CN106777078B - Video retrieval method and system based on information database - Google Patents
Video retrieval method and system based on information database Download PDFInfo
- Publication number
- CN106777078B CN106777078B CN201611145460.9A CN201611145460A CN106777078B CN 106777078 B CN106777078 B CN 106777078B CN 201611145460 A CN201611145460 A CN 201611145460A CN 106777078 B CN106777078 B CN 106777078B
- Authority
- CN
- China
- Prior art keywords
- information database
- retrieval
- video
- original video
- query
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a video retrieval method and a system based on an information database, wherein the method comprises the following steps: establishing an information database according to original video content and geographic positions corresponding to the point positions of the cameras; and searching the associated content in the information database as required, and positioning and displaying the search result. The video retrieval method and the video retrieval system based on the information database solve the problems of large retrieval calculation amount, low retrieval speed and high error rate caused by the fact that the retrieval method in the existing video retrieval technology mainly depends on an image processing technology. According to the video retrieval method and system based on the information database, provided by the embodiment of the invention, the information database is established according to the original video, the information database is retrieved according to the actual requirement, and the retrieval result is positioned, so that the video retrieval query speed is higher, the result is more accurate, the workload of video investigation is greatly reduced, and the video retrieval efficiency is effectively improved.
Description
Technical Field
The invention relates to the technical field of videos, in particular to a video retrieval method and a video retrieval system based on an information database.
Background
In the existing video retrieval technology, video retrieval is mainly realized by means of relevant modes such as key frame extraction, image feature similarity measurement, video segment matching and the like. The above image-based retrieval method has a large amount of calculation, a slow retrieval speed, and a high error rate, resulting in low retrieval efficiency.
Particularly, in the existing surveillance video retrieval technology, rapid retrieval cannot be performed through an image-based retrieval mode, retrieval query can be performed only through a name or an ID number of a surveillance camera, and deeper rapid retrieval query cannot be performed on specific information contained in a video picture of some cameras.
Disclosure of Invention
In view of this, embodiments of the present invention provide a video retrieval method and system based on an information database, which solve the problem of low retrieval efficiency in the existing video retrieval technology.
The video retrieval method based on the information database provided by the embodiment of the invention comprises the following steps:
establishing an information database according to original video content and geographic positions corresponding to the point positions of the cameras;
and searching the associated content in the information database as required, and positioning and displaying the search result.
The video retrieval system based on the information database provided by the embodiment of the invention comprises:
and an information database device 101 is established for establishing an information database according to the original video content and the geographic position corresponding to the point location of the camera.
And the retrieval positioning device 102 is used for retrieving the associated content in the information database as required and positioning and displaying the retrieval result.
According to the video retrieval method and system based on the information database, provided by the embodiment of the invention, the information database is established according to the original video content and the geographic position corresponding to the point position of the camera, the associated content in the information database is retrieved according to the actual requirement, and the retrieval result is positioned and displayed, so that the video retrieval query speed is higher, the result is more accurate, the workload of video investigation is greatly reduced, and the video retrieval efficiency is effectively improved.
Drawings
Fig. 1 is a schematic flowchart of a video retrieval method based on an information database according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart of a video retrieval method based on an information database according to another embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating an apparatus of a video retrieval system based on an information database according to an embodiment of the present invention.
Fig. 4 is a schematic diagram illustrating an apparatus of a video retrieval system based on an information database according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
Fig. 1 is a schematic flowchart of a video retrieval method based on an information database according to an embodiment of the present invention. As shown in fig. 1, the video retrieval method based on the information database in an embodiment of the present invention includes the following steps:
step 01: and establishing an information database according to the original video content and the geographic position corresponding to the point location of the camera.
Step 02: and searching the associated content in the information database as required, and positioning and displaying the search result.
According to the video retrieval method based on the information database, the information database is established according to the original video content and the geographic position corresponding to the point position of the camera, and the internal relation of the related objects in the related content of the videos in different geographic positions is formed. The method for searching the associated content in the information database according to the actual requirement and positioning the search result enables the video search query speed to be faster and the result to be more accurate, greatly reduces the workload of video investigation and effectively improves the video search efficiency.
