Image processing system, image processing method, and program

摘要

It is an object to reduce a computation related to a detection of a corresponding point intended for a compressed dynamic image. In order to attain the object, there are acquired first and second compressed dynamic images including a reference frame and a prediction frame with each pixel indicated by motion information based on the other frame respectively. Moreover, there is executed a detection processing for detecting a corresponding point which corresponds to each reference point of one frame contained in the first compressed dynamic image from one frame contained in the second compressed dynamic image by causing each set of frames between said first compressed dynamic image and said second compressed dynamic image to be a target. The detection processing intended for a set of prediction frames is executed by using the motion information indicative of the set of prediction frames.

主权项

1. An image processing system comprising:
an acquiring portion for acquiring first and second compressed dynamic images, wherein said first and second compressed dynamic images each comprises a plurality of frames, including a reference frame and a prediction frame, wherein each pixel of said prediction frames is indicated by motion information based on a corresponding frame of a respective compressed dynamic image; and a computing portion for carrying out a detection processing with respect to a plurality of sets of frames each set of frames comprising 1) a frame in said first compressed dynamic image and 2) a frame in said second compressed dynamic image corresponding thereto for detecting a corresponding point for each reference point contained in one frame of said first compressed dynamic image, wherein said detected corresponding point is contained in a frame of said second compressed dynamic image, wherein said detected corresponding point is detected by causing each of said plurality of sets of frame to be a target, said computing portion executing said detection processing for a set of prediction frames contained in said plurality of sets of frames by using motion information indicative of said set of said prediction frames.