CN111259728A - Video image information labeling method - Google Patents
Video image information labeling method Download PDFInfo
- Publication number
- CN111259728A CN111259728A CN201911327230.8A CN201911327230A CN111259728A CN 111259728 A CN111259728 A CN 111259728A CN 201911327230 A CN201911327230 A CN 201911327230A CN 111259728 A CN111259728 A CN 111259728A
- Authority
- CN
- China
- Prior art keywords
- picture information
- labeling
- database
- independent
- short video
- 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
- 238000002372 labelling Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 10
- 230000007547 defect Effects 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of video content processing, and particularly relates to a video image information labeling method, which comprises the following steps: step one, establishing a picture information labeling database; step two, transmitting the real-time videos recorded on site to a labeling server in a short video form, and identifying images in the short videos by using an identification model to acquire a plurality of pieces of independent picture information to be labeled; and step three, comparing the independent picture information to be marked with a picture information marking database, overcoming the defects of the prior art, firstly establishing and perfecting the picture information marking database, then conveying the picture information marking database to a marking server in the process of recording the video on site, and conveying the picture information marking database to a display after marking the picture information marking database by using the marking server.
Description
Technical Field
The invention belongs to the technical field of video content processing, and particularly relates to a video image information labeling method.
Background
The production and processing are the processing of purchasing raw materials in a large scale, standardization and production line by oneself, and the large scale, standardization and production line are the most important characteristics of the processing and manufacturing industry. The most fundamental competitive way of the process manufacturing industry, relative to the equipment manufacturing industry, is cost price competition. The conventional manufacturing industry uses the products of past labor as the labor objects, such as metallurgy, machinery, electronics, chemistry, petrochemical industry, wood processing, building materials, paper making, textile, food, leather industry. With the development of technology, the processing and manufacturing industry gradually turns to the high value-added processing and manufacturing industry utilizing high technology, new process and new material production.
However, with the development of intelligent production, the number of people in a factory is less and less, and therefore the production process needs to be monitored through a camera, but most of the existing camera monitoring has only a camera shooting function and does not have the functions of monitoring, identifying and automatically marking.
Disclosure of Invention
The invention aims to provide a video image information labeling method, which overcomes the defects of the prior art, firstly establishes and perfects a picture information labeling database, then transmits the database to a labeling server in the process of recording a video on site, and transmits the database to a display after the labeling server performs labeling processing.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a video image information annotation method comprises the following steps:
step one, establishing a picture information labeling database, analyzing a large number of existing related images by using an identification model to obtain a plurality of independent picture information, labeling each independent picture information in a manual labeling mode, and establishing a picture information labeling database;
step two, transmitting the real-time videos recorded on site to a labeling server in a short video form, wherein the shortest time of the short video is one frame, and identifying images in the short video by using an identification model to acquire a plurality of pieces of independent picture information to be labeled;
and step three, comparing the independent picture information to be marked with the picture information marking database, finding out corresponding picture information with the similarity of more than 99%, copying marks on the corresponding picture information to the independent picture information to be marked, then recombining a plurality of independent picture information to be marked into a short video, and finally transmitting the short video to a display.
Further, the independent picture information to be labeled is compared with the picture information labeling database one by adopting the outline comparison.
And further, the outlines are compared one by one, the relative positions of the pixel points at the whole edge of the picture information are compared firstly, then the relative positions of the pixel points at the edges of each independent color are compared, and finally the relative positions of each independent color in the whole picture information are compared.
Further, in the third step, when the marked picture information corresponding to the short video is found, the short video is recombined and the picture information corresponding to the marked picture information is found to be combined together, the short video and the picture information are synchronously transmitted to the picture information marking database and are stored separately, and then the picture information marking database is perfected by adopting a manual marking mode.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a video image information labeling method, which comprises the steps of firstly establishing and perfecting a picture information labeling database, then conveying the database to a labeling server in the process of recording a video on site, and conveying the database to a display after labeling processing by using the labeling server.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention relates to a video image information labeling method, which comprises the following steps: step one, establishing a picture information labeling database, analyzing a large number of existing related images by using an identification model to obtain a plurality of independent picture information, labeling each independent picture information in a manual labeling mode, and establishing a picture information labeling database; step two, transmitting the real-time videos recorded on site to a labeling server in a short video form, wherein the shortest time of the short video is one frame, and identifying images in the short video by using an identification model to acquire a plurality of pieces of independent picture information to be labeled; and step three, comparing the independent picture information to be marked with the picture information marking database, finding out corresponding picture information with the similarity of more than 99%, copying marks on the corresponding picture information to the independent picture information to be marked, then recombining a plurality of independent picture information to be marked into a short video, and finally transmitting the short video to a display.
Further, the independent picture information to be labeled is compared with a picture information labeling database one by adopting outlines; comparing the outlines one by one, firstly comparing the relative positions of pixel points at the whole edge of the picture information, then comparing the relative positions of the pixel points at the edge of each independent color, and finally comparing the relative positions of each independent color in the whole picture information; and in the third step, when the marked picture information corresponding to the short video is found, the short video is recombined and the picture information corresponding to the marked picture information is found, the short video and the picture information are combined together, the short video and the picture information are synchronously transmitted to a picture information marking database and are independently stored, and then the picture information marking database is perfected by adopting a manual marking mode.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (4)
1. A video image information labeling method is characterized in that: the method comprises the following steps:
step one, establishing a picture information labeling database, analyzing a large number of existing related images by using an identification model to obtain a plurality of independent picture information, labeling each independent picture information in a manual labeling mode, and establishing a picture information labeling database;
step two, transmitting the real-time videos recorded on site to a labeling server in a short video form, wherein the shortest time of the short video is one frame, and identifying images in the short video by using an identification model to acquire a plurality of pieces of independent picture information to be labeled;
and step three, comparing the independent picture information to be marked with the picture information marking database, finding out corresponding picture information with the similarity of more than 99%, copying marks on the corresponding picture information to the independent picture information to be marked, then recombining a plurality of independent picture information to be marked into a short video, and finally transmitting the short video to a display.
2. The method for labeling video image information according to claim 1, wherein: and comparing the independent picture information to be labeled with the picture information labeling database one by adopting the outlines.
3. The method for labeling video image information according to claim 1, wherein: the outlines are compared one by one, the relative positions of the pixel points at the whole edge of the picture information are compared firstly, then the relative positions of the pixel points at the edge of each independent color are compared, and finally the relative positions of each independent color in the whole picture information are compared.
4. The method for labeling video image information according to claim 1, wherein: and in the third step, when the marked picture information corresponding to the short video is found, the short video is recombined and the picture information corresponding to the marked picture information is found, the short video and the picture information are combined together, the short video and the picture information are synchronously transmitted to a picture information marking database and are independently stored, and then the picture information marking database is perfected by adopting a manual marking mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911327230.8A CN111259728A (en) | 2019-12-20 | 2019-12-20 | Video image information labeling method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911327230.8A CN111259728A (en) | 2019-12-20 | 2019-12-20 | Video image information labeling method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111259728A true CN111259728A (en) | 2020-06-09 |
Family
ID=70953915
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911327230.8A Pending CN111259728A (en) | 2019-12-20 | 2019-12-20 | Video image information labeling method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111259728A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136543A (en) * | 2011-12-02 | 2013-06-05 | 鸿富锦精密工业(深圳)有限公司 | Image processing device and image processing method |
CN104883515A (en) * | 2015-05-22 | 2015-09-02 | 广东威创视讯科技股份有限公司 | Video annotation processing method and video annotation processing server |
CN105094760A (en) * | 2014-04-28 | 2015-11-25 | 小米科技有限责任公司 | Picture marking method and device |
CN105117723A (en) * | 2015-08-17 | 2015-12-02 | 浪潮软件集团有限公司 | Image identification method and device |
CN105451029A (en) * | 2015-12-02 | 2016-03-30 | 广州华多网络科技有限公司 | Video image processing method and device |
CN105678758A (en) * | 2015-12-31 | 2016-06-15 | 天津慧医谷科技有限公司 | Image feature automatic identifying and extracting method |
CN106878674A (en) * | 2017-01-10 | 2017-06-20 | 哈尔滨工业大学深圳研究生院 | A kind of parking detection method and device based on monitor video |
CN109241907A (en) * | 2018-09-03 | 2019-01-18 | 北京旷视科技有限公司 | Mask method, device and electronic equipment |
CN109345562A (en) * | 2018-09-26 | 2019-02-15 | 贵州优易合创大数据资产运营有限公司 | A kind of traffic picture intelligent dimension system |
-
2019
- 2019-12-20 CN CN201911327230.8A patent/CN111259728A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136543A (en) * | 2011-12-02 | 2013-06-05 | 鸿富锦精密工业(深圳)有限公司 | Image processing device and image processing method |
CN105094760A (en) * | 2014-04-28 | 2015-11-25 | 小米科技有限责任公司 | Picture marking method and device |
CN104883515A (en) * | 2015-05-22 | 2015-09-02 | 广东威创视讯科技股份有限公司 | Video annotation processing method and video annotation processing server |
CN105117723A (en) * | 2015-08-17 | 2015-12-02 | 浪潮软件集团有限公司 | Image identification method and device |
CN105451029A (en) * | 2015-12-02 | 2016-03-30 | 广州华多网络科技有限公司 | Video image processing method and device |
CN105678758A (en) * | 2015-12-31 | 2016-06-15 | 天津慧医谷科技有限公司 | Image feature automatic identifying and extracting method |
CN106878674A (en) * | 2017-01-10 | 2017-06-20 | 哈尔滨工业大学深圳研究生院 | A kind of parking detection method and device based on monitor video |
CN109241907A (en) * | 2018-09-03 | 2019-01-18 | 北京旷视科技有限公司 | Mask method, device and electronic equipment |
CN109345562A (en) * | 2018-09-26 | 2019-02-15 | 贵州优易合创大数据资产运营有限公司 | A kind of traffic picture intelligent dimension system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110473170B (en) | Artificial intelligence detection method suitable for judging true and false defects of PCB | |
CN103477349B (en) | Landmark identification | |
CN103358685B (en) | Produce the method for printing packaging | |
CN108830147A (en) | A kind of commodity on shelf price recognition methods based on image recognition, device and system | |
CN103150564A (en) | Plate surface code spraying character recognition device and method thereof | |
JP5409910B2 (en) | Non-product image identification | |
CN104458748A (en) | Aluminum profile surface defect detecting method based on machine vision | |
CN105069640A (en) | Agricultural product tracing system and method based on random artificial mark and feature photo | |
CN110136166A (en) | A kind of automatic tracking method of multichannel picture | |
CN112801965A (en) | Sintering belt foreign matter monitoring method and system based on convolutional neural network | |
CN105184506A (en) | Cast pipe quality management method, cast pipe produced by using above method, and two-dimensional barcode tag | |
CN104182752A (en) | Intelligent monitoring method of outdoor advertising board | |
CN111259728A (en) | Video image information labeling method | |
CN111738769A (en) | Video processing method and device | |
CN103870966A (en) | Product tracing method | |
CN114820470A (en) | Plate defect detection system and detection method based on multi-feature fusion | |
Ruban et al. | The model and the method for forming a mosaic sustainable marker of augmented reality | |
CN114186933A (en) | Cold chain food intelligent supervision platform | |
CN104021546B (en) | The workpiece online method for rapidly positioning of label based on image procossing | |
CN114267213A (en) | Real-time demonstration method, device, equipment and storage medium for practical training | |
CN109493084A (en) | A kind of anti-fake method for preventing goods from altering based on the identification of sequential image information code | |
CN111491193B (en) | Method for automatically presenting live broadcast picture information of electric competition | |
CN112419239A (en) | Online jadeite rating method based on deep learning | |
CN107665331A (en) | A kind of production line Intelligent Recognition and automatic transmission system and method | |
CN111263108A (en) | Intelligent production video monitoring method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200609 |