Pulse or digital communications – Bandwidth reduction or expansion – Television or motion video signal
Reexamination Certificate
1999-06-17
2003-04-22
Kelley, Chris (Department: 2613)
Pulse or digital communications
Bandwidth reduction or expansion
Television or motion video signal
C375S240120, C375S240150
Reexamination Certificate
active
06553069
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to an image segmenting method, and more particularly, to a digital image segmentation method of segmenting a digital image into objects for object-based image processing. Also, the present invention relates to a method of tracking an area in an image segmented by the above-described method, and to a digital image segmenting device to accomplish the image segmenting method.
2. Description of the Related Art
Image segmentation is essential for object-based digital image processing. However, an image segmentation method, which provides satisfactory results in real time, has not been developed.
SUMMARY OF THE INVENTION
To solve the above problem, it is an object of the present invention to provide a digital image segmenting method for segmenting a digital image into objects at high speed for object-based image processing.
It is another object of the present invention to provide a method of tracking an area of an image segmented by the above-described method at high speed.
It is still another object of the present invention to provide a digital image segmenting device for accomplishing the image segmenting method.
Accordingly, to achieve the first object of the invention, there is provided a digital image segmenting method comprising: (a) grouping an image data stream into a plurality of continuous frame groups; (b) setting one arbitrary frame as an I frame and the others as P frames in each group; (c) segmenting the I frame into a plurality of regions; and (d) segmenting the P frames, by obtaining a motion vector using motion prediction for each of the segmented I frame regions with respect to every one of the P frames, by moving the segmented I frame regions by the motion vectors, respectively, and by setting the moved I frame regions as segmented P frame regions within each P frame.
It is preferable that step (d) comprises: performing an affine matching method of moving each of the segmented I frame regions with respect to every one of the P frames by a predetermined displacement and setting P frame regions, each having a minimum difference from the respective segmented I frame regions, as affine matching regions, respectively; obtaining a motion vector for each of the segmented I frame regions which represents the displacement of the P frame affine matching region with respect to the corresponding segmented I frame region; and moving the segmented I frame regions by the motion vectors, respectively, with respect to every P frame, and setting the moved segmented I frame regions as segmented P frame regions, respectively.
Preferably, the digital image segmenting method, after step (d), further comprises: (e) determining whether the processed segmented I frame region is the last region; and (f) returning to step (d) if it is determined in step (e) that the segmented I frame region is not the last region, wherein the P frames are sequentially segmented based on the segmentation of the I frame.
To achieve the second object of the invention, there is provided a method of tracking regions in an image segmented by the digital image segmenting method, the tracking method comprising: tracking the I frame regions using an affine motion compensation method of moving one I frame region in one frame group with respect to an I frame in another frame group by a predetermined displacement, and setting an I frame region in the other frame group having a minimum difference from the first I frame region as an affine matched region; and tracking the P frame regions formed by segmenting the P frames using motion prediction on the I frames in groups.
To achieve the third object of the invention, there is provided a digital image segmenting device comprising: a grouping unit for grouping an image data stream into a plurality of continuous frame groups and setting one arbitrary frame in each group as an I frame and the others as P frames; an I frame segmenting unit for segmenting the received I frame and outputting the segmented I frame and sequentially outputting the segmented I frame regions; an affine matching unit for obtaining a motion vector using motion prediction for each of the received segmented I frame regions with respect to every P frame; and a P frame segmenting unit for receiving the P frames and the motion vectors and segmenting each of the P frames by moving the segmented I frame regions by the motion vectors, respectively, in each of the P frames.
REFERENCES:
patent: 5592226 (1997-01-01), Lee
patent: 6173077 (2001-01-01), Trew
patent: 6272180 (2001-08-01), Lei
patent: 6285361 (2001-09-01), Brewer et al.
patent: 6295089 (2001-09-01), Hoang
patent: 6324216 (2001-11-01), Igarashi et al.
Choi Yang-lim
Deng Yining
Manjunath B. S.
Shin Hyun-doo
Kelley Chris
Parsons Charles
Samsung Electronics Co,. Ltd.
Sughrue & Mion, PLLC
LandOfFree
Digital image segmenting method and device does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Digital image segmenting method and device, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Digital image segmenting method and device will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3096559