Fig. 2 is a schematic flowchart of a video retrieval method based on an information database according to another embodiment of the present invention. Another embodiment of the invention relates to real-time raw video, such as real-time surveillance video. As shown in fig. 2, the video retrieval method based on the information database in another embodiment of the present invention includes the following steps:
step 01: and establishing an information database according to the original video content and the geographic position corresponding to the point location of the camera.
In step 01, the original video is a surveillance video, the information contained in the surveillance video is classified and stored according to the objectification difference, and is associated with the point location of the associated surveillance camera, that is, one point location of the surveillance camera in the information database may correspond to a plurality of objects, for example, a plurality of objects such as roads, buildings, warning lines, etc. may appear in the video image of the same point location of the surveillance camera. Meanwhile, the same object may also correspond to multiple monitoring camera sites, for example, different projected images of the same building may appear in the video pictures of the multiple monitoring camera sites.
The object includes object information of an added object appearing in the video picture, such as an added vehicle, a stream of people, and the like in the video picture.
Step 02: and searching the associated content in the information database as required, and positioning and displaying the search result.
In step 02, the method further comprises the following steps:
step 021: and according to actual requirements, searching and querying the associated content in the information database.
In step 021, the information database is a keyword-based object classification information database, and the keyword-based object classification is an object classification that includes an inherent description of an object feature.
In step 021, the associated content includes an associated object, which is the content associated with the keyword to be retrieved.
In step 021, when the information database is searched, fuzzy and combined query is performed in the information database according to the keywords of the object to be searched given by the user. And, the retrieval query is a correlation query, for example, a series of information can be correlated by the name of a property company person in charge, including the name of the property unit in charge of the person, the monitoring camera location where the property company can be seen, other information of the property company, and the like.
Step 022: and according to the obtained retrieval result, positioning the camera point location and/or the associated object in the original video, and displaying or listing the specific position of the camera point location and/or the associated object in the original video or the map in a view mode.
The retrieval query is an association query, and the association object in step 022 refers to an object associated with the query keyword obtained according to the association query, and includes objects such as roads and buildings.
At step 022, the returned qualified camera points and/or associated objects may be highlighted in the original video and overlaid to display other relevant information to obtain the required information quickly.
In step 022, when the camera location and/or the associated object need to be displayed on the map, an electronic map is called up in advance, the specific geographic location of the camera location and/or the associated object is marked on the map, and a specific video related to the camera location and/or the associated object is linked. The distribution characteristics of the point locations and/or the associated objects of the camera are checked by combining a map, and the real-time video can be rapidly and independently selected and called out through mouse or touch screen gesture operation, or operations such as watching back the video recording or controlling the cloud deck are carried out.
It should be understood that the electronic map is an electronic map of the area in the original video where the camera spot is located.
It should be understood that other real-time original videos similar to the surveillance video are suitable for the video retrieval method based on the information database provided by another embodiment of the present invention, such as program videos in a video camera for capturing programs at fixed points in real time of a television station.
According to the video retrieval method based on the information database, provided by the embodiment of the invention, the information database is established according to the original video content and the geographic position, the retrieval query is carried out on the associated content in the information database according to the actual requirement, the monitoring camera point location is positioned in the monitoring video according to the obtained query result, and the specific position in the video picture or the map is given through view display or list, so that the retrieval query of the monitoring video is more accurate and rapid, and the video retrieval efficiency is effectively improved. Particularly, in the case handling process of the policemen, the policemen can quickly acquire important video information required by case handling through the video retrieval method provided by the embodiment of the invention and perform positioning display in the original video or electronic map, so that the case handling efficiency is effectively improved.
On the basis of the above embodiment, another embodiment of the present invention relates to an existing original video, such as an original video of a building logo, such as an old palace. As shown in fig. 2, the video retrieval method based on the information database in another embodiment of the present invention includes the following steps:
step 01: and establishing an information database according to the original video content and the geographic position corresponding to the point location of the camera.
In step 01, the original video is an existing original video, such as a womb original video. The information contained in the existing original video is classified and stored according to the difference of adding objects, and is associated with the affiliated camera point location, that is, one camera point location in the information database can correspond to a plurality of adding objects, for example, a video picture containing a plurality of adding objects such as roads, palace, shopping shops and the like appears in the same camera point location. Meanwhile, the added object containing the same video information may also correspond to multiple camera points, for example, in the original image of the uterus, the uterus may appear in the video images of multiple camera points.
Step 02: and searching the associated content in the information database as required, and positioning and displaying the search result.
In step 02, the method further comprises the following steps:
step 021: and according to actual requirements, searching and querying the associated content in the information database.
In step 021, when the information database is searched, fuzzy and combined search is performed in the information database according to the keywords to be searched given by the user, and the search is related.
In step 021, when fuzzy query is performed on the keyword, the ambiguity can be manually set, and the ambiguity can also be zero, i.e. direct and accurate query. When the ambiguity is a low-order segment, the lower the ambiguity is, the closer the query is to the accurate query; and when the ambiguity is in a high-order segment, the higher the query ambiguity is. The fuzzy degree from the low-order section to the high-order section is in a linear increasing trend.
For example, when the field query of "imperial concubine dormitory" is performed through the original image of the Imperial palace, when the ambiguity is set to be a high-order segment, the video information related to the fields of "imperial concubine", "dormitory", "imperial concubine dormitory" and the like is queried; when the ambiguity is set to a low-order segment, only the video information related to the "Fei Zi Dou Gong" field is queried.
Step 022: and according to the obtained retrieval result, positioning the camera point location and/or the associated object in the original video, and displaying or listing the specific position of the camera point location and/or the associated object in the original video or the map in a view mode.
It should be understood that other existing videos similar to the original videos of the palace are all suitable for the video retrieval method based on the information database provided by the embodiment of the present invention, for example, the classroom teaching video.
The video retrieval method based on the information database provided by the embodiment of the invention can not only carry out retrieval and query through the point position of the camera or the ID number of the camera, but also carry out retrieval and query aiming at the specific information of the associated object in the video picture, and the hierarchical retrieval and query mode can lead the retrieval and query to be faster and more accurate and effectively improve the video retrieval efficiency.
Fig. 3 is a schematic diagram illustrating an apparatus of a video retrieval system based on an information database according to an embodiment of the present invention. As shown in fig. 3, the video retrieval system based on information database in an embodiment of the present invention includes:
and an information database device 101 is established for establishing an information database according to the original video content and the geographic position corresponding to the point location of the camera.
And the retrieval positioning device 102 is used for retrieving the associated content in the information database as required and positioning and displaying the retrieval result.
Fig. 4 is a schematic diagram illustrating an apparatus of a video retrieval system based on an information database according to another embodiment of the present invention. As shown in fig. 4, the video retrieval system based on information database in another embodiment of the present invention includes:
and an information database device 101 is established for establishing an information database according to the original video content and the geographic position corresponding to the point location of the camera.
And the retrieval positioning device 102 is used for retrieving the associated content in the information database as required and positioning and displaying the retrieval result.
The retrieving and positioning device 102 further comprises:
and the retrieval device 1021 is used for performing retrieval query on the associated content in the information database according to actual requirements.
And the positioning device 1022 is configured to, according to the obtained retrieval result, perform positioning of the camera location and/or the associated object in the original video, and view or list a specific position of the camera location and/or the associated object in the original video or the map.
It should be understood that although several modules or units of the apparatus are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, according to exemplary embodiments of the invention, the features and functions of two or more modules/units described above may be implemented in one module/unit, whereas the features and functions of one module/unit described above may be further divided into implementations by a plurality of modules/units. Furthermore, some of the modules/units described above may be omitted in some application scenarios.
It is also to be understood that the description has described only some of the critical, not necessarily essential, techniques and features, and may not have described some of the features that could be implemented by those skilled in the art, in order not to obscure the embodiments of the invention.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and the like that are within the spirit and principle of the present invention are included in the present invention.
Claims (5)
1. A video retrieval method based on an information database is characterized by comprising the following steps:
establishing an information database according to original video content and a geographic position corresponding to a camera point location, wherein the information database is an object classification information database based on keywords obtained by classifying and storing information contained in the original video according to objectification differences and associating the information with the affiliated camera point location, the object comprises at least one of a road, a building and an alert line, and the original video is a real-time original video;
retrieving the associated content in the information database as required, and positioning and displaying the retrieval result, wherein the retrieving the associated content in the information database as required, and positioning and displaying the retrieval result comprise:
according to actual requirements, searching and querying the associated content in the information database;
and according to the obtained retrieval result, positioning the camera point location and/or the associated object in the original video, and displaying or listing the specific position of the camera point location and/or the associated object in a map in a view mode, wherein the map is an electronic map of the area where the camera point location is located in the original video.
2. The method of claim 1, wherein the search query is a fuzzy, combinatorial query.
3. The method of claim 1, wherein the search query is an association query.
4. The method of claim 1, wherein the associated object is: when the retrieval query is carried out, the obtained object is related to the keyword of the query.
5. A video retrieval system based on an information database, comprising:
the method comprises the steps of establishing an information database device (101) for establishing an information database according to original video content and geographic positions corresponding to camera point locations, wherein the information database is an object classification information database based on keywords, which is obtained by classifying and storing information contained in original videos according to objectification differences and associating the information with the affiliated camera point locations, the object comprises at least one of a road, a building and a warning line, and the original videos are real-time original videos;
the retrieval positioning device (102) is used for retrieving the associated content in the information database according to the requirement and positioning and displaying the retrieval result, wherein the retrieval positioning device (102) comprises:
the retrieval device (1021) is used for carrying out retrieval query on the associated content in the information database according to actual requirements;
and the positioning device (1022) is used for positioning the camera point location and/or the associated object in the original video according to the obtained retrieval result, and displaying or listing the specific position of the camera point location and/or the associated object in the original video or a map in a view mode, wherein the map is an electronic map of the region where the camera point location is located in the original video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611145460.9A CN106777078B (en) | 2016-12-13 | 2016-12-13 | Video retrieval method and system based on information database |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611145460.9A CN106777078B (en) | 2016-12-13 | 2016-12-13 | Video retrieval method and system based on information database |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106777078A CN106777078A (en) | 2017-05-31 |
| CN106777078B true CN106777078B (en) | 2020-12-22 |
Family
ID=58876318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611145460.9A Active CN106777078B (en) | 2016-12-13 | 2016-12-13 | Video retrieval method and system based on information database |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106777078B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480228A (en) * | 2017-08-03 | 2017-12-15 | 深圳市置辰海信科技有限公司 | A kind of monitor video searching method towards hard objectives |
| CN110582009A (en) * | 2018-06-11 | 2019-12-17 | 上海金桥信息股份有限公司 | method and device for superposing retina information in video |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071447A (en) * | 2006-03-06 | 2007-11-14 | 索尼株式会社 | Search system, image-capturing apparatus, data storage apparatus, information processing apparatus |
| CN103955494A (en) * | 2014-04-18 | 2014-07-30 | 大唐联智信息技术有限公司 | Searching method and device of target object and terminal |
| CN104519319A (en) * | 2014-12-11 | 2015-04-15 | 北京中星微电子有限公司 | Method and device for surveillance video display of electronic map |
| CN104581000A (en) * | 2013-10-12 | 2015-04-29 | 北京航天长峰科技工业集团有限公司 | Method for rapidly retrieving motional trajectory of interested video target |
| CN105721825A (en) * | 2014-12-02 | 2016-06-29 | 四川浩特通信有限公司 | Intelligent combat system |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080294694A1 (en) * | 2007-05-24 | 2008-11-27 | Videoclix Technologies Inc. | Method, apparatus, system, medium, and signals for producing interactive video content |
| US8370382B2 (en) * | 2008-05-21 | 2013-02-05 | Ji Zhang | Method for facilitating the search of video content |
| CN101330604B (en) * | 2008-07-25 | 2012-01-11 | 北京中星微电子有限公司 | Retrieval method, apparatus and system for monitoring video image |
| CN101778260B (en) * | 2009-12-29 | 2012-01-04 | 公安部第三研究所 | Method and system for monitoring and managing videos on basis of structured description |
| CN101937452B (en) * | 2010-08-19 | 2012-01-11 | 周寅 | Schematization storage and retrieval method for video electronic map |
| EP2708032A4 (en) * | 2011-05-12 | 2014-10-29 | Solink Corp | Video analytics system |
| CN102289520A (en) * | 2011-09-15 | 2011-12-21 | 山西四和交通工程有限责任公司 | Traffic video retrieval system and realization method thereof |
| CN105138525B (en) * | 2014-05-30 | 2019-10-01 | 株式会社日立制作所 | Traffic video processing unit and method and retrieval device and method |
| CN105975570B (en) * | 2016-05-04 | 2019-10-18 | 深圳市至壹科技开发有限公司 | Video searching method and system based on geographical location |
-
2016
- 2016-12-13 CN CN201611145460.9A patent/CN106777078B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071447A (en) * | 2006-03-06 | 2007-11-14 | 索尼株式会社 | Search system, image-capturing apparatus, data storage apparatus, information processing apparatus |
| CN104581000A (en) * | 2013-10-12 | 2015-04-29 | 北京航天长峰科技工业集团有限公司 | Method for rapidly retrieving motional trajectory of interested video target |
| CN103955494A (en) * | 2014-04-18 | 2014-07-30 | 大唐联智信息技术有限公司 | Searching method and device of target object and terminal |
| CN105721825A (en) * | 2014-12-02 | 2016-06-29 | 四川浩特通信有限公司 | Intelligent combat system |
| CN104519319A (en) * | 2014-12-11 | 2015-04-15 | 北京中星微电子有限公司 | Method and device for surveillance video display of electronic map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106777078A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Vision meets drones: A challenge | |
| CN109871815B (en) | Method and device for inquiring monitoring information | |
| CN101778260B (en) | Method and system for monitoring and managing videos on basis of structured description | |
| US9684719B2 (en) | Object search by description | |
| US20170024899A1 (en) | Multi-source multi-modal activity recognition in aerial video surveillance | |
| US20080316311A1 (en) | Video Retrieval System, Method and Computer Program for Surveillance of Moving Objects | |
| Arslan Ay et al. | Relevance ranking in georeferenced video search | |
| US20180357316A1 (en) | Arrangement and related method for provision of video items | |
| US20140355823A1 (en) | Video search apparatus and method | |
| CN105787062A (en) | Method and equipment for searching for target object based on video platform | |
| TW201426353A (en) | Interactive object retrieval method and system based on association information | |
| CN109857891A (en) | A kind of querying method and device | |
| CN105608209A (en) | Video labeling method and video labeling device | |
| WO2024055966A1 (en) | Multi-camera target detection method and apparatus | |
| CN106777078B (en) | Video retrieval method and system based on information database | |
| CN115004273A (en) | Digital reconstruction method, device and system for traffic road | |
| Gochoo et al. | Fisheye8k: A benchmark and dataset for fisheye camera object detection | |
| CN116383436A (en) | Monitoring intelligent analysis method and device, electronic equipment and storage medium | |
| JP5356289B2 (en) | Image search system | |
| CN105447022A (en) | Method for rapidly searching target object | |
| Kim et al. | GeoTree: Using spatial information for georeferenced video search | |
| Zaman et al. | A robust deep networks based multi-object multi-camera tracking system for city scale traffic | |
| Wang et al. | Multi-attribute object detection benchmark for smart city | |
| van de Wouw et al. | Real-time change detection for countering improvised explosive devices | |
| CN110781797B (en) | Labeling method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |