CN206452471U - Visual identifying system - Google Patents
Visual identifying system Download PDFInfo
- Publication number
- CN206452471U CN206452471U CN201621295203.9U CN201621295203U CN206452471U CN 206452471 U CN206452471 U CN 206452471U CN 201621295203 U CN201621295203 U CN 201621295203U CN 206452471 U CN206452471 U CN 206452471U
- Authority
- CN
- China
- Prior art keywords
- detected
- camera
- identifying system
- utility
- visual identifying
- 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
- Image Analysis (AREA)
Abstract
The utility model discloses a kind of visual identifying system, belong to Visual identification technology field, solve existing Visual identification technology and there is limitation, there is the technical problem that can not effectively recognize object to be detected.The visual identifying system, including camera and vision storehouse;The camera shoots object to be detected, and will include the image transmitting of object to be detected to the vision storehouse;The vision storehouse recognizes object to be detected by contrast from described image.
Description
Technical field
The utility model is related to Visual identification technology field, specifically, is related to a kind of visual identifying system.
Background technology
With continuing to develop for intelligent identification technology, moving-vision identifying system is more and more applied various
In scene.
In existing Visual identification technology, it is inactive state to have one in detected object and detection object, most of
In the case of be detected object be inactive state.Or, detected object and detection object are all in inactive state.Also,
In existing Visual identification technology, the test point of object to be detected is generally large, it is easy to recognize.
But, for the less situation of test point of object to be detected, or object to be detected is in mobile or change
During state, existing Visual identification technology is difficult to the effective identification of object to be detected.Therefore, existing Visual identification technology is present
, there is the technical problem that can not effectively recognize object to be detected in limitation.
Utility model content
The purpose of this utility model is to provide a kind of visual identifying system exist to solve existing Visual identification technology
, there is the technical problem that can not effectively recognize object to be detected in limitation.
The utility model provides a kind of visual identifying system, including camera and vision storehouse;
The camera shoots object to be detected, and will include the image transmitting of object to be detected to the vision storehouse;
The vision storehouse recognizes object to be detected by contrast from described image.
It is preferred that, the camera is high-definition camera.
It is preferred that, the camera is removable camera.
Further, the camera is installed in mobile robot.
It is preferred that, described vision storehouse is OpenCV.
In a preferred embodiment, the object to be detected is the indicator lamp in rack.
Further, the visual identifying system also includes material database, the figure for the object to be detected that is stored with the material database
Piece;
The vision storehouse is contrasted described image with the picture in the material database, is recognized from described image tested
Survey object.
The utility model brings following beneficial effect:The utility model provide visual identifying system include camera and
Vision storehouse.Wherein, camera shoots object to be detected first, and will include the image transmitting of object to be detected to vision storehouse.
Then, the picture that camera is photographed is contrasted by vision storehouse, and recognizes from image object to be detected.The utility model
In the visual identifying system of offer, the image that camera is photographed is contrasted using vision storehouse, for object to be detected compared with
Small situation, and object to be detected are in dynamic situation, also can effectively recognize, therefore overcome existing visual identity
The limitation of system, the technical problem of object to be detected can not effectively be recognized by solving existing visual identifying system.
Other features and advantages of the utility model will illustrate in the following description, also, partial from specification
In become apparent, or understood by implementing the utility model.The purpose of this utility model and other advantages can pass through
Specifically noted structure is realized and obtained in specification, claims and accompanying drawing.
Brief description of the drawings
, below will be to needed for embodiment description for the technical scheme in clearer explanation the utility model embodiment
The accompanying drawing wanted does simple introduction:
Fig. 1 is the schematic diagram for the visual identifying system that the utility model embodiment is provided.
Embodiment
Embodiment of the present utility model is described in detail below with reference to drawings and Examples, whereby to the utility model
How application technology means solve technical problem, and reach the implementation process of technique effect and can fully understand and implement according to this.
As long as it should be noted that not constituting each feature in each embodiment and each embodiment in conflict, the utility model
It can be combined with each other, the technical scheme formed is within protection domain of the present utility model.
As shown in figure 1, the utility model embodiment provides a kind of visual identifying system, including camera 1 and vision
Storehouse 2.Wherein, camera 1 is used to shoot object to be detected, and will include the image transmitting of object to be detected to vision storehouse, depending on
Feel that storehouse 2, by contrast, recognizes object to be detected from image.
