CN111385604A - Unified algorithm combination service method - Google Patents
Unified algorithm combination service method Download PDFInfo
- Publication number
- CN111385604A CN111385604A CN202010230085.8A CN202010230085A CN111385604A CN 111385604 A CN111385604 A CN 111385604A CN 202010230085 A CN202010230085 A CN 202010230085A CN 111385604 A CN111385604 A CN 111385604A
- Authority
- CN
- China
- Prior art keywords
- special effect
- algorithm combination
- service
- combination service
- task
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000000694 effects Effects 0.000 claims abstract description 50
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 44
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 44
- 239000000463 material Substances 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 230000004927 fusion Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 7
- 230000011731 head segmentation Effects 0.000 claims description 4
- 230000032683 aging Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a unified algorithm combination service method. The method specifically comprises the following steps: the application layer combines the video preprocessing and the special effect video synthesis types into a rule field; combining the images uploaded by the user into a data field; materials selected by a user are combined into material fields to form a JSON structure body to send a request to an algorithm combination service; receiving the request by the algorithm combination service, performing JSON deserialization, and analyzing the rule, data and material fields; according to the preprocessing, carrying out algorithm processing, submitting a task to the special-effect video service after obtaining a preprocessing result, returning a task ID and returning the task ID to the application layer; after the special effect video service finishes the special effect video synthesis, the algorithm combination service is notified of the processing result in a callback mode; and the application layer initiates special effect video synthesis result query to the algorithm combination service according to the task ID. The invention has the beneficial effects that: the method realizes different special-effect video synthesis functions, enhances the expansibility of algorithm combination service, and reduces the access threshold of an application layer.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a unified algorithm combination service method.
Background
With the more mature AI technology, particularly, the AI falls to the ground at the product end in image and video technologies. Which comprises the following steps: 1. the method comprises the steps of face attribute identification, 2 human body segmentation, 3 human head segmentation, 4 video frame extraction, 5 face animation/aging/young changing, 6 face fusion, and 7 image AI processing is combined with special effect video processing.
The current image and video algorithms are algorithm services which are independent one by one, and the video synthesis with special effects or a certain video processing function on a product is realized, and a plurality of algorithm services are often required to be combined and called for video synthesis. At present, no unified service combines the single algorithm services to realize a service friendly service. And complex logic and complex calling relation of algorithm combination are not shielded, and if a service party realizes multiple algorithm combinations and multiple algorithm combination calling, the calling relation between each image and each video algorithm needs to be known and known. This increases the difficulty of service access to special effect video composition.
Disclosure of Invention
The invention provides a unified algorithm combination service method for reducing an access threshold in order to overcome the defects in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a unified algorithm combination service method adopts HTTP + JSON protocol for interaction, and concretely comprises the following steps:
(1) the application layer combines the video preprocessing and the special effect video synthesis types into a rule field; by combining images uploaded by a user into data fields; materials selected by a user are combined into material fields to form a JSON structure body to send a request to an algorithm combination service;
(2) receiving a request by the algorithm combination service, performing JSON deserialization on the request, and analyzing three fields of rules, data and materials;
(3) the algorithm combination service carries out corresponding algorithm processing according to the preprocessing in the rule, after a preprocessing result is obtained, the video synthesis type, data and materials in the combination rule submit tasks to the special effect video service, a task ID is correspondingly returned, and then the task ID is returned to the application layer;
(4) after the special video service processes the special video synthesis, the algorithm combination service is informed of the processing result in a callback mode;
(5) the application layer initiates special effect video synthesis result query to the algorithm combination service according to the task ID, and returns a result if the processing is finished; otherwise, the process returns to the process.
The algorithm combination service method realizes different special-effect video synthesis functions by defining image or video processing rules and realizing the same interface according to rule fields in application requests. The business side only needs to request according to the rule field, the data field and the material field of the algorithm combination service, and the algorithm combination service calls different algorithm services to synthesize the corresponding special effect video according to the requested rule. The expansibility of the algorithm combination service can be enhanced through the rule definition, and meanwhile, the access threshold of an application layer can be reduced.
Preferably, the algorithm combination service uses an HTTP service to provide a special effect video synthesis task submission interface and a special effect video synthesis task query interface, a synthesized rule field is arranged in the special effect video synthesis task submission interface, the rule field comprises a preprocessing rule and a special effect video synthesis type, and the preprocessing comprises algorithms of animation, youth changing, old changing, human body segmentation, human head segmentation and human face fusion image processing; the special effect video synthesis types comprise lyric special effect videos, face gradual change special effect videos, fusion special effect videos and human body segmentation special effect video synthesis types.
Preferably, in the step (3), different material types include different video synthesis rules, the algorithm combination service performs different processing on different materials according to the video synthesis rules, and if the combination can be performed by performing picture matting, picture fusion, picture animation processing and then synthesis, video synthesis requirements with different complexities are realized without modifying request cooperation, and the algorithm combination service has strong expansibility.
The invention has the beneficial effects that: the same interface is realized according to the rule field in the application request to realize different special effect video synthesis functions, the expansibility of algorithm combination service can be enhanced through rule definition, and meanwhile, the access threshold of an application layer can be reduced.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
In the embodiment shown in fig. 1, a unified algorithm combination service method is provided, where the algorithm combination service uses an HTTP service to provide a special effect video composition task submission interface and a special effect video composition task query interface, a synthesized rule field is provided in the special effect video composition task submission interface, the rule field includes a preprocessing rule and a special effect video composition type, and the preprocessing includes image processing algorithms such as animation, youth, aging, human body segmentation, human head segmentation, and face fusion; the special effect video synthesis types comprise video synthesis types such as lyric special effect video, face gradual change special effect video, fusion special effect video, human body segmentation special effect and the like, and a special effect video synthesis task submitting interface calls corresponding pictures and video processing algorithms according to the preprocessing types of rules; combining the preprocessing result, the video synthesis type, the material and the user data to form a corresponding request, submitting a task to the video special effect through a message queue, then returning a corresponding task id to a business party, inquiring the task from the subsequent business party to the algorithm combination service through a special effect video synthesis task inquiry interface according to the task id, and informing the algorithm combination service of the processing result of the video special effect in a callback mode; the method adopts an HTTP + JSON protocol for interaction, and specifically comprises the following steps:
(1) the application layer combines the video preprocessing and the special effect video synthesis types into a rule field; by combining images uploaded by a user into data fields; materials selected by a user are combined into material fields to form a JSON structure body to send a request to an algorithm combination service;
(2) receiving a request by the algorithm combination service, performing JSON deserialization on the request, and analyzing three fields of rules, data and materials;
(3) the algorithm combination service carries out corresponding algorithm processing according to the preprocessing in the rule, after a preprocessing result is obtained, the video synthesis type, data and materials in the combination rule submit tasks to the special effect video service, a task ID is correspondingly returned, and then the task ID is returned to the application layer; different material types comprise different video synthesis rules, the algorithm combination service performs different processing corresponding to different materials according to the video synthesis rules, and if the video synthesis service can perform picture matting, picture fusion, picture animation processing and then synthesis, the video synthesis requirements with different complexities are realized on the premise of not modifying request cooperation, and the video synthesis service has strong expansibility.
(4) After the special video service processes the special video synthesis, the algorithm combination service is informed of the processing result in a callback mode;
(5) the application layer initiates special effect video synthesis result query to the algorithm combination service according to the task ID, and returns a result if the processing is finished; otherwise, the process returns to the process.
Wherein: HTTP is a transport protocol used to transfer hypertext from a web server to a local browser. JSON is a lightweight data exchange format that stores and represents data in a text format that is completely independent of programming languages, based on a subset of ECMAScript (the js specification set by the european computer association). The algorithm combination service method realizes different special-effect video synthesis functions by defining image or video processing rules and realizing the same interface according to rule fields in application requests. The business side only needs to request according to the rule field, the data field and the material field of the algorithm combination service, and the algorithm combination service calls different algorithm services to synthesize the corresponding special effect video according to the requested rule. The expansibility of the algorithm combination service can be enhanced through the rule definition, and meanwhile, the access threshold of an application layer can be reduced.
Claims (3)
1. A unified algorithm combination service method is characterized in that an HTTP + JSON protocol is adopted for interaction, and the method specifically comprises the following steps:
(1) the application layer combines the video preprocessing and the special effect video synthesis types into a rule field; by combining images uploaded by a user into data fields; materials selected by a user are combined into material fields to form a JSON structure body to send a request to an algorithm combination service;
(2) receiving a request by the algorithm combination service, performing JSON deserialization on the request, and analyzing three fields of rules, data and materials;
(3) the algorithm combination service carries out corresponding algorithm processing according to the preprocessing in the rule, after a preprocessing result is obtained, the video synthesis type, data and materials in the combination rule submit tasks to the special effect video service, a task ID is correspondingly returned, and then the task ID is returned to the application layer;
(4) after the special video service processes the special video synthesis, the algorithm combination service is informed of the processing result in a callback mode;
(5) the application layer initiates special effect video synthesis result query to the algorithm combination service according to the task ID, and returns a result if the processing is finished; otherwise, the process returns to the process.
2. The unified algorithm combination service method according to claim 1, wherein said algorithm combination service uses HTTP service to provide a special effect video composition task submission interface and a special effect video composition task query interface, the special effect video composition task submission interface has a composition rule field therein, the rule field includes a preprocessing rule and a special effect video composition type, the preprocessing includes animation, youth, aging, body segmentation, head segmentation, face fusion image processing algorithms; the special effect video synthesis types comprise lyric special effect videos, face gradual change special effect videos, fusion special effect videos and human body segmentation special effect video synthesis types.
3. The unified algorithm combination service method according to claim 1 or 2, wherein in step (3), different material types comprise different video composition rules, and the algorithm combination service performs different processing corresponding to different materials according to the video composition rules, if the video composition requirements of different complexity are realized without modifying the request protocol, the algorithm combination service has strong extensibility if the image matting head, the image matting body, the image fusion, the image animation processing and then the composition can be performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010230085.8A CN111385604A (en) | 2020-03-27 | 2020-03-27 | Unified algorithm combination service method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010230085.8A CN111385604A (en) | 2020-03-27 | 2020-03-27 | Unified algorithm combination service method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111385604A true CN111385604A (en) | 2020-07-07 |
Family
ID=71218924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010230085.8A Pending CN111385604A (en) | 2020-03-27 | 2020-03-27 | Unified algorithm combination service method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111385604A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101038604A (en) * | 2007-04-26 | 2007-09-19 | 上海交通大学 | Vehicle impact strength computer synergic design and simulation system |
CN102739771A (en) * | 2012-04-18 | 2012-10-17 | 上海和辰信息技术有限公司 | Cloud application integrated management platform and method supporting service fusion |
CN103701772A (en) * | 2013-11-26 | 2014-04-02 | 北京航空航天大学 | Method for constructing digital media content resource cloud system |
WO2019184606A1 (en) * | 2018-03-27 | 2019-10-03 | 华为技术有限公司 | Smart video processing apparatus |
CN110740274A (en) * | 2019-10-24 | 2020-01-31 | 杭州趣维科技有限公司 | system and method for accessing framework based on image video algorithm system |
-
2020
- 2020-03-27 CN CN202010230085.8A patent/CN111385604A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101038604A (en) * | 2007-04-26 | 2007-09-19 | 上海交通大学 | Vehicle impact strength computer synergic design and simulation system |
CN102739771A (en) * | 2012-04-18 | 2012-10-17 | 上海和辰信息技术有限公司 | Cloud application integrated management platform and method supporting service fusion |
CN103701772A (en) * | 2013-11-26 | 2014-04-02 | 北京航空航天大学 | Method for constructing digital media content resource cloud system |
WO2019184606A1 (en) * | 2018-03-27 | 2019-10-03 | 华为技术有限公司 | Smart video processing apparatus |
CN110740274A (en) * | 2019-10-24 | 2020-01-31 | 杭州趣维科技有限公司 | system and method for accessing framework based on image video algorithm system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11410275B2 (en) | Video coding for machine (VCM) based system and method for video super resolution (SR) | |
US20090262136A1 (en) | Methods, Systems, and Products for Transforming and Rendering Media Data | |
JP2003087785A (en) | Method of converting format of encoded video data and apparatus therefor | |
CN101065972A (en) | Method and system for streaming documents, e-mail attachments and maps to wireless devices | |
US8296416B2 (en) | Representing aggregated rich presence information | |
EP3923585A1 (en) | Video transcoding method and device | |
CN110072119A (en) | A kind of perception of content video adaptive transmission method based on deep learning network | |
CN110555076A (en) | Data marking method, processing method and device | |
WO2020108060A1 (en) | Video processing method and apparatus, and electronic device and storage medium | |
CN107862810A (en) | A kind of self-aided terminal control system based on browser | |
US11405663B2 (en) | Rendering a modeled scene | |
CN116501432A (en) | Vehicle wallpaper generation method and device, electronic equipment and readable storage medium | |
CN113191945B (en) | Heterogeneous platform-oriented high-energy-efficiency image super-resolution system and method thereof | |
CN111385604A (en) | Unified algorithm combination service method | |
Lin et al. | Im4d: High-fidelity and real-time novel view synthesis for dynamic scenes | |
CN105338371B (en) | A kind of multi-media transcoding dispatching method and device | |
EP3759884B1 (en) | Artificial intelligence (ai) based enhanced resolution content delivery | |
US20200279356A1 (en) | Method and system for enhancing image, and computer readable storage medium | |
US11166035B1 (en) | Method and device for transcoding video | |
EP3996374A1 (en) | Media processing method | |
CN112187851A (en) | Multi-screen information pushing method and device based on 5G and edge calculation | |
CN112367492A (en) | Low-bandwidth artificial intelligence portrait video transmission method | |
KR20210052884A (en) | Personalized Video Production System and Method Using Chroma Key | |
US20120290437A1 (en) | System and Method of Selecting and Acquiring Still Images from Video | |
US11979645B1 (en) | Dynamic code integration within network-delivered 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200707 |
|
RJ01 | Rejection of invention patent application after publication |