| 摘要 |
<P>PROBLEM TO BE SOLVED: To acquire positional information about an optional subject in a wider range on the basis of images captured from a plurality of view points. <P>SOLUTION: The image processing system comprises: acquisition means for acquiring a first image and a second image captured from a view point different from that in the first image; detection means for detecting a feature point of a subject in each of the first image and the second image; and calculation means for calculating the positional information about the subject on the basis of the first image and the second image. The calculation means calculates the positional information and a subject model corresponding to the subject on the basis of each feature point when the feature points are detected in both of the first image and the second image and calculates information by referring to the subject model when the feature point is detected in only either the first image or the second image. <P>COPYRIGHT: (C)2013,JPO&INPIT |