As a preferred scheme, the camera 1 in the present embodiment is high-definition camera.Due to indicator lamp volume compared with
It is small, so to determine the state of indicator lamp, it is necessary to which high-definition camera shoots monitored picture, it is ensured that software is identified by OpenCV
The state of indicator lamp.
High definition has clear and definite regulation in DTV, although having been formed in camera field without clear stipulaties
The professional etiquette of acquiescence.High-definition camera refers to HD 1080P or HD 960P or HD 720P camera, and lens member
Five layers of glass lens must be used, because full glass lens add the lens articulation of glass well many than plastics.
It is further that the camera 1 in the utility model plastics is removable camera, such as can be by camera 1
It is installed in mobile robot, in order to the collection of image.
In the present embodiment, vision storehouse 2 is OpenCV.OpenCV full name is Open Source Computer Vision
Library, be one based on BSD permit (increasing income) distribution cross-platform computer vision library, may operate in Linux,
In Windows and Mac OS operating systems, with lightweight and also it is efficient the characteristics of.
In the present embodiment, OpenCV is write with C Plus Plus, and its primary interface is also C Plus Plus, but is still remained
Substantial amounts of C language interface.Also there is connecing for substantial amounts of Python, Java, MATLAB/OCTAVE (version 2 .5) in OpenCV simultaneously
Mouthful, the support for C#, Ch, Ruby can be also provided, the api interface function of these language can be obtained by online document.
Also include material database 3 in the visual identifying system that the utility model embodiment is provided, be stored with material database 3 tested
Survey the picture of object.Vision storehouse 2 is contrasted image with the picture in material database 3, and object to be detected is recognized from image.
The present embodiment is illustrated using the indicator lamp in rack as object to be detected, and specific identification process includes as follows
Step:
1) image of detected rack position is shot using the high-definition camera in mobile robot.
2) high-definition camera reaches the ad-hoc location where detected rack.
3) specific indicator lamp in the rack that high-definition camera is shot is detected and recognized by visual identifying system, that is, be detected
Survey object.
4) the instruction modulating signal of identification is compared visual identifying system using OpenCV with the picture in material database, with
The series data for collecting according to the time to be associated.
The visual identifying system provided by the utility model embodiment, carries out the collection of instrumented data, can be to inconvenience
In the artificial place for reading instruction modulating signal, pass through the Data Detection collection system of visual identity, carry out the collection of data, to existing
The instruction modulating signal of field carries out video monitoring and carries out data identification in real time.
Video is split according to shot segmentation technique to obtain multiple camera lens fragments, and these camera lens fragments are carried out
Indicator lamp is recognized, to recognize the camera lens fragment where specific indicator lamp.The technical scheme that the utility model embodiment is provided is combined
Indicator lamp identification technology and shot segmentation technique, can overcome and indicator lamp identification technology is only used only carry out each of video identification
Plant limitation.
The utility model embodiment provide technical scheme, be not using frame as identification object, but using camera lens fragment for knowledge
Other object.Among whole camera lens fragment, as long as specific indicator lamp place can just be recognized by once recognizable indicator lamp occur
Camera lens fragment.Indicator lamp visual identifying system will also ensure that the indicator lamp of detection is not the OFF state of flicker state, in order to
Accomplish to determine the state of indicator lamp by the photo of different angles in this point, the present embodiment.
Dynamic contrast is done by the material in OpenCV and material database, the process of dynamic contrast assumes that A, B, C, D point are deposited
In indicator lamp, tetra- points of A, B, C, D are mainly contrasted in OpenCV.If it find that it is different with OpenCV material database, then can
Database is saved in, user can understand the state of indicator lamp in software, and makes and timely tackling, for example, alarmed
Deng.
Identifying system is selected in the present embodiment, is detected and recognized in the picture that high-definition camera is shot by OpenCV
After data, the data type of the data of identification and corresponding data implication are defined by visual identifying system, with collect by
The series data being associated according to the time.
Because some places are unsuitable for the artificial signal for reading indicator lamp, the utility model embodiment provides one kind
The system of people can be replaced to go to recognize the state of indicator lamp in site environment, some are recognized by this video identification technology not
Person who happens to be on hand for an errand's part work and part study fetching shows the indicator lamp in the place of modulating signal.
Although embodiment disclosed in the utility model is as above, described content is only to facilitate understand this practicality
It is new and use embodiment, be not limited to the utility model.Skill in any the utility model art
Art personnel, on the premise of spirit and scope disclosed in the utility model are not departed from, can implementation formal and details
On make any modification and change, but scope of patent protection of the present utility model, must still be defined with appended claims
Scope be defined.
Claims (4)
1. a kind of visual identifying system, it is characterised in that including camera and vision storehouse;
The camera is removable camera, is installed in mobile robot, and the camera shoots object to be detected, described
Object to be detected is the indicator lamp in rack, and will include the image transmitting of object to be detected to the vision storehouse;
The vision storehouse recognizes object to be detected by contrast from described image.
2. visual identifying system according to claim 1, it is characterised in that the camera is high-definition camera.
3. visual identifying system according to claim 1, it is characterised in that described vision storehouse is OpenCV.
4. deposited in visual identifying system according to claim 1, it is characterised in that also including material database, the material database
Contain the picture of object to be detected;
The vision storehouse is contrasted described image with the picture in the material database, and detected material is recognized from described image
Body.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201621295203.9U CN206452471U (en) | 2016-11-29 | 2016-11-29 | Visual identifying system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201621295203.9U CN206452471U (en) | 2016-11-29 | 2016-11-29 | Visual identifying system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN206452471U true CN206452471U (en) | 2017-08-29 |
Family
ID=59662417
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201621295203.9U Active CN206452471U (en) | 2016-11-29 | 2016-11-29 | Visual identifying system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN206452471U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110239232A (en) * | 2019-04-08 | 2019-09-17 | 上海泰威技术发展股份有限公司 | A kind of intelligent identification Method for the more change in pattern printings of plate |
-
2016
- 2016-11-29 CN CN201621295203.9U patent/CN206452471U/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110239232A (en) * | 2019-04-08 | 2019-09-17 | 上海泰威技术发展股份有限公司 | A kind of intelligent identification Method for the more change in pattern printings of plate |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886130B (en) | Target object determination method and device, storage medium and processor | |
CN106527892B (en) | Screen capturing method and system of electronic equipment | |
WO2021082635A1 (en) | Region of interest detection method and apparatus, readable storage medium and terminal device | |
CN109284737A (en) | A kind of students ' behavior analysis and identifying system for wisdom classroom | |
CN111726586A (en) | Production system operation standard monitoring and reminding system | |
US20130243343A1 (en) | Method and device for people group detection | |
CN110796018B (en) | Hand motion recognition method based on depth image and color image | |
CN108090908B (en) | Image segmentation method, device, terminal and storage medium | |
CN109766779A (en) | It hovers personal identification method and Related product | |
CN110659659A (en) | Method and system for intelligently identifying and early warning pests | |
CN110428449A (en) | Target detection tracking method, device, equipment and storage medium | |
CN109857878B (en) | Article labeling method and device, electronic equipment and storage medium | |
TW202009681A (en) | Sample labeling method and device, and damage category identification method and device | |
US11610388B2 (en) | Method and apparatus for detecting wearing of safety helmet, device and storage medium | |
US20190116310A1 (en) | Method of processing object in image and apparatus for same | |
CN106598356A (en) | Method, device and system for detecting positioning point of input signal of infrared emission source | |
KR102653485B1 (en) | Electronic apparatus for building fire detecting model and method thereof | |
CN206452471U (en) | Visual identifying system | |
KR101360999B1 (en) | Real time data providing method and system based on augmented reality and portable terminal using the same | |
CN113610077A (en) | System method and equipment for monitoring and analyzing dissolution behavior by using artificial intelligence image recognition technology | |
CN109460077B (en) | Automatic tracking method, automatic tracking equipment and automatic tracking system | |
CN103903269B (en) | The description method and system of ball machine monitor video | |
CN114494486B (en) | Method, device and storage medium for generating user type graph | |
CN106339089B (en) | A kind of interactive action identifying system and method | |
WO2019212501A1 (en) | Trained recognition models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |