US5805221A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Video signal coding system employing segmentation technique
Assignee: Quarterhill Inc
•
Filing: 1995-10-30
•
Granted: 1998-09-08
•
Expires: 2015-10-30
Abstract
Abstract A video signal coding system employing a segmentation technique segments a video frame signal into regions to generate contour and texture information of each region and detects continuous boundaries located between adjacent regions. The contour and the texture information of each region and the boundary information of the continuous boundary are encoded to provide an encoded video signal. The video signal coding system calculates a mean value of pixels in two adjacent regions of each side of a continuous boundary and updates each pixel value within a predetermined distance from a continuous boundary with the mean value.
Inventors
- 👤 Min-Sup Lee
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-29 17:14
CPC Classifications
G; G06; G06T; G06T9/00; G06T9/20; H; H04; H04N; H04N19/00; H04N19/20
Claims Analysis
Total Claims: 15
Claim 1
Independent Claim
285 words
An image processing system having an encoder for providing an encoded video signal based on an input video signal and a decoder for providing a decoded video signal based on the encoded video signal, wherein the encoder comprises: means for segmenting the input video signal into a plurality of regions to generate contour information and texture information, wherein the contour information represents the shape and location of said each of the regions and the respective texture information represents a mean pixel value of all the pixels contained in said each of the regions; means for detecting boundaries between the regions based on the contour information for said each of the regions and calculating a mean gradient value of pixels within a predetermined width from each of the boundaries; means for comparing the mean gradient value with a predetermined threshold value and, if the mean gradient value is less than the predetermined threshold value, determining a corresponding boundary as a continuous boundary to thereby provide boundary information representing the location of the continuous boundary; and means for encoding the contour information, the texture information, and the boundary information to provide the encoded video signal; and wherein the decoder comprises: means for decoding the encoded video signal to thereby reproduce the contour information, the texture information and the boundary information; means for providing a reconstructed video signal based on the contour information and the texture information; and means for determining a mean level between the texture information of two adjacent regions on each side of the continuous boundary corresponding to the boundary information, and updating each pixel value within a predetermined distance from the continuous boundary with the mean level to thereby provide the decoded video signal.
Claim 2
Dependent Claim
285 words
An image processing system having an encoder for providing an encoded video signal based on an input video signal and a decoder for providing a decoded video signal based on the encoded video signal, wherein the encoder comprises: means for segmenting the input video signal into a plurality of regions to generate contour information and texture information, wherein the contour information represents the shape and location of said each of the regions and the respective texture information represents a mean pixel value of all the pixels contained in said each of the regions; means for detecting boundaries between the regions based on the contour information for said each of the regions and calculating a mean gradient value of pixels within a predetermined width from each of the boundaries; means for comparing the mean gradient value with a predetermined threshold value and, if the mean gradient value is less than the predetermined threshold value, determining a corresponding boundary as a continuous boundary to thereby provide boundary information representing the location of the continuous boundary; and means for encoding the contour information, the texture information, and the boundary information to provide the encoded video signal; and wherein the decoder comprises: means for decoding the encoded video signal to thereby reproduce the contour information, the texture information and the boundary information; means for providing a reconstructed video signal based on the contour information and the texture information; and means for determining a mean level between the texture information of two adjacent regions on each side of the continuous boundary corresponding to the boundary information, and updating each pixel value within a predetermined distance from the continuous boundary with the mean level to thereby provide the decoded video signal.
Claim 3
Dependent Claim
238 words
An image processing system for processing a video signal, having an encoder and a decoder, wherein the encoder comprises: means for segmenting the video signal into a plurality of regions to generate contour information and texture information, wherein the contour information represents the shape and location of each of the regions and the texture information represents a mean pixel value of all the pixels contained in said each of the regions; means for detecting boundaries between the regions based on the contour information and calculating a mean gradient value of pixels within a predetermined width from each of the boundaries; means for determining continuous boundaries by comparing the mean gradient value of said each of the boundaries with a predetermined threshold value, to thereby provide boundary information representing locations of the boundaries determined as the continuous boundaries; and means for encoding the contour information, the texture information, and the boundary information to provide an encoded video signal; and wherein the decoder comprises: means for decoding the encoded video signal to thereby reproduce the contour information, the texture information and the boundary information; means for providing a reconstructed video signal based on the contour information and the texture information; and means for compensating differences between pixel values within a predetermined distance on each side from each of continuous boundaries based on the boundary information, the contour information and the reconstructed video signal, to thereby produce a decoded video signal.
Claim 4
Dependent Claim
238 words
An image processing system for processing a video signal, having an encoder and a decoder, wherein the encoder comprises: means for segmenting the video signal into a plurality of regions to generate contour information and texture information, wherein the contour information represents the shape and location of each of the regions and the texture information represents a mean pixel value of all the pixels contained in said each of the regions; means for detecting boundaries between the regions based on the contour information and calculating a mean gradient value of pixels within a predetermined width from each of the boundaries; means for determining continuous boundaries by comparing the mean gradient value of said each of the boundaries with a predetermined threshold value, to thereby provide boundary information representing locations of the boundaries determined as the continuous boundaries; and means for encoding the contour information, the texture information, and the boundary information to provide an encoded video signal; and wherein the decoder comprises: means for decoding the encoded video signal to thereby reproduce the contour information, the texture information and the boundary information; means for providing a reconstructed video signal based on the contour information and the texture information; and means for compensating differences between pixel values within a predetermined distance on each side from each of continuous boundaries based on the boundary information, the contour information and the reconstructed video signal, to thereby produce a decoded video signal.
Claim 5
Dependent Claim
29 words
The image processing system according to claim 2, wherein the encoder determines a boundary whose mean gradient value is less than the predetermined threshold value as the continuous boundary.
Claim 6
Dependent Claim
72 words
The image processing system according to claim 3, wherein the compensating means includes: means for computing a mean level between the texture information of two adjacent regions on each side of said each of the continuous boundaries recognized by the boundary information; and means for updating each pixel value within the predetermined distance on each side from each of continuous boundaries with the mean level to thereby provide the decoded video signal.
Claim 7
Dependent Claim
151 words
A video signal encoder for encoding an input video signal to provide an encoded video signal, comprising: means for segmenting the input video signal into a plurality of regions to generate contour information and texture information for each region, wherein the contour information represents a shape and a location of each region and the texture information represents a mean pixel value of all the pixels contained in that region; means for detecting boundaries between the regions based on the contour information and calculating a mean gradient value of pixels within a predetermined width from each of the boundaries; means for determining a boundary whose mean gradient value is less than a predetermined threshold value as a continuous boundary to thereby provide boundary information representing locations of the continuous boundaries; and means for encoding the contour information, the texture information, and the boundary information in order to produce the encoded video signal.
Claim 8
Dependent Claim
151 words
A video signal encoder for encoding an input video signal to provide an encoded video signal, comprising: means for segmenting the input video signal into a plurality of regions to generate contour information and texture information for each region, wherein the contour information represents a shape and a location of each region and the texture information represents a mean pixel value of all the pixels contained in that region; means for detecting boundaries between the regions based on the contour information and calculating a mean gradient value of pixels within a predetermined width from each of the boundaries; means for determining a boundary whose mean gradient value is less than a predetermined threshold value as a continuous boundary to thereby provide boundary information representing locations of the continuous boundaries; and means for encoding the contour information, the texture information, and the boundary information in order to produce the encoded video signal.
Claim 9
Dependent Claim
92 words
A video signal decoder for decoding an encoded video signal to provide a decoded video signal, comprising: means for decoding the encoded video signal to thereby reproduce contour information, texture information and boundary information; means for providing a reconstructed video signal based on the contour information and the texture information; and means for compensating differences between pixel values within a predetermined distance on each side from each of continuous boundaries corresponding to the boundary information based on the contour information and the reconstructed video signal, to thereby produce the decoded video signal.
Claim 10
Dependent Claim
92 words
A video signal decoder for decoding an encoded video signal to provide a decoded video signal, comprising: means for decoding the encoded video signal to thereby reproduce contour information, texture information and boundary information; means for providing a reconstructed video signal based on the contour information and the texture information; and means for compensating differences between pixel values within a predetermined distance on each side from each of continuous boundaries corresponding to the boundary information based on the contour information and the reconstructed video signal, to thereby produce the decoded video signal.
Claim 11
Dependent Claim
68 words
The video signal decoder as recited in claim 6, wherein the compensating means includes: means for computing a mean level between the texture information of two adjacent regions on each side of said each of the continuous boundaries; and means for updating each pixel value within said predetermined distance on each side from each of continuous boundaries with the mean level to thereby provide the decoded video signal.
Claim 12
Independent Claim
212 words
An apparatus for encoding and decoding an image, said apparatus comprising: an encoder comprising: means for segmenting the image into a plurality of regions, each of said regions being represented by contour information comprising a shape and size of that region, and by texture information comprising a mean pixel value for all pixels within that region, each pair of adjoining regions being separated by a corresponding boundary; means for calculating a mean gradient value for all pixels within a first predetermined distance from each of said boundaries in the image and comparing said mean gradient value to a predetermined threshold to provide continuous boundary information identifying at least one continuous boundary, said at least one continuous boundary requiring smoothing following reconstruction of said image; and means for encoding said contour information, texture information, and continuous boundary information; and a decoder comprising: means for decoding said contour information, texture information, and continuous boundary information; means for reconstructing a reconstructed image from said contour information and continuous boundary information; and means for smoothing said reconstructed image, said means for smoothing assigning to each pixel within a predetermined second distance from each of said continuous boundaries, a mean of the mean pixel values of said pair of regions corresponding to said each continuous boundary .
Claim 13
Independent Claim
212 words
An apparatus for encoding and decoding an image, said apparatus comprising: an encoder comprising: means for segmenting the image into a plurality of regions, each of said regions being represented by contour information comprising a shape and size of that region, and by texture information comprising a mean pixel value for all pixels within that region, each pair of adjoining regions being separated by a corresponding boundary; means for calculating a mean gradient value for all pixels within a first predetermined distance from each of said boundaries in the image and comparing said mean gradient value to a predetermined threshold to provide continuous boundary information identifying at least one continuous boundary, said at least one continuous boundary requiring smoothing following reconstruction of said image; and means for encoding said contour information, texture information, and continuous boundary information; and a decoder comprising: means for decoding said contour information, texture information, and continuous boundary information; means for reconstructing a reconstructed image from said contour information and continuous boundary information; and means for smoothing said reconstructed image, said means for smoothing assigning to each pixel within a predetermined second distance from each of said continuous boundaries, a mean of the mean pixel values of said pair of regions corresponding to said each continuous boundary .
Claim 14
Independent Claim
194 words
A method for encoding and decoding an image, said method comprising the steps of: segmenting the image into a plurality of regions, each of said regions being represented by contour information comprising a shape and size of that region, and by texture information comprising a mean pixel value for all pixels within that region, each pair of adjoining regions being separated by a corresponding boundary; calculating a mean gradient value for all pixels within a first predetermined distance from each of said boundaries in the image and comparing said mean gradient value to a predetermined threshold to provide continuous boundary information identifying at least one continuous boundary, said at least one continuous boundary requiring smoothing following reconstruction of said image; and encoding said contour information, texture information, and continuous boundary information; and subsequently decoding said contour information, texture information, and continuous boundary information; reconstructing a reconstructed image from said contour information and continuous boundary information; and smoothing said reconstructed image by assigning to each pixel within a predetermined second distance from each of said continuous boundaries, a mean of the mean pixel values of said pair of regions corresponding to said each continuous boundary.
Claim 15
Independent Claim
194 words
A method for encoding and decoding an image, said method comprising the steps of: segmenting the image into a plurality of regions, each of said regions being represented by contour information comprising a shape and size of that region, and by texture information comprising a mean pixel value for all pixels within that region, each pair of adjoining regions being separated by a corresponding boundary; calculating a mean gradient value for all pixels within a first predetermined distance from each of said boundaries in the image and comparing said mean gradient value to a predetermined threshold to provide continuous boundary information identifying at least one continuous boundary, said at least one continuous boundary requiring smoothing following reconstruction of said image; and encoding said contour information, texture information, and continuous boundary information; and subsequently decoding said contour information, texture information, and continuous boundary information; reconstructing a reconstructed image from said contour information and continuous boundary information; and smoothing said reconstructed image by assigning to each pixel within a predetermined second distance from each of said continuous boundaries, a mean of the mean pixel values of said pair of regions corresponding to said each continuous boundary.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-09-07 | 2002-03-09 | 2002-09-08 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-09-07 | 2006-03-09 | 2006-09-08 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-09-07 | 2010-03-09 | 2010-09-08 | $7700.00 | Window Closed / Lapsed |