CN205378015U - Detecting device with two cameras - Google Patents
Detecting device with two cameras Download PDFInfo
- Publication number
- CN205378015U CN205378015U CN201520726432.0U CN201520726432U CN205378015U CN 205378015 U CN205378015 U CN 205378015U CN 201520726432 U CN201520726432 U CN 201520726432U CN 205378015 U CN205378015 U CN 205378015U
- Authority
- CN
- China
- Prior art keywords
- camera lens
- camera
- shell
- circuit board
- color 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.)
- Active
Links
Landscapes
- Studio Devices (AREA)
Abstract
The utility model discloses a detecting device with two cameras, including shell, upper cover, sheet metal component, circuit board, camera lens, tail wire, the shell includes protecgulum, mid portion and back lid, the camera lens is installed on the sheet metal component, tail wire passes back lid with the circuit board is connected, the camera lens includes first camera lens and second camera lens, first camera lens is installed at the B/W camera front end, a light filter is installed through light filter switching ring to first camera lens front end, the front end at color video camera is installed to the second camera lens, first camera lens and second camera lens all with the circuit board is connected. The utility model discloses, gathering video image through two cameras, can clearly learning the information of monitoring, solved prior art, gather through single camera that video image is unable to be satisfied, the definition of video analysis needs, has brought the problem of very big restriction to the application of detector.
Description
Technical field
This utility model belongs to intelligent video analysis monitoring field, particularly relates to a kind of detection device with dual camera.
Background technology
Along with developing rapidly of economic technology, detector is widely used in all trades and professions, but, detector of the prior art is single camera, it gathers video image and cannot meet, and the definition of video analysis needs, and the application of detector is brought great restriction.
It addition, along with traffic transport industry is day by day flourishing, this makes traffic problems increasingly serious, frequent accidents occurs, and causes the deepest concern of the country and people.Especially on tunnel, highway, vehicle flowrate is big, speed is very fast, sometimes has the object vehicle that drops from vehicle or break down and cannot process movement in time, in turn results in traffic accident.Shed formal matter part and have become as a traffic events taken place frequently, only once the vehicle of accident impact is not many, also can cause second accident, the security of the lives and property of serious harm people, causing unpredictable loss sometimes, the vehicle accident thus caused and the potential safety hazard caused have become as problem in urgent need to solve.Therefore, shedding thing and reporting to the police on tunnel, highway how to be detected rapidly and accurately, find potential safety hazard as early as possible and get rid of in time, keep the safe and smooth of tunnel, highway etc. to become the problem that traffic safety-security area is important.
In consideration of it, this utility model provides a kind of detection device with dual camera.
Utility model content
The purpose of this utility model is in that a kind of detection device with dual camera, with solve in prior art exist detector for single camera, it gathers video image and cannot meet, and the definition of video analysis needs, and the application of detector is brought the problem limited greatly.
For realizing the purpose of this utility model, this utility model provides a kind of detection device with dual camera, including shell, upper cover, sheet metal component, circuit board, camera lens, buttock line, wherein, one end of described upper cover and described housing hinge, described circuit board is fixedly mounted on sheet metal component, described sheet metal component is fixedly mounted in described shell, described shell includes protecgulum, mid portion and bonnet, described camera lens is arranged on described sheet metal component, described buttock line is connected through described bonnet with described circuit board, described camera lens includes the first camera lens and the second camera lens, described first camera lens is arranged on B/W camera front end, described first camera lens front end is provided with an optical filter by optical filter adapter ring, described second camera lens is arranged on color video camera front end, described first camera lens and the second camera lens are all connected with described circuit board.
Wherein, described circuit board being provided with cpu chip, the cooling mechanism of described cpu chip is fin.
Wherein, the inner side of described upper cover is pasted with sealing EVA foam, described shell and the described upper cover place of being tightly connected are provided with sealing rubber strip, conductive fabric is uniformly pasted on described sealing EVA foam surface, and it is seamless between the two after pasting, described sealing rubber strip surface is pasted with conductive fabric completely, and after stickup, conductive fabric surface smoothing is seamless between the two.
Wherein, described color video camera is encapsulated in shell, the cylindrical, hollow encapsulating shell that shell is made up of Stainless steel 316 L, shell protecgulum is provided with clear glass, color video camera is arranged close to the side of front end clear glass, and color video camera can pass through front glass and be acquired surrounding situation map picture simultaneously；Shell bonnet has two wiring holes, and a hole is used for connecting power line, powers to color video camera, and another one hole is used for connecting fiber optic cables, for the video signal of color video camera collection is transferred to hundred meters or the outer Control Room of km.
This utility model, gathers video image by dual camera, it is possible to clearly know the information of monitoring, solve in prior art, cannot being met by single camera collection video image, the definition of video analysis needs, and the application of detector is brought the problem limited greatly.
Accompanying drawing explanation
Accompanying drawing is used for providing being further appreciated by of the present utility model, and constitutes a part for description, is used for explaining this utility model, is not intended that restriction of the present utility model together with example of the present utility model.
Fig. 1 is this utility model device schematic diagram；
Fig. 2 is this utility model link block schematic diagram；
Fig. 3 is that this utility model sheds analyte detection cell operation flow chart；
Fig. 4 is that this utility model sheds thing alarm condition explanation figure.
Detailed description of the invention
Below in conjunction with instantiation, each detailed problem involved by technical solutions of the utility model is described.It is to be noted that described example is intended merely to facilitate understanding of the present utility model, does not therefore limit protection domain of the present utility model.
Embodiment 1
nullAs shown in Figure 1，This utility model provides a kind of detection device with dual camera，Including shell 10、Upper cover 15、Sheet metal component 17、Circuit board 16、Camera lens、Buttock line 18，Wherein，One end of described upper cover 15 is hinged with described shell 10，Described circuit board 16 is fixedly mounted on sheet metal component 17，Described sheet metal component 17 is fixedly mounted in described shell 10，Described shell 10 includes protecgulum、Mid portion and bonnet，Described camera lens is arranged on described sheet metal component，Described buttock line is connected through described bonnet with described circuit board，Described camera lens includes the first camera lens 13 and the second camera lens 14，Described first camera lens 13 is arranged on B/W camera front end，Described first camera lens front end is provided with an optical filter by optical filter adapter ring，Described second camera lens 14 is arranged on color video camera front end，Described first camera lens 13 and the second camera lens 14 are all connected with described circuit board.First light compensating lamp 11, the second light compensating lamp 12.
Wherein, described circuit board being provided with cpu chip, the cooling mechanism of described cpu chip is fin.
Wherein, the inner side of described upper cover is pasted with sealing EVA foam, described shell and the described upper cover place of being tightly connected are provided with sealing rubber strip, conductive fabric is uniformly pasted on described sealing EVA foam surface, and it is seamless between the two after pasting, described sealing rubber strip surface is pasted with conductive fabric completely, and after stickup, conductive fabric surface smoothing is seamless between the two.
Embodiment 2
As shown in Figure 2,3, 4, this utility model embodiment additionally provides and sheds that analyte detection unit 9 mainly includes color video camera 2, protection device 1, infrared illumination lamp 6 and DSP process chip 4.Wherein, what color video camera 2 collected is color video frequency image, and color video camera 2 processes chip 4 by netting twine with DSP and is connected transmission data.Image transmitting is processed chip 4, DSP to DSP and processes chip 4 mainly algorithm unit by color video camera 2, it is provided that sheds thing Intelligent Measurement scheme, color video camera 2 and DSP process chip 4 and is encapsulated in shell 3.The cylindrical, hollow encapsulating shell that shell 3 is made up of Stainless steel 316 L; shell 3 interior forward end is provided with clear glass; clear glass is used for protecting color video camera 2 and DSP to process chip 4; color video camera 2 is arranged close to the side of front end clear glass; DSP processes chip 4 and is mounted remotely from the side of front end clear glass, and color video camera 2 can pass through front glass and be acquired surrounding situation map picture simultaneously.Shell 3 rear end has two wiring holes, one hole is used for connecting power line, process chip 4 to color video camera 2 and DSP to power, another one hole is used for connecting fiber optic cables, processes the alarm signal obtained be transferred to the Control Room outside hundred meters or km for the video signal gathered by color video camera 2 and DSP process chip 4.Protection device 1 is rain shade, for curved thin plate shape, is arranged on the shell 3 of Intelligent Measurement module, it is possible to rain cover, the extension fixture time limit in service life.Infrared illumination lamp 6 provides night illumination, and detection range is 150 meters, it is ensured that when without background light source, and color video camera 2 can be normally carried out image acquisition work.Infrared illumination lamp 6 is encapsulated in cylindrical stainless steel protection shell 5, sheds the underface of the shell 3 of analyte detection unit 9, and two shells 5,3 are rigidly connected, and stainless steel protection shell 5 afterbody perforate connects power line and powers to infrared lamp.
Described display module is display screen 7, is arranged in Control Room, receives the next video information of color video camera 2 transmission and shows in real time.What reception DSP process chip 4 process simultaneously obtained sheds thing information and shows.
Described alarm module is alarm 8, for receive DSP process chip 4 process obtain shed thing alarm signal, prompting monitoring personnel process the thing of shedding on tunnel, highway in time.
Above-mentioned analyte detection cell operation step of shedding is:
1. the color image information that color video camera 2 gathers, it is delivered simultaneously to display module 7 and DSP processes chip 4, display module 7 shows tunnel, highway live state information in real time, and DSP processes chip 4 and receives the further Intelligent Recognition process of color video frequency image information that color video camera transmission comes.
2.DSP processes that the color video frequency image information received is carried out background modeling by chip 4, foreground detection, the setting of protection zone, prospect coupling update, shed thing and judge handling process, obtains shedding thing information.
3.DSP processes chip 4 and result is transferred to alarm module 8, will shed thing information simultaneously and be transferred to display module 7, it is shown that shedding thing information, prompting monitoring personnel be for further processing.
It is illustrated in figure 3 this and sheds thing Intelligent Measurement flow chart, mainly include background modeling, foreground detection, the setting of protection zone, prospect coupling renewal, shed thing judgement.
Described background modeling mainly carries out pattern recognition, Intelligent Establishment adaptive learning background model according to the color video frequency image of color video camera 2 input.The lightness of video image, chrominance information is utilized to set up background model.Owing to algorithm carries out performing computing in embedded device, the data message that algorithm adopts is all integer parameter.Pixel in traversing graph picture successively, finds its eight neighborhood pixel to each pixel, sets up Gauss model according to seed points and eight neighborhood information, and Gauss model parameter has lightness, colourity, saturation, weight, covariance information.Each seed points is set up Gauss model.
The lightness of model, colourity are obtained by seed points and its eight neighborhood relevant information.Such as matrix Shown in position, middle 1 is seed points Pixel Information, and eight neighborhood is indicated with 0.To eight neighborhood pixel information according to from left to right, order from top to bottom is labeled as P successively1, P2, P3, P4, P5, P6, P7, P8, seed points is denoted as P0.According to weight parameter, seed points is set up Gauss model,
Y0=0.5*YP0+0.043*YP1+0.0555YP2+0.043YP3+0.0945YP4+
0.0945YP5+0.057YP6+0.0555YP7+0.057YP8
Wherein, Y0For setting up the lightness after Gauss model, YP0、YP1、YP2、YP3、YP4、YP5、YP6、YP7、YP8The respectively lightness of seed points and its eight neighborhood.
In like manner, same method sets up the Gauss model of seed points colourity and saturation,
U0=0.5*UP0+0.043*UP1+0.0555UP2+0.043UP3+0.0945UP4+
0.0945UP5+0.057UP6+0.0555UP7+0.057UP8
Wherein, U0For setting up the colourity after Gauss model, UP0、UP1、UP2、UP3、UP4、UP5、UP6、UP7、UP8The respectively colourity of seed points and its eight neighborhood.
V0=0.5*VP0+0.043*VP1+0.0555VP2+0.043VP3+0.0945VP4+
0.0945VP5+0.057VP6+0.0555VP7+0.057VP8
Wherein, V0For setting up the saturation after Gauss model, VP0、VP1、VP2、VP3、VP4、VP5、VP6、VP7、VP8The respectively saturation of seed points and its eight neighborhood.
Model variance learning process is:
Δi+1=Δi*(1-β)+β*|Yi+1-Yi|++β*|Ui+1-Ui|++β*|Vi+1-Vi|
Wherein, Δi+1Represent a new two field picture variance learning outcome, ΔiRepresenting the variance of current background, β represents model variance Studying factors, Yi、Ui、ViRepresent the lightness of Gauss model at background image seed points place, colourity, saturation infromation respectively.Yi+1、Ui+1、Vi+1Represent current frame image and the lightness of Gauss model at seed points place, background image corresponding position, colourity, saturation infromation respectively.
Model Weight record is that background seed points models successfully number.When background seed points modeling sum reaches the 1/3 of whole seed points quantity, background modeling success.
Described foreground detection is detection emerging people or thing in the background.The foreground detection method that this utility model adopts is prospect method compared with the Gauss model of background.In like manner set up the Gauss model parameter lightness of current frame image pixel seed points, colourity, saturation, weight, covariance information.Respectively corresponding with the Gauss model of background for prospect lightness, colourity, saturation, that variance parameter carries out respectively is poor.If difference is less than certain threshold value, then seed points is doubtful foreground point.It it is otherwise background dot.After all seed points in foreground point have been contrasted, seed points is carried out UNICOM's expansion process, so, each seed points of same foreground object is by UNICOM, calculate the size in each UNICOM region, girth, area, center of gravity, depth-width ratio information, exclude the impact of too small false prospect noise spot, then respectively the mask of different prospects is labeled as different sequence numbers.Effective foreground data in the first two field picture after Background learning is stored in prospect history information library, in order to the prospect coupling in subsequent detection process updates and sheds the operations such as thing judgement.
Described protection zone be set as on tunnel or highway, vehicle travel region.By drawing two lines to indicate protection zone information along tunnel or highway edge in the picture.And concurrently set shed thing warning sensitivity, shed object plane long-pending monitoring restriction, depth-width ratio restriction, it is prevented that the impact of too small stone, pit etc..
The foreground information that described prospect coupling renewal process generally refers to newly detecting removes renewal prospect history information library.By detecting the emerging foreground information of current frame image, according to prospect size, girth, area, center of gravity, depth-width ratio information, prospect historical data is compared, if change is less than threshold value, then think and belong to same foreground information, and update prospect historical data, if not finding the historical information of coupling, then it is emerging prospect, relevant new prospect is saved in historical data.
Described formal matter part of shedding judges mainly to judge that whether prospect is for shedding thing and whether shedding thing whether protection zone and warning sensitivity meet requirement.Judge process is traversal prospect history information library, it is judged that whether the area of prospect, depth-width ratio information meet threshold value sets, if it is satisfied, then for shedding thing.Judge whether in the protection zone set according further to prospect center of gravity information, if in protection zone, it is judged that whether warning sensitivity meets requirement; if meeting warning sensitivity; then for shedding thing, it is simultaneously emitted by warning message, and marks out by foreground information and be shown on screen.
It is illustrated in figure 4 this and sheds thing Intelligent Measurement alarm condition figure.As shown in Figure 4, oblique line information in the left and right sides is highway or direction, tunnel marginal information.Monitor area position distance scope for limiting up and down, constitutes closed area A.Closed area A is protection zone, only when thing information is shed in closed area, just can report to the police.As shed thing 11 in the A of protection zone, detection process can be reported to the police；Shed thing 10 in the B of non-protected area, detection process will not be reported to the police.
Any those skilled in the art are changed or are modified as the Equivalent embodiments of equivalent variations possibly also with the technology contents of the disclosure above.But every without departing from technical solutions of the utility model content, any simple modification, equivalent variations and remodeling above example made according to technical spirit of the present utility model, still fall within the protection domain of technical solutions of the utility model.
Claims (4)
1. the detection device with dual camera, it is characterized in that, including shell, upper cover, sheet metal component, circuit board, camera lens, buttock line, wherein, one end of described upper cover and described housing hinge, described circuit board is fixedly mounted on sheet metal component, described sheet metal component is fixedly mounted in described shell, described shell includes protecgulum, mid portion and bonnet, described camera lens is arranged on described sheet metal component, described buttock line is connected through described bonnet with described circuit board, described camera lens includes the first camera lens and the second camera lens, described first camera lens is arranged on B/W camera front end, described first camera lens front end is provided with an optical filter by optical filter adapter ring, described second camera lens is arranged on color video camera front end, described first camera lens and the second camera lens are all connected with described circuit board.
2. a kind of detection device with dual camera according to claim 1, it is characterised in that being provided with cpu chip on described circuit board, the cooling mechanism of described cpu chip is fin.
3. a kind of detection device with dual camera according to claim 1, it is characterized in that, the inner side of described upper cover is pasted with sealing EVA foam, described shell and the described upper cover place of being tightly connected are provided with sealing rubber strip, conductive fabric is uniformly pasted on described sealing EVA foam surface, and seamless between the two after pasting, described sealing rubber strip surface is pasted with conductive fabric completely, and after stickup, conductive fabric surface smoothing is seamless between the two.
4. a kind of detection device with dual camera according to claim 1, it is characterized in that, described color video camera is encapsulated in shell, the cylindrical, hollow encapsulating shell that shell is made up of Stainless steel 316 L, shell protecgulum is provided with clear glass, color video camera is arranged close to the side of front end clear glass, and color video camera can pass through front glass and be acquired surrounding situation map picture simultaneously；Shell bonnet has two wiring holes, and a hole is used for connecting power line, powers to color video camera, and another one hole is used for connecting fiber optic cables, for the video signal of color video camera collection is transferred to hundred meters or the outer Control Room of km.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201520726432.0U CN205378015U (en) | 2015-09-18 | 2015-09-18 | Detecting device with two cameras |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201520726432.0U CN205378015U (en) | 2015-09-18 | 2015-09-18 | Detecting device with two cameras |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205378015U true CN205378015U (en) | 2016-07-06 |
Family
ID=56261195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201520726432.0U Active CN205378015U (en) | 2015-09-18 | 2015-09-18 | Detecting device with two cameras |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205378015U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105245831A (en) * | 2014-11-26 | 2016-01-13 | 天津艾思科尔科技有限公司 | Detector based on binocular vision |
| CN110035214A (en) * | 2019-06-03 | 2019-07-19 | 黄山中鼎信息技术有限公司 | A kind of camera housing |
| CN114302033A (en) * | 2021-12-01 | 2022-04-08 | 杭州海康威视数字技术股份有限公司 | Photographing apparatus |
-
2015
- 2015-09-18 CN CN201520726432.0U patent/CN205378015U/en active Active
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105245831A (en) * | 2014-11-26 | 2016-01-13 | 天津艾思科尔科技有限公司 | Detector based on binocular vision |
| CN105245831B (en) * | 2014-11-26 | 2019-10-08 | 天津艾思科尔科技有限公司 | Shed object intelligent detection device |
| CN110035214A (en) * | 2019-06-03 | 2019-07-19 | 黄山中鼎信息技术有限公司 | A kind of camera housing |
| CN110035214B (en) * | 2019-06-03 | 2023-09-19 | 黄山中鼎信息技术有限公司 | Camera shell |
| CN114302033A (en) * | 2021-12-01 | 2022-04-08 | 杭州海康威视数字技术股份有限公司 | Photographing apparatus |
| CN114302033B (en) * | 2021-12-01 | 2023-09-29 | 杭州海康威视数字技术股份有限公司 | Photographing apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105245831A (en) | Detector based on binocular vision | |
| CN108922188B (en) | Radar tracking and positioning four-dimensional live-action traffic road condition perception early warning monitoring management system | |
| US8614744B2 (en) | Area monitoring using prototypical tracks | |
| CN111753612B (en) | Method and device for detecting casting object and storage medium | |
| CN103400111B (en) | Method for detecting fire accident on expressway or in tunnel based on video detection technology | |
| CN105512623A (en) | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors | |
| CN204990743U (en) | Superelevation vehicle early warning system | |
| CN106504580A (en) | A kind of method for detecting parking stalls and device | |
| CN205378015U (en) | Detecting device with two cameras | |
| CN113850123A (en) | Video-based road monitoring method and device, storage medium and monitoring system | |
| CN112784821A (en) | Building site behavior safety detection and identification method and system based on YOLOv5 | |
| CN103546723A (en) | Monitoring system and monitoring method | |
| CN103729858A (en) | Method for detecting article left over in video monitoring system | |
| CN117809275B (en) | Environment sensing method and system based on 360-degree circular system of civil aviation vehicle | |
| CN111931726B (en) | Traffic light detection method, device, computer storage medium and road side equipment | |
| CN105575121A (en) | Intelligent traffic-based source technology overload control and prevention data acquisition system and method | |
| CN111862129B (en) | Virtual fence system for sealing sample storage | |
| CN111144301A (en) | Road pavement defect quick early warning device based on degree of depth learning | |
| CN110691224A (en) | Transformer substation perimeter video intelligent detection system | |
| CN114875877A (en) | Ship lockage safety detection method | |
| CN102479416B (en) | Method and device for eliminating false alarm in monitoring system | |
| CN116475089A (en) | Coordinated control device and method for intelligent video image recognition of mine belt conveyor | |
| CN116846059A (en) | Edge detection system for power grid inspection and monitoring | |
| CN112668478B (en) | Well lid monitoring method and device, electronic equipment and storage medium | |
| CN205378086U (en) | Space saving type detecting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |