CN101459828A - Image monitoring system based on target retrieval and recognition - Google Patents
Image monitoring system based on target retrieval and recognition Download PDFInfo
- Publication number
- CN101459828A CN101459828A CNA2007101687482A CN200710168748A CN101459828A CN 101459828 A CN101459828 A CN 101459828A CN A2007101687482 A CNA2007101687482 A CN A2007101687482A CN 200710168748 A CN200710168748 A CN 200710168748A CN 101459828 A CN101459828 A CN 101459828A
- Authority
- CN
- China
- Prior art keywords
- image
- retrieval
- transmitter
- monitoring system
- dissector
- 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
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to an image monitoring system based on object retrieval and identifying, which comprises at least one image sensor and an image application terminal, wherein an image data base is generated in the image application terminal. The system is characterized in that an image processor is further arranged between the image sensor and the image application terminal, wherein the image processor analyzes the output of each of the image sensors, identifies the characteristics of each object, and codes the characteristics of each object to form an image retrieval frame, and the image retrieval frame is transmitted to the image application terminal through an image transmitter to form an image retrieval frame date base. The image application terminal of the invention firstly carries out the retrieval to the characteristics of the objects through the image retrieval data base, if the characteristics satisfy the conditions of the object characteristics, the area geographical location information and the time information in the image retrieval frame are utilized, calls out the image information of the area at the time in the image information data base, and thereby the retrieval risk can be completed, which greatly improves the retrieval speed and saves an amount of labor and time.
Description
Technical field
The invention belongs to a kind of image monitoring system, is a kind of based target retrieval and the image monitoring system of discerning specifically.
Background technology
At present in environment to the social safety growing interest, image monitoring system in various occasions by a large amount of uses, these views monitor day and night in the zone that sets as viewing system and monitor log are stored on the computer-readable recording medium, when certain user need inquire about specific object at a time between section when whether appearing at regional that this sets, need assemble all should the time period, all are stored in monitor log on the computer-readable recording medium this zone that sets, and carefully watch each frame image information of these monitor logs, and therefrom analyze certain specific object situation by manual method.Because these image monitoring systems only have only writing function, can not provide and analyze classification, retrieval and query function, make utilize image monitoring system inquire about certain specific object at a time between section need waste great amount of manpower and a large amount of time when whether appearing at regional that this sets.
Summary of the invention
The purpose of this invention is to provide a kind of image monitoring system that has analytic function, sets based target identification with the retrieval of retrieval frame, to overcome above-mentioned deficiency.
To achieve these goals, the present invention includes at least one imageing sensor and an image applications terminal, wherein the output of each imageing sensor is connected with the image applications terminal, in the image applications terminal, generate an image data base, be characterized in: between imageing sensor and image applications terminal, also be provided with image processor, the input of image processor links to each other with the output of each imageing sensor, and the output of image processor is connected with the image applications terminal.
Above-mentioned image processor comprises image dissector and image transmitter, the output of each imageing sensor links to each other with the image dissector input, the output of each imageing sensor is also joined with image transmitter input, the output of image dissector is also joined with image transmitter input, and the output of image transmitter is connected with the image applications terminal.
The output of above-mentioned each imageing sensor is connected with the image transmitter with image dissector respectively by an image converter in the image processor.
Above-mentioned image dissector is analyzed the output of a certain each imageing sensor of the moment, discern each clarification of objective, and each clarification of objective is made coding form the image retrieval frame, all target image retrieval frames that form in the image dissector are transferred to the image applications terminal by the image transmitter, form image retrieval frame data storehouse in the image applications terminal.
In the above-mentioned image retrieval frame, its coding comprises monitor area geographic orientation information and temporal information.
In the above-mentioned image retrieval frame, if institute's monitored object is the people, its coding comprises people's macroscopic features.
In the above-mentioned image retrieval frame, if institute's monitored object is a thing, its coding comprises geometry, physical dimension and the sign sign of object.
Above-mentioned image dissector is by long-range setting, for the image dissector database that supplies a model, is used to change various analytical parameters.
Because the present invention also is provided with an image dissector before the image applications terminal, image dissector is exported the image retrieval frame of each target, make the image information data storehouse that existing former surveillance produced in the image applications terminal, there is image dissector to produce the image retrieval frame data storehouse that is given birth to again, if certain user need inquire about certain specific target at a time between the section whether appear at this surveillance set the zone retrieval the time, only need utilize related software that some features of specific objective are inputed in the image applications terminal, the image applications terminal is retrieved these target signatures by image retrieval frame data storehouse earlier, if satisfy the target signature condition, then utilize regional geography azimuth information and the temporal information that retrieves in the image retrieval frame, access this zone in the image information data storehouse in the image information of this time, can finish retrieval tasks, so greatly improve retrieval rate, saved great amount of manpower and time.
Description of drawings
Fig. 1 is a theory diagram of the present invention.
Fig. 2 is the theory diagram of the embodiment of the invention.
Embodiment
The present invention is described in further detail below in conjunction with drawings and Examples, but following embodiment should not be construed as limitation of the present invention.
The present invention includes at least one imageing sensor and an image applications terminal, wherein the output of each imageing sensor is connected with the image applications terminal, in the image applications terminal, generate an image data base, between imageing sensor and image applications terminal, also be provided with image processor, image processor comprises image converter, image dissector and image transmitter, the output of each imageing sensor links to each other with the image dissector input, the output of each imageing sensor is also joined with image transmitter input, the output of image dissector is also joined with image transmitter input, the output of image transmitter be connected with the image applications terminal (Fig. 1).Image dissector can be provided with by remote terminal, for the image dissector database that supplies a model, is used to change various analytical parameters.
Image transmitter of the present invention is the chnnel coding transmitter, image converter links to each other with the chnnel coding transmitter by source encoder, image dissector is connected with the chnnel coding transmitter by retrieval frame encoder, and geographic orientation and temporal information are sent into retrieval frame encoder (Fig. 2) by the GPS transducer.If the output of imageing sensor is digital signal, then can be without image converter.
Imageing sensor of the present invention, chnnel coding transmitter, image converter, source encoder, image dissector, GPS transducer and retrieval frame encoder can be independent device, also can be integrated in the complete device.
Method of work of the present invention and principle are: image dissector is analyzed the output of each imageing sensor, discern the feature of each institute's monitored object, and with the feature (geographic orientation at information and transducer place of each institute's monitored object, the information such as time that target occurs are together) make coding formation image retrieval frame by retrieval frame encoder, the image retrieval frame of all monitored object that form in the image dissector is transferred to the image applications terminal by the chnnel coding transmitter, form image retrieval frame data storehouse in the image applications terminal, if certain user need inquire about certain specific target at a time between the section whether appear at this surveillance set the zone retrieval the time, only need some features of specific objective are inputed in the image applications terminal, related software in the image applications terminal is retrieved these characteristics of objects by image retrieval frame data storehouse, if satisfy the target signature condition, then utilize regional geography azimuth information and the temporal information that retrieves in the image retrieval frame, access this zone in the image information data storehouse in the image information of this time, can finish retrieval tasks.
Embodiment 1:
At each crossing of cross traffic intersection a video camera is set, the output of four video cameras is transferred to image processor by data wire (data wire is video line or coaxial cable or grid line etc.), image processor earlier converts the output analog signal of No. four video cameras to digital signal (if the output of video camera be digital signal just must image converter) by image converter and is transferred to image dissector and image transmitter respectively, the output image signal of four video cameras that the image transmitter will obtain is transferred to image applications terminal storage (Fig. 1), and forms the image data base at this crossing in the image applications terminal by the time; Image dissector is after the output that receives four video cameras, vehicle and pedestrian by (stop) crossing registers (as pedestrian 1～pedestrian 100 to take the photograph in a certain moment video camera, vehicle 1～vehicle 100), then for each pedestrian and vehicle different angles according to four video cameras, extract each pedestrian's the appearance information and the classification (visitor of vehicle, goods), sign, licence plate, information such as profile and color, and these information are made coding form image retrieval frame data storehouse, at last this image retrieval frame data storehouse is transferred to the image applications terminal storage by the image transmitter.When needs retrieve certain pedestrian or vehicle at a time between in during whether by (stop) this crossing, can by the input earlier of image applications terminal appearance information or licence plate, model and the colouring information of the pedestrian that retrieves or vehicle in image retrieval frame data storehouse, retrieve, if when retrieving the image retrieval frame that satisfies initial conditions, retrieve in the image data base of this time by the temporal information in the image retrieval frame, check the pedestrian that retrieves or vehicle at the video image that passes through (stop) time period at this crossing, and finish retrieval tasks.
Embodiment 2:
(going out) mouth that advances in residential quarters is provided with a cover video camera, forms the image data base of being somebody's turn to do (go out) mouth by the time with embodiment 1 identical method in the image applications terminal; Extract each the appearance information of advancing (going out) residential quarters personnel and the licence plate of vehicle with embodiment 1 the same image dissector, model and colouring information, the appearance information of each personnel of software analysis by image dissector and the licence plate of vehicle, model and colouring information, if registered personnel and vehicle in the residential quarters, just do not make the image retrieval frame, registered personnel and vehicle in the residential quarters, just with the appearance information of these personnel and vehicle and the licence plate of vehicle, model and colouring information are made coding and are formed image retrieval frame data storehouse, at last this image retrieval frame data storehouse are transferred to the image applications terminal storage by the image transmitter.When needs retrieve the personnel of certain non-sub-district registration or vehicle at a time between in when whether entering this sub-district when having the personnel of which non-sub-district registration or vehicle to enter the sub-district at a time (or), can import the appearance information or the licence plate of retrieval personnel of institute or vehicle by the image applications terminal earlier, model and colouring information are retrieved in image retrieval frame data storehouse, if when retrieving the image retrieval frame that satisfies initial conditions, know these personnel or the vehicle time in the sub-district by the temporal information in the image retrieval frame, by time period and the image retrieval frame information of knowing, in the sub-district, retrieve in the image data base of all video cameras, check the pedestrian that retrieves or vehicle at the video image of this sub-district time period, and finish retrieval tasks.
In addition, the information that the present invention provides according to the image retrieval frame can be judged direction of motion, speed of target etc. rapidly.
As a same reason, the present invention can be used for finance equally, and ShangWu Building waits other that place of surveillance need be set in the office.
The content that is not described in detail in this specification belongs to this area professional and technical personnel's known prior art.
Claims (10)
1, a kind of based target retrieval and the image monitoring system of discerning, comprise at least one imageing sensor and an image applications terminal, wherein the output of each imageing sensor is connected with the image applications terminal, in the image applications terminal, generate an image data base, it is characterized in that: between imageing sensor and image applications terminal, also be provided with image processor, the input of image processor links to each other with the output of each imageing sensor, and the output of image processor is connected with the image applications terminal.
2, based target retrieval as claimed in claim 1 and the image monitoring system of discerning, it is characterized in that: image processor comprises image dissector and image transmitter, the output of each imageing sensor links to each other with the image dissector input, the output of each imageing sensor is also joined with image transmitter input, the output of image dissector is also joined with image transmitter input, and the output of image transmitter is connected with the image applications terminal.
3, based target retrieval as claimed in claim 1 or 2 and the image monitoring system of discerning, it is characterized in that: the output of each imageing sensor is connected with the image transmitter with image dissector respectively by an image converter in the image processor.
4, as claim 1 or 2 or 3 described based target retrievals and the image monitoring system of discerning, it is characterized in that: the image transmitter is the chnnel coding transmitter, image converter links to each other with the chnnel coding transmitter by source encoder, and image dissector is connected with the chnnel coding transmitter by retrieval frame encoder.
5, based target retrieval as claimed in claim 2 and the image monitoring system of discerning, it is characterized in that: image dissector is analyzed the output of a certain each imageing sensor of the moment, discern each clarification of objective, and each clarification of objective is made coding form the image retrieval frame, the image retrieval frame of all targets that form in the image dissector is transferred to the image applications terminal by the image transmitter, forms image retrieval frame data storehouse in the image applications terminal.
6, based target retrieval as claimed in claim 5 and the image monitoring system of discerning, it is characterized in that: in the image retrieval frame, its coding comprises the geographic orientation and the temporal information of monitor area.
7, based target retrieval as claimed in claim 5 and the image monitoring system of discerning, it is characterized in that: in the image retrieval frame, if institute's monitored object is the people, its coding comprises people's macroscopic features; If institute's monitored object is a thing, its coded message comprises geometry or the physical dimension or the sign sign of object.
8, the image monitoring system of based target as claimed in claim 5 retrieval and identification is characterized in that: the image applications terminal is by long-range setting, for the image dissector database that supplies a model, is used to change various analytical parameters.
9, based target retrieval as claimed in claim 8 and the image monitoring system of discerning, it is characterized in that: image dissector obtains the geographic orientation and the temporal information at respective image scene by the GPS transducer.
10, as claim 1 or 4 or 9 described based target retrievals and the image monitoring system of discerning, it is characterized in that: imageing sensor, image converter, source encoder, GPS transducer, image dissector, retrieval frame encoder and chnnel coding transmitter are integrated in the complete device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007101687482A CN101459828A (en) | 2007-12-10 | 2007-12-10 | Image monitoring system based on target retrieval and recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007101687482A CN101459828A (en) | 2007-12-10 | 2007-12-10 | Image monitoring system based on target retrieval and recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101459828A true CN101459828A (en) | 2009-06-17 |
Family
ID=40770413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2007101687482A Pending CN101459828A (en) | 2007-12-10 | 2007-12-10 | Image monitoring system based on target retrieval and recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101459828A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999954A (en) * | 2011-10-01 | 2013-03-27 | 无锡市世一电力机械厂 | Vehicle monitoring system and method |
| CN103155550A (en) * | 2010-10-11 | 2013-06-12 | Lg电子株式会社 | Image-monitoring device and method for searching for objects therefor |
| CN103841367A (en) * | 2012-11-21 | 2014-06-04 | 深圳市赛格导航科技股份有限公司 | Monitoring system |
| CN111898416A (en) * | 2020-06-17 | 2020-11-06 | 绍兴埃瓦科技有限公司 | Video stream processing method and device, computer equipment and storage medium |
-
2007
- 2007-12-10 CN CNA2007101687482A patent/CN101459828A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103155550A (en) * | 2010-10-11 | 2013-06-12 | Lg电子株式会社 | Image-monitoring device and method for searching for objects therefor |
| CN103155550B (en) * | 2010-10-11 | 2016-10-26 | Lg电子株式会社 | Image monitoring arrangement and the method for the object search for it |
| CN102999954A (en) * | 2011-10-01 | 2013-03-27 | 无锡市世一电力机械厂 | Vehicle monitoring system and method |
| CN103841367A (en) * | 2012-11-21 | 2014-06-04 | 深圳市赛格导航科技股份有限公司 | Monitoring system |
| CN111898416A (en) * | 2020-06-17 | 2020-11-06 | 绍兴埃瓦科技有限公司 | Video stream processing method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180357247A1 (en) | Behavior-aware security systems and associated methods | |
| US20180025636A1 (en) | Systems, apparatuses and methods for detecting driving behavior and triggering actions based on detected driving behavior | |
| US20200073969A1 (en) | Systems and methods for querying a distributed inventory of visual data | |
| CN105306796A (en) | Night vision equipment with regular infrared illumination function and global shutter CMOS (Complementary Metal Oxide Semiconductor) sensor | |
| CA3075859A1 (en) | System and method for gate monitoring during departure or arrival of an autonomous vehicle | |
| US20190333378A1 (en) | Distributed safety infrastructure for autonomous vehicles and methods of use | |
| WO1999005867A9 (en) | Abnormality detection and surveillance system | |
| ATE491309T1 (en) | AUTOMATED SITE SECURITY, MONITORING AND ACCESS CONTROL SYSTEM | |
| CN110522617A (en) | Blind person's wisdom glasses | |
| CN102306234A (en) | Meteorological popular science robot system | |
| CN101459828A (en) | Image monitoring system based on target retrieval and recognition | |
| CN107409198B (en) | Camera image data-based situation confirmation system, control device, and camera image data-based situation confirmation method | |
| KR20190043396A (en) | Method and system for generating and providing road weather information by using image data of roads | |
| CN112907867A (en) | Early warning method and device based on image recognition and server | |
| CN111192476A (en) | Public safety protection system of wisdom city | |
| CN109977908B (en) | Vehicle driving lane detection method based on deep learning | |
| CN203165221U (en) | Public security checkpoint type parking lot vehicle information acquiring and reporting system | |
| CN206162876U (en) | Road speed limit prison bat system based on visibility detection | |
| KR20210066296A (en) | Apparatus and method for monitoring city condition | |
| CN201181982Y (en) | Image monitoring device based on objective searching and recognition | |
| CN202134012U (en) | Meteorological popular science robot system | |
| CN111914050B (en) | Visual 3D monitoring platform based on specific places | |
| CN117392852A (en) | Cloud computing resource scheduling optimization system oriented to big data analysis | |
| CN115083208B (en) | Human-vehicle conflict early warning method, early warning analysis method, electronic device and storage medium | |
| CN113538967B (en) | Vehicle-road cooperation device and method under crossroad scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20090617 |