of pixel value similarities; an instruction unit (12) for instructing the position of a target object in the first image; a reference domain setup unit (13) for configuring as a reference domain a set of segments including an instructed segment, which is a segment that exists in an instructed position; an extraction unit (14) for extracting from the reference domain a feature value showing a first feature as a target object feature value; a target domain setup unit (15) for configuring a target domain within the third image on the basis of the relationship between the position of a feature point extracted from a feature domain, which is the domain corresponding to the target object within the second image, and the position of the feature point within the third image corresponding to the relevant feature point; and a tracking unit (16) for using the target object feature value to determine whether or not the segments included in the target domain are segments corresponding to the target object. |
