CN106851303B - Method and system for detecting small object blocks in video image - Google Patents
Method and system for detecting small object blocks in video image Download PDFInfo
- Publication number
- CN106851303B CN106851303B CN201611253747.3A CN201611253747A CN106851303B CN 106851303 B CN106851303 B CN 106851303B CN 201611253747 A CN201611253747 A CN 201611253747A CN 106851303 B CN106851303 B CN 106851303B
- Authority
- CN
- China
- Prior art keywords
- processed
- image
- image block
- block
- neighborhood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000013598 vector Substances 0.000 claims abstract description 61
- 238000006243 chemical reaction Methods 0.000 abstract description 7
- 238000013467 fragmentation Methods 0.000 abstract description 3
- 238000006062 fragmentation reaction Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
- H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
- H04N19/51—Motion estimation or motion compensation
- H04N19/513—Processing of motion vectors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
- H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
- H04N19/51—Motion estimation or motion compensation
- H04N19/53—Multi-resolution motion estimation; Hierarchical motion estimation
Abstract
The invention provides a method and a system for detecting small object blocks in a video image, wherein the method comprises the following steps: calculating the brightness variance varY and the motion vector MV of the image block to be processed; if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood; and if the ratio of Ns to Nd is larger than a set threshold, determining the image block to be processed as a small object block. The invention can accurately detect the small object block in the video image, thereby avoiding the object fragmentation phenomenon in the frame rate conversion of the video image.
Description
Technical Field
The present invention relates to the field of multimedia technologies, and in particular, to a method and a system for detecting small object blocks in video images.
Background
In the field of high definition video application, the current main frame rate conversion and lifting method is to perform motion estimation on an original frame, obtain a motion vector between adjacent frames according to a motion estimation result, and perform motion compensation on the obtained motion vector to obtain an interpolation frame result. In general, a video often includes small object blocks, and when motion estimation is performed, motion vectors of the small objects may be incorrectly estimated as motion vectors of a background, so that the small object blocks are replaced by the background blocks during motion compensation, and an object fragmentation phenomenon occurs in an intermediate interpolated frame. Therefore, in order to prevent the above phenomenon, it is necessary to detect a small object block in a video image.
Disclosure of Invention
In order to solve the above-mentioned problems in the prior art, that is, to solve the problem that the prior art cannot detect the small object blocks in the video image, thereby causing the object fragmentation phenomenon in the frame rate conversion of the video image, the present invention provides a method for detecting the small object blocks in the video image, which comprises:
calculating the brightness variance varY and the motion vector MV of the image block to be processed; if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood; and if the ratio of Ns to Nd is larger than a set threshold, determining the image block to be processed as a small object block.
Preferably, the image block to be processed is determined as a small object block, specifically: and when the difference value between the mean value and the MV of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed is larger than a set threshold value, determining the image block to be processed as a small object block.
Preferably, the image block to be processed is determined as a small object block, specifically: and when the difference value between the brightness variance of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the varY is larger than a set threshold value, determining the image block to be processed as a small object block.
Preferably, after the step of determining that the image to be processed is a small object block, the method further comprises: and marking the image blocks in the neighborhood of the preset size of the image block to be processed as small object blocks.
Preferably, the motion vector (vx) of the image block within the first neighborhood or the second neighborhood1,vy1) And MV (vx)2,vy2) Is defined as diffv ═ vx1-vx2|+|vy1-vy2|。
Correspondingly, the invention also provides a system for detecting the small object blocks in the video images, which comprises:
the calculation module is used for calculating the brightness variance varY and the motion vector MV of the image block to be processed; the statistical module is used for counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is greater than the set threshold and the difference between the motion vector and the MV is less than a first preset value and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is less than the set threshold and the difference between the motion vector and the MV is greater than a second preset value if varY is greater than the set threshold; and the determining module is used for determining the image block to be processed as a small object block if the ratio of Ns to Nd is greater than a set threshold.
Preferably, the determination module comprises an enclosure determination unit for: and when the difference value between the mean value and the MV of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed is larger than a set threshold value, determining the image block to be processed as a small object block.
Preferably, the enclosure determination unit is further configured to: and when the difference value between the brightness variance of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the varY is larger than a set threshold value, determining the image block to be processed as a small object block.
Preferably, the system further comprises: and the expansion module is used for marking the image blocks in the neighborhood of the image block to be processed with the preset size as small object blocks.
Preferably, the motion vector (vx) of the image block within the first neighborhood or the second neighborhood1,vy1) And MV (vx)2,vy2) Is defined as diffv ═ vx1-vx2|+|vy1-vy2|。
The invention provides a method and a system for detecting small object blocks in a video image, wherein the method comprises the steps of calculating the brightness variance varY and the motion vector MV of an image block to be processed; if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood; and if the ratio of Ns to Nd is larger than a set threshold, determining the image block to be processed as a small object block. Therefore, small object blocks in the video images can be accurately detected, and the phenomenon of object breakage in the frame rate conversion of the video images is avoided.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting small object blocks in video images according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for detecting small object blocks in video images according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a system for detecting small object volumes in video images in a third embodiment of the present invention;
fig. 4 is another schematic diagram of a system for detecting small object volumes in video images in a third embodiment of the present invention.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention.
First embodiment
Referring to fig. 1, fig. 1 shows a schematic flow chart of a method for detecting a small object block in a video image according to a first embodiment of the present invention, which includes the following specific steps:
s101, calculating the brightness variance varY and the motion vector MV of the image block to be processed.
In the embodiment, whether the image block to be processed is a small object block is determined according to the luminance variance varY and the motion vector MV of the image block to be processed. The motion vector MV is obtained by motion estimation, and any existing motion estimation method, such as full search, 3DSR, etc., may be used for motion estimation, which is not described herein again.
S102, if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in the first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in the second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value.
The second neighborhood is larger than the first neighborhood, and specifically, in this embodiment, the first neighborhood is a 3 × 3 neighborhood, and the second neighborhood is a 9 × 9 neighborhood. It will of course be appreciated that it is,on the premise that the second neighborhood is larger than the first neighborhood, the present embodiment does not limit the specific sizes of the first neighborhood and the second neighborhood. Motion vector (vx) for image block in first neighborhood or second neighborhood1,vy1) With the motion vector (vx) of the image block to be processed2,vy2) The difference diffv in this embodiment is calculated by using the following formula: diffv ═ vx1-vx2|+|vy1-vy2|。
And S103, if the ratio of Ns to Nd is greater than a set threshold, determining that the image block to be processed is a small object block.
In this embodiment, when the ratio of Ns to Nd is greater than the set threshold, it is preliminarily determined that the image block to be processed is a small object block. Meanwhile, the image blocks at the junction of a large object and the background in the image are considered, and the image blocks comprise object pixel points and background pixel points, so that the motion estimation is inaccurate, and the image blocks are often misjudged as small object blocks. In this embodiment, when the ratio of Ns to Nd is greater than the set threshold, it is further determined whether the image block to be processed is surrounded by the background block, and when the image block to be processed is surrounded by the background block, it is finally determined that the image block to be processed is a small object block.
The present embodiment mainly determines whether the image block to be processed is surrounded by the background block according to the difference between the motion and the texture of the image block to be processed and the background block, and certainly may also determine according to the difference between other features of the image block to be processed and the background block, and may determine according to a single feature, or may determine according to the combination of a plurality of features. The method for judging the difference between the motion and the texture of the image block to be processed and the background block is as follows:
when the difference value between the mean value of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper direction, the lower direction, the left direction and the right direction of the image block to be processed and the motion vector of the image block to be processed is larger than a set threshold value, the image block to be processed is surrounded by the background block, and the image block to be processed is determined to be a small object block.
When the difference value between the brightness variance of the image block in the neighborhood in at least three directions of the upper direction, the lower direction, the left direction and the right direction of the image block to be processed and the brightness variance of the image block to be processed is larger than a set threshold value, the image block to be processed is surrounded by the background block, and the image block to be processed is determined to be a small object block.
The present embodiment calculates the brightness variance varY and the motion vector MV of the image block to be processed; if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood; and if the ratio of Ns to Nd is larger than a set threshold, determining the image block to be processed as a small object block. Therefore, small object blocks in the video images can be accurately detected, and the phenomenon of object breakage in the frame rate conversion of the video images is avoided.
Second embodiment
Referring to fig. 2, fig. 2 is a schematic flow chart illustrating a method for detecting a small object block in a video image according to a second embodiment of the present invention, which includes the following specific steps:
s201, the luminance variance varY and the motion vector MV of the image block to be processed are calculated, and then the process proceeds to S202.
In the embodiment, whether the image block to be processed is a small object block is determined according to the luminance variance varY and the motion vector MV of the image block to be processed. The motion vector MV is obtained by motion estimation, and any existing motion estimation method, such as full search, 3DSR, etc., may be used for motion estimation, which is not described herein again.
S202, if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in the first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in the second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, and then entering S203.
The second neighborhood is larger than the first neighborhood, and specifically, in this embodiment, the first neighborhood is a 3 × 3 neighborhood, and the second neighborhood is a 9 × 9 neighborhood. It will of course be appreciated that the second neighbourhood is larger than the first neighbourhood provided thatNext, the present embodiment does not limit the specific sizes of the first neighborhood region and the second neighborhood region. Motion vector (vx) for image block in first neighborhood or second neighborhood1,vy1) With the motion vector (vx) of the image block to be processed2,vy2) The difference diffv in this embodiment is calculated by using the following formula: diffv ═ vx1-vx2|+|vy1-vy2|。
S203, judging whether the ratio of Ns and Nd is larger than a set threshold value, if the ratio of Ns and Nd is not larger than the set threshold value, the process goes to S204, and if the ratio of Ns and Nd is larger than the set threshold value, the process goes to S205.
And S204, determining that the image block to be processed is not a small object block.
S205, determining the image block to be processed as a small object block, and then entering S206.
In this embodiment, when the ratio of Ns to Nd is greater than the set threshold, it is preliminarily determined that the image block to be processed is a small object block. Meanwhile, the image blocks at the junction of a large object and the background in the image are considered, and the image blocks comprise object pixel points and background pixel points, so that the motion estimation is inaccurate, and the image blocks are often misjudged as small object blocks. In this embodiment, when the ratio of Ns to Nd is greater than the set threshold, it is further determined whether the image block to be processed is surrounded by the background block, and when the image block to be processed is surrounded by the background block, it is finally determined that the image block to be processed is a small object block.
The present embodiment mainly determines whether the image block to be processed is surrounded by the background block according to the difference between the motion and the texture of the image block to be processed and the background block, and certainly may also determine according to the difference between other features of the image block to be processed and the background block, and may determine according to a single feature, or may determine according to the combination of a plurality of features. The method for judging the difference between the motion and the texture of the image block to be processed and the background block is as follows:
when the difference value between the mean value of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper direction, the lower direction, the left direction and the right direction of the image block to be processed and the motion vector of the image block to be processed is larger than a set threshold value, the image block to be processed is surrounded by the background block, and the image block to be processed is determined to be a small object block.
When the difference value between the brightness variance of the image block in the neighborhood in at least three directions of the upper direction, the lower direction, the left direction and the right direction of the image block to be processed and the brightness variance of the image block to be processed is larger than a set threshold value, the image block to be processed is surrounded by the background block, and the image block to be processed is determined to be a small object block.
And S206, marking the image blocks in the neighborhood of the image block to be processed with the preset size as small object blocks.
In this embodiment, the neighborhood of the predetermined size is a 3 × 3 neighborhood, but it should be understood that the specific size of the neighborhood of the predetermined size is not limited in this embodiment.
The present embodiment calculates the brightness variance varY and the motion vector MV of the image block to be processed; if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood; if the ratio of Ns and Nd is larger than a set threshold value, further judging whether the image block to be processed is surrounded by the background block, determining that the image block to be processed is a small object block when the image block to be processed is surrounded by the background block, and simultaneously marking the image blocks in the neighborhood of the image block to be processed with the preset size as the small object blocks. Therefore, small object blocks in the video images can be accurately detected, and the phenomenon of object breakage in the frame rate conversion of the video images is avoided.
Third embodiment
Referring to fig. 3, fig. 3 shows a schematic diagram of a small object detection system in a video image according to a third embodiment of the present invention, the system comprising:
a calculating module 301, configured to calculate a luminance variance varY and a motion vector MV of the image block to be processed.
The counting module 302 is configured to count an image block number Ns that a luminance variance in a first neighborhood of the to-be-processed image block is greater than a set threshold and a difference between the motion vector and the MV is less than a first preset value, and a image block number Nd that a luminance variance in a second neighborhood of the to-be-processed image block is less than the set threshold and a difference between the motion vector and the MV is greater than a second preset value, if varY is greater than the set threshold.
And the determining module 303 is configured to determine that the image block to be processed is a small object block if the ratio of Ns to Nd is greater than a set threshold.
Further, referring to fig. 4, the determining module 303 includes a surrounding determining unit 3031, where the surrounding determining unit 3031 is configured to: and when the difference value between the mean value and the MV of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed is larger than a set threshold value, determining the image block to be processed as a small object block.
The enclosure determination unit 3031 is further configured to: and when the difference value between the brightness variance of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the varY is larger than a set threshold value, determining the image block to be processed as a small object block.
The system also includes an expansion module 304 for marking tiles within a predetermined size neighborhood of the tiles to be processed as small object blocks.
The present embodiment calculates the brightness variance varY and the motion vector MV of the image block to be processed; if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood; if the ratio of Ns and Nd is larger than a set threshold value, further judging whether the image block to be processed is surrounded by the background block, determining that the image block to be processed is a small object block when the image block to be processed is surrounded by the background block, and simultaneously marking the image blocks in the neighborhood of the image block to be processed with the preset size as the small object blocks. Therefore, small object blocks in the video images can be accurately detected, and the phenomenon of object breakage in the frame rate conversion of the video images is avoided.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. A method for detecting small object blocks in video images, the method comprising:
calculating the brightness variance varY and the motion vector MV of the image block to be processed;
if varY is larger than a set threshold, counting the number Ns of image blocks of which the brightness variance in a first neighborhood of the image block to be processed is larger than the set threshold and the difference between the motion vector and the MV is smaller than a first preset value, and the number Nd of image blocks of which the brightness variance in a second neighborhood of the image block to be processed is smaller than the set threshold and the difference between the motion vector and the MV is larger than a second preset value, wherein the second neighborhood is larger than the first neighborhood;
and if the ratio of the Ns to the Nd is larger than a set threshold, determining that the image block to be processed is a small object block.
2. The method according to claim 1, wherein the determining that the image block to be processed is a small object block is specifically:
and when the difference value between the mean value of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the MV is larger than a set threshold value, determining that the image block to be processed is a small object block.
3. The method according to claim 1, wherein the determining that the image block to be processed is a small object block is specifically:
and when the difference value between the brightness variance of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the varY is larger than a set threshold value, determining that the image block to be processed is a small object block.
4. The method of claim 1, wherein after the step of determining that the image to be processed is a small object volume, the method further comprises:
and marking the image blocks in the neighborhood of the preset size of the image block to be processed as small object blocks.
5. Method according to claim 1, wherein the motion vectors (vx) of the image blocks within the first neighbourhood or the second neighbourhood1,vy1) And the MV (vx)2,vy2) Is defined as diffv ═ vx1-vx2|+|vy1-vy2|。
6. A system for detecting small object volumes in video images, said system comprising:
the calculation module is used for calculating the brightness variance varY and the motion vector MV of the image block to be processed;
a counting module, configured to count, if varY is greater than a set threshold, a number Ns of image blocks in which a luminance variance in a first neighborhood of the to-be-processed image block is greater than the set threshold and a difference between the motion vector and the MV is less than a first preset value, and a number Nd of image blocks in which a luminance variance in a second neighborhood of the to-be-processed image block is less than the set threshold and a difference between the motion vector and the MV is greater than a second preset value, where the second neighborhood is larger than the first neighborhood;
and the determining module is used for determining the image block to be processed as a small object block if the ratio of Ns to Nd is greater than a set threshold.
7. The system of claim 6, wherein the determination module comprises an enclosure determination unit to:
and when the difference value between the mean value of the motion vectors of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the MV is larger than a set threshold value, determining that the image block to be processed is a small object block.
8. The system of claim 7, wherein the enclosure determination unit is further to:
and when the difference value between the brightness variance of the image blocks in the neighborhoods in at least three directions of the upper, lower, left and right directions of the image block to be processed and the varY is larger than a set threshold value, determining that the image block to be processed is a small object block.
9. The system of claim 6, wherein the system further comprises:
and the expansion module is used for marking the image blocks in the neighborhood of the to-be-processed image block with the preset size as small object blocks.
10. System according to claim 6, characterized in that the motion vectors (vx) of the image blocks within the first neighbourhood or the second neighbourhood1,vy1) And the MV (vx)2,vy2) Is defined as diffv ═ vx1-vx2|+|vy1-vy2|。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611253747.3A CN106851303B (en) | 2016-12-30 | 2016-12-30 | Method and system for detecting small object blocks in video image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611253747.3A CN106851303B (en) | 2016-12-30 | 2016-12-30 | Method and system for detecting small object blocks in video image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106851303A CN106851303A (en) | 2017-06-13 |
CN106851303B true CN106851303B (en) | 2020-06-16 |
Family
ID=59114001
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611253747.3A Active CN106851303B (en) | 2016-12-30 | 2016-12-30 | Method and system for detecting small object blocks in video image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106851303B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1885946A (en) * | 2005-06-24 | 2006-12-27 | 三星电子株式会社 | Motion error compensator, and method for detecting and compensating motion error |
CN101189882A (en) * | 2004-07-20 | 2008-05-28 | 高通股份有限公司 | Method and apparatus for encoder assisted-frame rate up conversion (EA-FRUC) for video compression |
CN105574891A (en) * | 2015-12-11 | 2016-05-11 | 上海兴芯微电子科技有限公司 | Method and system for detecting moving object in image |
-
2016
- 2016-12-30 CN CN201611253747.3A patent/CN106851303B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101189882A (en) * | 2004-07-20 | 2008-05-28 | 高通股份有限公司 | Method and apparatus for encoder assisted-frame rate up conversion (EA-FRUC) for video compression |
CN1885946A (en) * | 2005-06-24 | 2006-12-27 | 三星电子株式会社 | Motion error compensator, and method for detecting and compensating motion error |
CN105574891A (en) * | 2015-12-11 | 2016-05-11 | 上海兴芯微电子科技有限公司 | Method and system for detecting moving object in image |
Non-Patent Citations (1)
Title |
---|
适用于高清视频的帧率上变换算法研究与实现;韩睿;《中国博士学位论文全文数据库信息科技辑》;20150415;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN106851303A (en) | 2017-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8891905B2 (en) | Boundary-based high resolution depth mapping | |
JP4162621B2 (en) | Frame interpolation method and apparatus for frame rate conversion | |
CN102638679B (en) | Method for image interpolation based on matrix and image processing system | |
US20080095399A1 (en) | Device and method for detecting occlusion area | |
CN109729298B (en) | Image processing method and image processing apparatus | |
CN106327488B (en) | Self-adaptive foreground detection method and detection device thereof | |
CN106204441B (en) | Image local amplification method and device | |
US20110026776A1 (en) | Image Detecting Apparatus and Method Thereof | |
EP2897358B1 (en) | Method and apparatus for de-interlacing video | |
WO2009140916A1 (en) | Deinterlacing method, deinterlacing device and video process system for video data | |
CN106851303B (en) | Method and system for detecting small object blocks in video image | |
CN105430382A (en) | Method and device for detecting black edge of video image | |
CN100594723C (en) | Image processor having frame speed conversion and its method | |
JP2021051382A (en) | Attached matter detection device and attached matter detection method | |
JP5114290B2 (en) | Signal processing device | |
CN106851047B (en) | Method and system for detecting static pixel points in video image | |
US8401286B2 (en) | Image detecting device and method | |
JP2006215657A (en) | Method, apparatus, program and program storage medium for detecting motion vector | |
JP4250598B2 (en) | Motion compensation IP conversion processing apparatus and motion compensation IP conversion processing method | |
CN108495073B (en) | Video image frame field detection method, storage medium and computer | |
CN111582100A (en) | Target object detection method and device | |
JP2005229166A (en) | Apparatus and method for measuring noise amount in video signal | |
JP2007097028A (en) | Motion vector detecting method and motion vector detecting circuit | |
CN108171128B (en) | Face detection method and device | |
JP2009080623A (en) | Image processor and image pickup device with image processor mounted thereon |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |