CN117857808A - Efficient video transmission method and system based on data classification compression - Google Patents
Efficient video transmission method and system based on data classification compression Download PDFInfo
- Publication number
- CN117857808A CN117857808A CN202410251450.1A CN202410251450A CN117857808A CN 117857808 A CN117857808 A CN 117857808A CN 202410251450 A CN202410251450 A CN 202410251450A CN 117857808 A CN117857808 A CN 117857808A
- Authority
- CN
- China
- Prior art keywords
- video frame
- area
- frame image
- image
- characteristic
- 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.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 51
- 238000007906 compression Methods 0.000 title claims abstract description 39
- 230000006835 compression Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000033001 locomotion Effects 0.000 claims abstract description 49
- 238000009432 framing Methods 0.000 claims description 4
- 230000036314 physical performance Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses a high-efficiency video transmission method and a system based on data classification compression, which relate to the technical field of video processing and comprise the following steps: obtaining at least one similar image set; obtaining at least one moving area; summarizing to obtain a motion vector group; acquiring a first video frame image in a similar image set as a characteristic video frame image; compressing the motion vector group and the characteristic motion region into first binary data; obtaining a reference background area; obtaining a difference region, and obtaining a difference region group; acquiring a characteristic reference background area of a characteristic video frame image; compressing the characteristic reference background area and the difference area group into second binary data; the first binary data and the second binary data are transmitted. By arranging the image mobile identification module, the image pairing module and the image background identification module, the physical performance of the network equipment is not required to be improved, the compression mode is changed from the compression algorithm, and the transmission efficiency is improved.
Description
Technical Field
The invention relates to the technical field of video processing, in particular to a high-efficiency video transmission method and system based on data classification compression.
Background
Video transmission refers to the process of transmitting various video data and its related information over a computer network via a transmission protocol, and is mainly divided into a sender and a receiver. Video transmission requires a network with rich application protocols, high security and low delay to ensure smooth data transmission.
Because the performance and quality of the current network device are limited, as the requirement on video transmission efficiency is continuously improved, the existing network device cannot further improve the video transmission efficiency, so that the delay of video transmission cannot be further reduced, and the use experience can be influenced in video transmission operation such as video conference.
Disclosure of Invention
In order to solve the technical problems, the technical scheme solves the problems that the prior network equipment cannot further improve the video transmission efficiency along with the continuous improvement of the requirement on the video transmission efficiency due to the limited performance and quality of the prior network equipment, so that the delay of video transmission cannot be further reduced, and the use experience is influenced in video transmission operation such as video conference.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a high-efficiency video transmission method based on data classification compression comprises the following steps:
dividing the video into at least one video frame image;
numbering at least one video frame image;
classifying at least one video frame image to obtain at least one similar image set;
performing moving object identification in at least one video frame image in the similar image set to obtain at least one moving area;
obtaining the motion vector of the motion area in the adjacent video frame images in the similar image set, and summarizing to obtain a motion vector group;
acquiring a first video frame image in a similar image set as a characteristic video frame image;
acquiring a characteristic moving region of a characteristic video frame image, and matching a moving vector group corresponding to the characteristic video frame image with the characteristic moving region;
compressing the motion vector group and the characteristic motion region into first binary data;
performing background recognition in at least one video frame image in the similar image set to obtain a reference background area;
difference is carried out on the reference background areas of the adjacent video frame images in the similar image set, so that a difference area is obtained, and a difference area group is obtained;
acquiring a characteristic reference background area of the characteristic video frame image, and pairing the characteristic reference background area with a difference value area group;
compressing the characteristic reference background area and the difference area group into second binary data;
the first binary data and the second binary data are transmitted.
Preferably, the classifying the at least one video frame image to obtain at least one similar image set includes the following steps:
acquiring a first video frame image and a second video frame image in at least one video frame image;
calculating an image pixel difference value of the first video frame image and the second video frame image;
taking the difference of pixel values of pixel points at the same position in the first video frame image and the second video frame image and taking the absolute value to obtain a first pixel value difference;
accumulating all the first pixel value differences to obtain image pixel difference values of the first video frame image and the second video frame image;
judging whether the pixel difference value of the image is larger than a preset value, if not, classifying the first video frame image and the second video frame image into similar image sets, and if so, not performing any processing;
at least one set of similar images is obtained when the first video frame image and the second video frame image traverse all image combinations in the at least one video frame image.
Preferably, the moving object identification in at least one video frame image in the similar image set includes the following steps:
in the adjacent video frame images, carrying out difference on pixel values of pixel points at the same position and taking absolute values to obtain second pixel value difference values;
obtaining pixel points with the second pixel value difference value larger than a preset pixel value to obtain characteristic pixel points;
and merging the characteristic pixel points with the distance smaller than the preset distance into a moving area to obtain at least one moving area.
Preferably, the step of obtaining the motion vector of the motion area in the adjacent video frame images in the similar image set includes the following steps:
acquiring adjacent video frame images in the similar image set as a third video frame image and a fourth video frame image;
acquiring at least one third moving area of a third video frame image and at least one fourth moving area of a fourth video frame image;
extracting the contours of the third moving region and the fourth moving region, and matching the third moving region and the fourth moving region with the same contours;
calculating the geometric center of the third moving area and the geometric center of the fourth moving area;
the geometric center of the fourth moving area is subtracted from the geometric center of the third moving area paired with the fourth moving area to obtain the moving vector of the moving area.
Preferably, the background recognition in at least one video frame image in the similar image set includes the following steps:
in the adjacent video frame images in the similar image set, carrying out difference on pixel values of pixel points at the same position and taking absolute values to obtain a second pixel value difference value;
obtaining pixel points of which the second pixel value difference value is smaller than a preset pixel value, and obtaining similar pixel points;
and merging the similar pixel points with the distance smaller than the preset distance into a reference background area to obtain the reference background area.
Preferably, the step of obtaining a difference region by making a difference between the reference background regions of adjacent video frame images in the similar image set includes the steps of:
acquiring reference background areas of adjacent video frame images in a similar image set to obtain a first reference background area and a second reference background area;
acquiring an overlapping part of the first reference background area and the second reference background area to obtain an overlapping area;
removing the overlapping area from the first reference background area to obtain a first duplicate removal area;
removing the overlapping area in the second reference background area to obtain a second duplicate removal area;
and pairing the first de-duplication area and the second de-duplication area to obtain a difference area.
An efficient video transmission system based on data classification compression is used for realizing the efficient video transmission method based on data classification compression, and comprises the following steps:
the video framing module is used for dividing the video into at least one video frame image;
the image numbering module is used for numbering at least one video frame image;
the image movement identification module is used for identifying a moving object in at least one video frame image in the similar image set;
the image pairing module is used for pairing the motion vector group corresponding to the characteristic video frame image with the characteristic motion region and pairing the characteristic reference background region with the difference region group;
the image background recognition module is used for matching the characteristic reference background area with the difference area group;
the image compression module compresses the motion vector group and the characteristic motion region into first binary data, and compresses the characteristic reference background region and the difference region group into second binary data;
and a data transmission module that transmits the first binary data and the second binary data.
Compared with the prior art, the invention has the beneficial effects that:
through setting up image movement identification module, image pair module and image background identification module, cut apart the video, obtain the video frame, and carry out classification and compression to the video frame picture, when reducing the transmission, the total amount of data, and then make transmission speed accelerate, and then promote transmission rate, reduce the delay nature of video, in video transmission operation such as the video conference that requires higher to delay, guarantee that the user uses experience, whole process need not to promote the physical properties of network equipment, from compressed algorithm, change compression mode, promote transmission efficiency.
Drawings
FIG. 1 is a flow chart of a method for efficient video transmission based on data classification compression according to the present invention;
FIG. 2 is a schematic view of a flow chart of classifying at least one video frame image to obtain at least one similar image according to the present invention;
FIG. 3 is a schematic diagram of a process for identifying a moving object in at least one video frame image in a set of similar images according to the present invention;
FIG. 4 is a schematic flow chart of a process for obtaining a motion vector of a motion region in adjacent video frame images in a similar image set according to the present invention;
FIG. 5 is a schematic diagram of a background recognition process performed on at least one video frame image in a similar image set according to the present invention;
fig. 6 is a flow chart of the difference area obtained by making differences between the reference background areas of adjacent video frame images in the similar image set according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, a high-efficiency video transmission method based on data classification compression includes:
dividing the video into at least one video frame image;
numbering at least one video frame image;
classifying at least one video frame image to obtain at least one similar image set;
performing moving object identification in at least one video frame image in the similar image set to obtain at least one moving area;
obtaining the motion vector of the motion area in the adjacent video frame images in the similar image set, and summarizing to obtain a motion vector group;
acquiring a first video frame image in a similar image set as a characteristic video frame image;
acquiring a characteristic moving region of a characteristic video frame image, and matching a moving vector group corresponding to the characteristic video frame image with the characteristic moving region;
compressing the motion vector group and the characteristic motion region into first binary data;
performing background recognition in at least one video frame image in the similar image set to obtain a reference background area;
difference is carried out on the reference background areas of the adjacent video frame images in the similar image set, so that a difference area is obtained, and a difference area group is obtained;
acquiring a characteristic reference background area of the characteristic video frame image, and pairing the characteristic reference background area with a difference value area group;
compressing the characteristic reference background area and the difference area group into second binary data;
transmitting the first binary data and the second binary data;
and after the data transmission is finished, reproducing the video frame images according to the compression process, and sequencing the numbers of the video frame images according to the numbers of the video frame images to obtain the video before compression again.
Referring to fig. 2, classifying at least one video frame image to obtain at least one set of similar images includes the steps of:
acquiring a first video frame image and a second video frame image in at least one video frame image;
calculating an image pixel difference value of the first video frame image and the second video frame image;
taking the difference of pixel values of pixel points at the same position in the first video frame image and the second video frame image and taking the absolute value to obtain a first pixel value difference;
accumulating all the first pixel value differences to obtain image pixel difference values of the first video frame image and the second video frame image;
judging whether the pixel difference value of the image is larger than a preset value, if not, classifying the first video frame image and the second video frame image into similar image sets, and if so, not performing any processing;
when the first video frame image and the second video frame image traverse all the image combinations in at least one video frame image, at least one similar image set is obtained;
at least one video frame image is classified to obtain at least one similar image set, the purpose of the at least one similar image set is to combine similar images into one type so as to compress the similar images, the similar images are consistent in structure, the background and a moving object are approximately qualified, therefore, all images in the similar image set can be gradually generated through continuous small-scale transformation based on one image, the data volume corresponding to the small-scale transformation is small, and therefore, the data corresponding to the small-scale transformation and the image serving as a base are taken as compression objects, the compression data is greatly reduced compared with the similar image set, and therefore, the transmission efficiency can be improved.
Referring to fig. 3, in at least one video frame image in a similar image set, performing moving object recognition includes the steps of:
in the adjacent video frame images, carrying out difference on pixel values of pixel points at the same position and taking absolute values to obtain second pixel value difference values;
obtaining pixel points with the second pixel value difference value larger than a preset pixel value to obtain characteristic pixel points;
combining the characteristic pixel points with the distance smaller than the preset distance into a moving area to obtain at least one moving area;
in at least one video frame image in the similar image set, since the moving object is displaced, whether the pixel point is a part of the moving object is determined by determining whether the pixel points at the same position adjacent to the video frame image are consistent, if so, the range of the moving object is an area, and therefore, adjacent pixel points need to be aggregated, so that the moving area is obtained.
Referring to fig. 4, in the adjacent video frame images in the similar image set, acquiring the motion vector of the motion area includes the steps of:
acquiring adjacent video frame images in the similar image set as a third video frame image and a fourth video frame image;
acquiring at least one third moving area of a third video frame image and at least one fourth moving area of a fourth video frame image;
extracting the contours of the third moving region and the fourth moving region, and matching the third moving region and the fourth moving region with the same contours;
calculating the geometric center of the third moving area and the geometric center of the fourth moving area;
subtracting the geometric center of the third moving area paired with the fourth moving area from the geometric center of the fourth moving area to obtain a moving vector of the moving area;
the moving area moves in the adjacent video frame images in the similar image set, so that the moving track of the moving area needs to be described, and subsequent images in the similar image set are generated according to the characteristic video frame images by using the moving vector, therefore, during compression, only the characteristic video frame images and the moving vector are required to be compressed, and the subsequent images in the similar image set do not need to be compressed.
Referring to fig. 5, in at least one video frame image in a similar image set, performing background recognition includes the steps of:
in the adjacent video frame images in the similar image set, carrying out difference on pixel values of pixel points at the same position and taking absolute values to obtain a second pixel value difference value;
obtaining pixel points of which the second pixel value difference value is smaller than a preset pixel value, and obtaining similar pixel points;
merging similar pixel points with the distance smaller than the preset distance into a reference background area to obtain the reference background area;
since the image as the background does not change, the reference background area can be obtained from the difference in pixel points.
Referring to fig. 6, the step of obtaining a difference region by differentiating the reference background regions of adjacent video frame images in the similar image set includes the steps of:
acquiring reference background areas of adjacent video frame images in a similar image set to obtain a first reference background area and a second reference background area;
acquiring an overlapping part of the first reference background area and the second reference background area to obtain an overlapping area;
removing the overlapping area from the first reference background area to obtain a first duplicate removal area;
removing the overlapping area in the second reference background area to obtain a second duplicate removal area;
pairing the first de-duplication area and the second de-duplication area to obtain a difference area;
when the difference value area is used for recovery, the first reference background area is used for removing the first duplicate removal area, and the second duplicate removal area is added to obtain a second reference background area, so that the first reference background area and the second reference background area adjacent to the video frame image can be obtained by the same method, and therefore, the characteristic reference background area of the characteristic video frame image is used as a reference, and all the reference background areas in at least one video frame image in the similar image set can be obtained;
the background in the similar image set is almost consistent, so that the data volume of the difference region is greatly smaller than that of the similar image set, and therefore, the compression characteristic reference background region and the difference region group are compressed, the obtained data volume is greatly reduced compared with that of the traditional compression mode, and the transmission efficiency is improved.
An efficient video transmission system based on data classification compression is used for realizing the efficient video transmission method based on data classification compression, and comprises the following steps:
the video framing module is used for dividing the video into at least one video frame image;
the image numbering module is used for numbering at least one video frame image;
the image movement identification module is used for identifying a moving object in at least one video frame image in the similar image set;
the image pairing module is used for pairing the motion vector group corresponding to the characteristic video frame image with the characteristic motion region and pairing the characteristic reference background region with the difference region group;
the image background recognition module is used for matching the characteristic reference background area with the difference area group;
the image compression module compresses the motion vector group and the characteristic motion region into first binary data, and compresses the characteristic reference background region and the difference region group into second binary data;
and a data transmission module that transmits the first binary data and the second binary data.
The working process of the high-efficiency video transmission system based on data classification compression is as follows:
step one: the video framing module divides the video into at least one video frame image;
step two: the image numbering module is used for numbering at least one video frame image;
step three: classifying at least one video frame image to obtain at least one similar image set;
step four: the image movement identification module is used for identifying a moving object in at least one video frame image in the similar image set to obtain at least one moving area;
step five: obtaining the motion vector of the motion area in the adjacent video frame images in the similar image set, and summarizing to obtain a motion vector group;
step six: acquiring a first video frame image in a similar image set as a characteristic video frame image;
step seven: acquiring a characteristic moving region of a characteristic video frame image, and matching a moving vector group corresponding to the characteristic video frame image with the characteristic moving region by an image matching module;
step eight: the image compression module compresses the motion vector group and the characteristic motion region into first binary data;
step nine: the image background recognition module performs background recognition in at least one video frame image in the similar image set to obtain a reference background area;
step ten: difference is carried out on the reference background areas of the adjacent video frame images in the similar image set, so that a difference area is obtained, and a difference area group is obtained;
step eleven: acquiring a characteristic reference background area of a characteristic video frame image, and matching the characteristic reference background area with a difference value area group by an image matching module;
step twelve: the image compression module compresses the characteristic reference background area and the difference area group into second binary data;
step thirteen: the data transmission module transmits the first binary data and the second binary data.
Still further, the present disclosure also proposes a storage medium having a computer readable program stored thereon, the computer readable program when invoked performing the above-described efficient video transmission method based on data classification compression.
It is understood that the storage medium may be a magnetic medium, e.g., floppy disk, hard disk, magnetic tape; optical media such as DVD; or a semiconductor medium such as a solid state disk SolidStateDisk, SSD, etc.
In summary, the invention has the advantages that: through setting up image movement identification module, image pair module and image background identification module, cut apart the video, obtain the video frame, and carry out classification and compression to the video frame picture, when reducing the transmission, the total amount of data, and then make transmission speed accelerate, and then promote transmission rate, reduce the delay nature of video, in video transmission operation such as the video conference that requires higher to delay, guarantee that the user uses experience, whole process need not to promote the physical properties of network equipment, from compressed algorithm, change compression mode, promote transmission efficiency.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. The efficient video transmission method based on data classification compression is characterized by comprising the following steps of:
dividing the video into at least one video frame image;
numbering at least one video frame image;
classifying at least one video frame image to obtain at least one similar image set;
performing moving object identification in at least one video frame image in the similar image set to obtain at least one moving area;
obtaining the motion vector of the motion area in the adjacent video frame images in the similar image set, and summarizing to obtain a motion vector group;
acquiring a first video frame image in a similar image set as a characteristic video frame image;
acquiring a characteristic moving region of a characteristic video frame image, and matching a moving vector group corresponding to the characteristic video frame image with the characteristic moving region;
compressing the motion vector group and the characteristic motion region into first binary data;
performing background recognition in at least one video frame image in the similar image set to obtain a reference background area;
difference is carried out on the reference background areas of the adjacent video frame images in the similar image set, so that a difference area is obtained, and a difference area group is obtained;
acquiring a characteristic reference background area of the characteristic video frame image, and pairing the characteristic reference background area with a difference value area group;
compressing the characteristic reference background area and the difference area group into second binary data;
the first binary data and the second binary data are transmitted.
2. The efficient video transmission method based on data classification compression of claim 1, wherein classifying at least one video frame image to obtain at least one similar image set comprises the steps of:
acquiring a first video frame image and a second video frame image in at least one video frame image;
calculating an image pixel difference value of the first video frame image and the second video frame image;
taking the difference of pixel values of pixel points at the same position in the first video frame image and the second video frame image and taking the absolute value to obtain a first pixel value difference;
accumulating all the first pixel value differences to obtain image pixel difference values of the first video frame image and the second video frame image;
judging whether the pixel difference value of the image is larger than a preset value, if not, classifying the first video frame image and the second video frame image into similar image sets, and if so, not performing any processing;
at least one set of similar images is obtained when the first video frame image and the second video frame image traverse all image combinations in the at least one video frame image.
3. The efficient video transmission method based on data classification compression according to claim 2, wherein the moving object recognition in at least one video frame image in the similar image set comprises the steps of:
in the adjacent video frame images, carrying out difference on pixel values of pixel points at the same position and taking absolute values to obtain second pixel value difference values;
obtaining pixel points with the second pixel value difference value larger than a preset pixel value to obtain characteristic pixel points;
and merging the characteristic pixel points with the distance smaller than the preset distance into a moving area to obtain at least one moving area.
4. A method of efficient video transmission based on data classification compression as claimed in claim 3 wherein said obtaining a motion vector of a motion region in adjacent ones of said video frame images in a set of similar images comprises the steps of:
acquiring adjacent video frame images in the similar image set as a third video frame image and a fourth video frame image;
acquiring at least one third moving area of a third video frame image and at least one fourth moving area of a fourth video frame image;
extracting the contours of the third moving region and the fourth moving region, and matching the third moving region and the fourth moving region with the same contours;
calculating the geometric center of the third moving area and the geometric center of the fourth moving area;
the geometric center of the fourth moving area is subtracted from the geometric center of the third moving area paired with the fourth moving area to obtain the moving vector of the moving area.
5. The efficient video transmission method based on data classification compression according to claim 4, wherein the background recognition in at least one video frame image in the similar image set comprises the steps of:
in the adjacent video frame images in the similar image set, carrying out difference on pixel values of pixel points at the same position and taking absolute values to obtain a second pixel value difference value;
obtaining pixel points of which the second pixel value difference value is smaller than a preset pixel value, and obtaining similar pixel points;
and merging the similar pixel points with the distance smaller than the preset distance into a reference background area to obtain the reference background area.
6. The efficient video transmission method based on data classification compression according to claim 5, wherein the step of obtaining a difference region by differencing reference background regions of adjacent video frame images in the similar image set comprises the steps of:
acquiring reference background areas of adjacent video frame images in a similar image set to obtain a first reference background area and a second reference background area;
acquiring an overlapping part of the first reference background area and the second reference background area to obtain an overlapping area;
removing the overlapping area from the first reference background area to obtain a first duplicate removal area;
removing the overlapping area in the second reference background area to obtain a second duplicate removal area;
and pairing the first de-duplication area and the second de-duplication area to obtain a difference area.
7. A data-classification-compression-based efficient video transmission system for implementing the data-classification-compression-based efficient video transmission method as claimed in any one of claims 1 to 6, comprising:
the video framing module is used for dividing the video into at least one video frame image;
the image numbering module is used for numbering at least one video frame image;
the image movement identification module is used for identifying a moving object in at least one video frame image in the similar image set;
the image pairing module is used for pairing the motion vector group corresponding to the characteristic video frame image with the characteristic motion region and pairing the characteristic reference background region with the difference region group;
the image background recognition module is used for matching the characteristic reference background area with the difference area group;
the image compression module compresses the motion vector group and the characteristic motion region into first binary data, and compresses the characteristic reference background region and the difference region group into second binary data;
and a data transmission module that transmits the first binary data and the second binary data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410251450.1A CN117857808B (en) | 2024-03-06 | Efficient video transmission method and system based on data classification compression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410251450.1A CN117857808B (en) | 2024-03-06 | Efficient video transmission method and system based on data classification compression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117857808A true CN117857808A (en) | 2024-04-09 |
| CN117857808B CN117857808B (en) | 2024-06-04 |
Family
ID=
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060153288A1 (en) * | 2002-07-12 | 2006-07-13 | Atvisican Ag | Method for compressing and decompressing video image data |
| US20100034476A1 (en) * | 2008-08-09 | 2010-02-11 | Keyence Corporation | Image Data Compression Method, Pattern Model Positioning Method in Image Processing, Image Processing Apparatus, Image Processing Program, and Computer Readable Recording Medium |
| WO2012019417A1 (en) * | 2010-08-10 | 2012-02-16 | 中国科学院自动化研究所 | Device, system and method for online video condensation |
| CN104243994A (en) * | 2014-09-26 | 2014-12-24 | 厦门亿联网络技术股份有限公司 | Method for real-time motion sensing of image enhancement |
| CN110097568A (en) * | 2019-05-13 | 2019-08-06 | 中国石油大学(华东) | A kind of the video object detection and dividing method based on the double branching networks of space-time |
| WO2020125631A1 (en) * | 2018-12-17 | 2020-06-25 | 深圳Tcl新技术有限公司 | Video compression method and apparatus, and computer-readable storage medium |
| CN112203095A (en) * | 2020-12-04 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Video motion estimation method, device, equipment and computer readable storage medium |
| CN113014923A (en) * | 2021-03-03 | 2021-06-22 | 西北工业大学 | Behavior identification method based on compressed domain representation motion vector |
| CN113038133A (en) * | 2021-05-24 | 2021-06-25 | 星航互联(北京)科技有限公司 | Video compression transmission system based on satellite transmission |
| CN113411582A (en) * | 2021-05-10 | 2021-09-17 | 华南理工大学 | Video coding method, system, device and medium based on active contour |
| CN116156196A (en) * | 2023-04-19 | 2023-05-23 | 探长信息技术(苏州)有限公司 | Efficient transmission method for video data |
| CN117354525A (en) * | 2023-12-05 | 2024-01-05 | 深圳市旭景数字技术有限公司 | Video coding method and system for realizing efficient storage and transmission of digital media |
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060153288A1 (en) * | 2002-07-12 | 2006-07-13 | Atvisican Ag | Method for compressing and decompressing video image data |
| US20100034476A1 (en) * | 2008-08-09 | 2010-02-11 | Keyence Corporation | Image Data Compression Method, Pattern Model Positioning Method in Image Processing, Image Processing Apparatus, Image Processing Program, and Computer Readable Recording Medium |
| WO2012019417A1 (en) * | 2010-08-10 | 2012-02-16 | 中国科学院自动化研究所 | Device, system and method for online video condensation |
| CN104243994A (en) * | 2014-09-26 | 2014-12-24 | 厦门亿联网络技术股份有限公司 | Method for real-time motion sensing of image enhancement |
| WO2020125631A1 (en) * | 2018-12-17 | 2020-06-25 | 深圳Tcl新技术有限公司 | Video compression method and apparatus, and computer-readable storage medium |
| CN110097568A (en) * | 2019-05-13 | 2019-08-06 | 中国石油大学(华东) | A kind of the video object detection and dividing method based on the double branching networks of space-time |
| CN112203095A (en) * | 2020-12-04 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Video motion estimation method, device, equipment and computer readable storage medium |
| CN113014923A (en) * | 2021-03-03 | 2021-06-22 | 西北工业大学 | Behavior identification method based on compressed domain representation motion vector |
| CN113411582A (en) * | 2021-05-10 | 2021-09-17 | 华南理工大学 | Video coding method, system, device and medium based on active contour |
| CN113038133A (en) * | 2021-05-24 | 2021-06-25 | 星航互联(北京)科技有限公司 | Video compression transmission system based on satellite transmission |
| CN116156196A (en) * | 2023-04-19 | 2023-05-23 | 探长信息技术(苏州)有限公司 | Efficient transmission method for video data |
| CN117354525A (en) * | 2023-12-05 | 2024-01-05 | 深圳市旭景数字技术有限公司 | Video coding method and system for realizing efficient storage and transmission of digital media |
Non-Patent Citations (2)
| Title |
|---|
| VASILEIOS AVRAMELOS;GLENN VAN WALLENDAEL;PETER LAMBERT: "Real-Time Low-Complexity Digital Video Stabilization in the Compressed Domain", 2018 IEEE 8TH INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - BERLIN (ICCE-BERLIN), 16 December 2018 (2018-12-16) * |
| 熊骁玥: "基于压缩视频的动作识别系统的设计与实现", 中国硕士论文数据库, 15 January 2024 (2024-01-15), pages 1 - 76 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5539515B2 (en) | System and method for compressing video content | |
| CN103886623A (en) | Image compression method and equipment, and system | |
| WO2011140783A1 (en) | Method and mobile terminal for realizing video preview and retrieval | |
| WO2009056038A1 (en) | A method and device for describing and capturing video object | |
| CN102724492A (en) | Method and system for transmitting and playing video images | |
| CN104702955A (en) | Method and system for predictive coding of screen video | |
| CN104079950A (en) | Video output processing method, device and system and video receiving processing method, device and system | |
| CN103020138A (en) | Method and device for video retrieval | |
| CN117857808B (en) | Efficient video transmission method and system based on data classification compression | |
| CN107682699B (en) | A kind of nearly Lossless Image Compression method | |
| CN112770116B (en) | Method for extracting video key frame by using video compression coding information | |
| CN117857808A (en) | Efficient video transmission method and system based on data classification compression | |
| CN111738236B (en) | Image segmentation identification method, device and system of self-adaptive hierarchy | |
| US11095901B2 (en) | Object manipulation video conference compression | |
| CN115379233B (en) | Big data video information analysis method and system | |
| CN115113821B (en) | 5G big data power calculation service system based on quantum encryption | |
| CN107194961B (en) | Method for determining multiple reference images in group image coding | |
| CN116489333A (en) | Edge classification model construction method for depth map coding unit division | |
| CN116055762A (en) | Video synthesis method and device, electronic equipment and storage medium | |
| CN113727105B (en) | Depth map compression method, device, system and storage medium | |
| CN112422134B (en) | Method and device for space-time trajectory compression and segmented state expression | |
| CN112218082B (en) | Reconfigurable multi-video coding acceleration design-based method and system | |
| CN107509074A (en) | Adaptive 3 D video coding-decoding method based on compressed sensing | |
| CN102510427B (en) | Real-time online transmission method for cell phone with low network bandwidth | |
| CN117354525B (en) | Video coding method and system for realizing efficient storage and transmission of digital media |
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 |