CN103902594A - Sub-shot inverted index based matching method - Google Patents
Sub-shot inverted index based matching method Download PDFInfo
- Publication number
- CN103902594A CN103902594A CN201210581097.0A CN201210581097A CN103902594A CN 103902594 A CN103902594 A CN 103902594A CN 201210581097 A CN201210581097 A CN 201210581097A CN 103902594 A CN103902594 A CN 103902594A
- Authority
- CN
- China
- Prior art keywords
- sub
- shot
- camera lens
- inverted index
- 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
Classifications
-
- 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
- G06F16/71—Indexing; Data structures therefor; Storage structures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a sub-shot inverted index based matching method. The method includes the steps of 1, inputting a video; 2, subjecting the input video to feature extraction by sub-shot segmentation; 3, inputting extracted features to a visual keyword dictionary; 4, after building the visual keyword dictionary, performing sub-shot feature quantification; 5, using quantified sub-shot features as basic units of an index to build a sub-shot code index table and a sub-shot inverted index table. The method has the advantages that after the visual keyword dictionary is built, any decrease or increase can be performed on a video database just by modifying the corresponding sub-shot code index table and sub-shot inverted index table with no need of rebuilding the index; query speed of sub-shots is not significantly increased with increase of data amount of the video database.
Description
Technical field
The present invention relates to the field of video database, especially a kind of matching process based on sub-camera lens inverted index.
Background technology
Universal along with the accumulation of TV programme and Internet video, scale and the capacity of video database increase sharply, so automatically to a large amount of and just analyzing and understanding at ever-increasing video and become a more and more urgent task.Meanwhile, organizing video data realize quick-searching and also become more and more important research topic how.
For video frequency searching, existing general method is mainly by manual method, the content in video to be marked, and then according to this mark, video is organized and index.The shortcoming of this method is that making to mark is by hand a job of wasting time and energy in the video sample space of a large amount of even magnanimity, uses some mark words or word paragraph to be difficult to all sake of clarity of contents whole in video simultaneously.So from the angle of development, should, more from the content of video, find the video mating most with target video in video library for video storage tissue and the index of magnanimity.
The search method using at present, retrieval rate is slow, and the increase of index data amount has increased the complexity of calculating.
Summary of the invention
The technical problem to be solved in the present invention is: in order to overcome the problem of above-mentioned middle existence, provide a kind of matching process based on sub-camera lens inverted index, its index speed is fast, can not occur significant increase because of the growth of the data volume of video database
The technical solution adopted for the present invention to solve the technical problems is: a kind of matching process based on sub-camera lens inverted index, build the inverted index of sub-camera lens, and carry out the quick-searching to keyword, concrete steps are as follows:
(1) input video;
(2) utilize sub-camera lens to cut apart feature extraction to input video;
(3) by the feature input vision keyword dictionary extracting;
(4) vision keyword dictionary carries out sub-lens features quantification after building;
(5) the sub-lens features after quantification is as the base unit of index, for constructing sub-camera lens code index table and sub-camera lens inverted index table.
The invention has the beneficial effects as follows, a kind of matching process based on sub-camera lens inverted index of the present invention, after vision keyword dictionary builds, any increase and decrease to video database, only need amendment corresponding sub-camera lens code index table and sub-camera lens inverted index table, without re-establishing index, can't there is significant increase because of the growth of the data volume of video database in the inquiry velocity of sub-camera lens.
Brief description of the drawings
Below in conjunction with drawings and Examples, the present invention is further described.
Fig. 1 is structural representation of the present invention.
Embodiment
In conjunction with the accompanying drawings, the present invention is further detailed explanation.These accompanying drawings are the schematic diagram of simplification, and basic structure of the present invention is only described in a schematic way, and therefore it only shows the formation relevant with the present invention.
A kind of matching process based on sub-camera lens inverted index as shown in Figure 1, builds the inverted index of sub-camera lens, carries out the quick-searching to keyword, and concrete steps are as follows:
(1) input video;
(2) utilize sub-camera lens to cut apart feature extraction to input video;
(3) by the feature input vision keyword dictionary extracting;
(4) vision keyword dictionary carries out sub-lens features quantification after building;
(5) the sub-lens features after quantification is as the base unit of index, for constructing sub-camera lens code index table and sub-camera lens inverted index table.
A kind of matching process based on sub-camera lens inverted index of the present invention, inquiry is reduced to characteristic quantification and the string integer search procedure of sub-camera lens, finally returns to the position of the sub-camera lens with same characteristic features coding in video database.Whole process all sub-camera lens and calculate the sub-camera lens and the similarity of database neutron camera lens of inquiry in need not sequential scanning video database, has greatly reduced the complexity of calculating.
Taking above-mentioned foundation desirable embodiment of the present invention as enlightenment, by above-mentioned description, relevant staff can, not departing from the scope of this invention technological thought, carry out various change and amendment completely.The technical scope of this invention is not limited to the content on instructions, must determine its technical scope according to claim scope.
Claims (1)
1. the matching process based on sub-camera lens inverted index, builds the inverted index of sub-camera lens, carries out the quick-searching to keyword, it is characterized in that concrete steps are as follows:
(1) input video;
(2) utilize sub-camera lens to cut apart feature extraction to input video;
(3) by the feature input vision keyword dictionary extracting;
(4) vision keyword dictionary carries out sub-lens features quantification after building;
(5) the sub-lens features after quantification is as the base unit of index, for constructing sub-camera lens code index table and sub-camera lens inverted index table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210581097.0A CN103902594A (en) | 2012-12-28 | 2012-12-28 | Sub-shot inverted index based matching method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210581097.0A CN103902594A (en) | 2012-12-28 | 2012-12-28 | Sub-shot inverted index based matching method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103902594A true CN103902594A (en) | 2014-07-02 |
Family
ID=50993922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210581097.0A Pending CN103902594A (en) | 2012-12-28 | 2012-12-28 | Sub-shot inverted index based matching method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103902594A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115004173A (en) * | 2020-04-14 | 2022-09-02 | 深圳市欢太科技有限公司 | Text matching method and device, electronic equipment and storage medium |
-
2012
- 2012-12-28 CN CN201210581097.0A patent/CN103902594A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| 李远宁等: "基于"bag of words"的视频匹配方法", 《通信学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115004173A (en) * | 2020-04-14 | 2022-09-02 | 深圳市欢太科技有限公司 | Text matching method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2940557B1 (en) | Method and device used for providing input candidate item corresponding to input character string | |
| CN102073692B (en) | Based on the semantic retrieval system and method for agriculture field ontology library | |
| CN102339294B (en) | Searching method and system for preprocessing keywords | |
| CN108121739B (en) | Data collection method and data collection system | |
| CN112527948B (en) | Sentence-level index-based real-time data deduplication method and system | |
| CN104281698A (en) | Efficient big data query method | |
| JP2022191412A (en) | Method for training multi-target image-text matching model and image-text retrieval method and apparatus | |
| CN103885939A (en) | Uyghur-Chinese bi-directional translation memory system construction method | |
| CN102567409A (en) | Method and device for providing retrieval associated word | |
| CN113190687B (en) | Knowledge graph determining method and device, computer equipment and storage medium | |
| CN105868177A (en) | Universal formula search method | |
| CN108268600A (en) | Unstructured Data Management and device based on AI | |
| CN106407180A (en) | Entity disambiguation method and apparatus | |
| CN103279551A (en) | High-dimensional data accurate neighbor quick searching method based on euclidean distance | |
| CN102819592A (en) | Lucene-based desktop searching system and method | |
| CN104778182A (en) | Data import method and system based on HBase (Hadoop Database) | |
| CN103678273A (en) | Internet paragraph level topic recognition system | |
| CN104915405A (en) | Microblog query expansion method based on multiple layers | |
| CN113596601A (en) | Video picture positioning method, related device, equipment and storage medium | |
| CN117332103A (en) | Image retrieval method based on keyword extraction and multi-modal feature fusion | |
| CN103902594A (en) | Sub-shot inverted index based matching method | |
| CN105005619A (en) | Rapid retrieval method and system for mass website basic information | |
| CN116595043A (en) | Big data retrieval method and device | |
| CN113806376B (en) | Index construction method and device | |
| CN115408532A (en) | Open source information-oriented weapon equipment knowledge graph construction method, system, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140702 |
|
| WD01 | Invention patent application deemed withdrawn after publication |