System and method for object based parametric video coding
First Claim
1. A digital video decoder, comprising:
- a decoding block configured to decode background I frames and edge blocks of background P-frames in an encoded video sequence;
an object appearance estimator configured to estimate an object appearance based on object appearance parameters in the encoded video sequence;
a texture synthesizer coupled to the decoding block and configured to generate background P blocks based on auto regressive coefficients and thread information in the encoded video sequence and the decoded edge blocks; and
a frame compositor coupled to the decoding block, the object appearance estimator and the texture synthesizer and configured to generate a composite output frame based on outputs of the decoding block, the texture synthesizer and the object appearance estimator.
5 Assignments
0 Petitions
Accused Products
Abstract
A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.
13 Citations
21 Claims
-
1. A digital video decoder, comprising:
-
a decoding block configured to decode background I frames and edge blocks of background P-frames in an encoded video sequence; an object appearance estimator configured to estimate an object appearance based on object appearance parameters in the encoded video sequence; a texture synthesizer coupled to the decoding block and configured to generate background P blocks based on auto regressive coefficients and thread information in the encoded video sequence and the decoded edge blocks; and a frame compositor coupled to the decoding block, the object appearance estimator and the texture synthesizer and configured to generate a composite output frame based on outputs of the decoding block, the texture synthesizer and the object appearance estimator. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method of decoding an encoded digital video sequence, the method comprising:
-
decoding background I frames in the encoded video sequence; H.264/AVC (Advanced Video Coding) decoding edge blocks of background P frames; estimating an object appearance based on object appearance parameters in the encoded video sequence; generating background P frames based on auto regressive coefficients and thread information in the encoded video sequence and on the decoded edge block; and generating a composite output frame based on the decoded background I frames, the estimated object appearance and the generated background P frames. - View Dependent Claims (7, 8, 9, 10)
-
-
11. A non-transitory computer-readable memory medium whose contents cause a processor to perform a method of decoding an encoded video image sequence, the method comprising:
-
decoding background I frames in the encoded video sequence; H.264/AVC (Advanced Video Coding) decoding edge blocks of background P frames;
estimating an object appearance based on object appearance parameters in the encoded video sequence;generating background P frames based on auto regressive coefficients and thread information in the encoded video sequence and on the decoded edge block; and generating a composite output frame based on the decoded background I frames, the estimated object appearance and the generated background P frames. - View Dependent Claims (12, 13, 14, 15)
-
-
16. A system comprising:
-
a decoder comprising; an H.264 I slice decoder configured to decode background I frames in an encoded video sequence; an H.264 P slice decoder configured to decode edge blocks of background P frames; an object appearance estimator configured to estimate an object appearance based on object appearance parameters in the encoded video sequence; a texture synthesizer configured to generate background P frames based on auto regressive coefficients and thread information in the encoded video sequence and the decoded edge blocks of background P frames; and a frame compositor coupled to the H.264 I slice decoder, the object appearance estimator and the texture synthesizer and configured to generate a composite output frame based on outputs of the H.264 I slice decoder, the texture synthesizer and the object appearance estimator; and a digital video encoder. - View Dependent Claims (17, 18, 19, 20)
-
-
21. A system comprising:
-
a decoder comprising; a decoding block configured to decode background I frames in an encoded video sequence; an object appearance estimator configured to estimate an object appearance based on object appearance parameters in the encoded video sequence; a texture synthesizer configured to generate background P frames based on auto regressive coefficients and thread information in the encoded video sequence; and a frame compositor coupled to the decoding block, the object appearance estimator and the texture synthesizer and configured to generate a composite output frame based on outputs of the decoding block, the texture synthesizer and the object appearance estimator; and a digital video encoder configured to; segment frames in a digital video sequence into object regions and background regions; generate object motion and appearance parameters based on segmented object regions; and generate an auto regressive background model based on segmented background regions.
-
Specification