CN205692214U - A kind of monocular vision pose measurement system - Google Patents
A kind of monocular vision pose measurement system Download PDFInfo
- Publication number
- CN205692214U CN205692214U CN201620447304.7U CN201620447304U CN205692214U CN 205692214 U CN205692214 U CN 205692214U CN 201620447304 U CN201620447304 U CN 201620447304U CN 205692214 U CN205692214 U CN 205692214U
- Authority
- CN
- China
- Prior art keywords
- processing unit
- graphics processing
- pose
- image
- image acquisition
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
This utility model provides a kind of monocular vision pose measurement system, at least include the object carrying cooperative target template, pose image acquisition units, graphics processing unit, power supply and display memory element, described cooperative target template uses four coplanar annulus compositions, and annulus area is not of uniform size；Pose image acquisition units is USB interface-based camera, and pose image acquisition units is connected with graphics processing unit, exports data to graphics processing unit；Described graphics processing unit is provided with USB interface and network interface or serial ports, and described graphics processing unit uses STM320DM8148 hardware platform, has been internally integrated the heterogeneous dual-core processor of ARM and DSP；Data are exported by graphics processing unit by network interface or serial ports, and described power supply is connected with graphics processing unit and powers.This system provides a kind of hardware platform, it is possible to combine with algorithm, thus realize monocular vision pose and accurately measure.
Description
Technical field
This utility model provides a kind of monocular vision pose measurement system, belongs to technical field of vision detection.
Background technology
Vision detection technology is the emerging measurement technology of developed over nearly twenties years, have employed a large amount of automatization, intelligence
Can change technology, by computer identification and control, measurement process only needs little manual intervention just can complete.Along with vision technique
Development ripe so that it obtains a wide range of applications in fields such as industry, medical science, Aero-Space, military affairs.Vision technique
Can substitute for the mankind and carry out size detection, target tracking, robot navigation etc., and repeatability height, non-contact precision are surveyed
Amount, the application that acquisition of information is rapid and site environment is severe are more suitable for.
Great majority are all based on PC end to the research of vision measurement at present, because its volume is big, power consumption is high, are scarcely suitable for machine
Carry, the most how to be applied in vision detection technology gradually receive publicity by embedded technology, and be increasingly becoming the focus of research.
But vision-based detection related algorithm is complicated, and image procossing is computationally intensive, and the real time problems of tracking is the most effectively solved, its
The performance of middle hardware platform and the efficiency of software algorithm are two big influence factors, therefore, still must do substantial amounts of research in this field
Work.
Image acquisition hardware plateform system in vision measurement system mainly includes with lower part: image acquisition units, figure
As processing and analysis unit, data storage cell and control feedback unit etc..Wherein, image acquisition units is computer vision system
The critical component of middle acquisition information, its most essential function is exactly to convert optical signals into into the orderly signal of telecommunication and by certain
Mode be transferred to signal processing platform.And the design of image acquisition units is the most relevant with optical sensor and interface thereof.
Traditional vision measurement system is mostly based on " CCD ten video frequency signal processing chip+CPLD/FPGA+DSP " framework
's.Current this framework relative maturity, but ccd sensor needs a considerable number of outside support circuit, at electric power management circuit
Difficulty in design is higher.Its power consumption and volume are relatively big, and hardware designs is complicated, and development difficulty is bigger.
Cmos sensor has that volume is little, low in energy consumption, high integration, Novel USB interface and infrared interface technology these dash forward
The advantage gone out.The probability of the miscellaneous point of its original appearance is the biggest, it is easy to the product being disturbed impact the most ripe also can be from rear
Compensate on level circuit and optimize so that the photographic head finished product of COMS technology becomes leading market product.
USB interface-based COMS camera need not extra collecting device can obtain real-time uncompressed video data and
Seizure to image.But its transmitting procedure relates to complex communication agreement, if based on traditional " CPLD/FPGA+DSP " framework,
Need to build considerably complicated logic circuit to manage.And arm processor can well play control function in this kind of system,
Have only to use internal USB Host to drive reception photographic head data, it is possible to obtain complete or compressed image or
Person's video.In terms of the storage and process of image, for oneself through the upper this image acquisition and processing platform of operating system, image
The process to data inside file system can be stored in as file.And single arm processor is processing complicated image calculation
During method the most inadequate, it is impossible to the task that competent computational complexity is higher.The programmability of dsp chip and powerful disposal ability,
Make it can be used for rapidly and realize various digital signal processing algorithm, become the optimum selection of current image processing system.Therefore,
It is proposed that use " COMS+ARM+DSP " framework to build vision measurement hardware platform.Leonardo da Vinci's series processors of TI company
It is integrated with the heterogeneous dual-core processor of ARM and DSP so that Leonardo da Vinci's processor has possessed the respective advantage of ARM and DSP, can be very
Meet application demand well.
The most domestic research for monocular vision pose measurement system, mostly also in the theoretical simulation stage, does not the most become
The product of type.Monocular vision pose measuring method is also mostly based on PC end, depends on OpenCV computer vision storehouse.Owing to there being PC
The powerful hardware of machine, as guarantee, need not too much consideration overhead problem during application and development, and OpenCV regards
Feeling that storehouse provides abundant vision processing algorithm, simplify algorithm realizes difficulty.But it is not easy to greatly popularize in view of PC build
Application, along with the development of embedded technology, relevant hardware platform performance promotes further, allows embedded platform for vision figure
It also is able to preferably support as processing related application.And the embedded feature with low-power consumption and low cost itself so that base
Of increased attention in the vision measurement system of embedded technology.Therefore, the monocular studying a kind of high efficient and reliable regards
Feel that pose measurement system is necessary.
Utility model content
This utility model provides a kind of monocular vision pose measurement system based on cooperative target, solves background technology
In deficiency, this system provides a kind of hardware platform, it is possible to combine with algorithm, thus realize monocular vision pose and accurately survey
Amount.
Realizing the technical scheme that this utility model above-mentioned purpose used is:
A kind of monocular vision pose measurement system, at least includes at cooperative target template, pose image acquisition units, image
Reason unit, power supply and display memory element, cooperative target template is mounted on object, and described cooperative target template is four
Coplanar annulus, and the size of four annulus all differs；Described pose image acquisition units is USB interface-based
COMS camera, described COMS camera includes image sensing part, signal read circuit and control circuit, image sensing part,
Signal read circuit and control circuit are integrated on one chip, and pose image acquisition units is connected with graphics processing unit,
Pose view data is exported to graphics processing unit by USB interface；Described graphics processing unit is provided with for receiving
The USB interface of pose view data and for transmitting network interface or the serial ports of data, described graphics processing unit uses TI company
STM320DM8148 hardware platform, it has been internally integrated the heterogeneous dual-core processor of ARM and DSP；Graphics processing unit is with aobvious
Showing that memory element connects, described power supply is connected with graphics processing unit and powers to graphics processing unit.
Described display memory element is that display screen adds SD card, or is PC end.
Compared with prior art, this utility model use " COMS+ARM+DSP " framework build vision measurement hardware put down
Platform.USB interface-based COMS camera need not extra collecting device can obtain real-time uncompressed video data and to figure
The seizure of picture.Leonardo da Vinci's series processors of TI company is integrated with the heterogeneous dual-core processor of ARM and DSP so that at Leonardo da Vinci
Reason device has possessed the respective advantage of ARM and DSP, and ARM, as main control processor, is responsible for peripheral hardware and data acquisition function, and DSP is because of it
Possess efficient operational capability, process for pose resolving.Overcome in tradition Based PC end vision detection technology, for application
The problems such as volume is excessive when special environment, not readily portable, it also avoid based on common embedded platform real-time simultaneously and
The problem that efficiency is bad.There is the feature of low-power consumption and low cost, application demand can be met well.The calculation that native system is combined
Method proposes to use Otsu method to carry out binaryzation on pose measuring method, compares traditional method, and Otsu method is at embedded platform
Operational efficiency is higher.Meanwhile, because the difference of two two field pictures is little, native system can use previous frame to calculate when calculating threshold value
Value, so calculating threshold value and binaryzation can be carried out parallel, and speed can be greatly improved.
Accompanying drawing explanation
The theory diagram of the pose measurement system that Fig. 1 provides for this utility model；
Fig. 2 is algorithm flow chart；
Fig. 3 is Coordinate Conversion figure；
Fig. 4 is data transmission scheme.
Detailed description of the invention
Below in conjunction with the accompanying drawings this utility model is done detailed specific description, but protection domain of the present utility model is not
It is confined to following example.
The pose measurement system that this utility model provides is divided into five parts: cooperative target template, pose image acquisition list
Unit, graphics processing unit, power supply and display and memory element.The structured flowchart of whole system is as shown in Figure 1.
(1) cooperative target template: native system cooperative target template in use is mounted on object, described cooperative target
Mark template uses containing four coplanar annulus marks as cooperative target template, for ease of identifying the corresponding relation of circle, four annulus
Size be all set to difference.
(2) pose image acquisition units: present design uses USB interface-based COMS camera to obtain pose image,
Described COMS camera includes image sensing part, signal read circuit and control circuit, and image sensing part, signal read electricity
Road and control circuit are integrated on one chip, and pose image acquisition units is connected with graphics processing unit, by pose image
Data are by USB interface output to graphics processing unit, and the data of its output are 1280*1024 gray level image.
(3) graphics processing unit: gather pose image information by USB interface, after intelligent image Processing Algorithm processes,
Result and original image are shown by display unit and preserved by memory element.Wherein, Intelligent treatment algorithm part
It is mainly concerned with image binaryzation, feature point extraction and pose and resolves three parts.
(4) power supply: by civil power 220V voltage conversion DC12V voltage and power to DM8148 hardware platform.
(5) display and memory element: be responsible for setting up with graphics processing unit being connected, show in real time and store image procossing list
The raw image data of unit's output and intelligent algorithm result, and camera parameter and store path can be configured.Logical
Cross display measurement system precision and reliability.Described display memory element is that display screen adds SD card, or is PC end, it is also possible to
For other devices.
One whole for Leonardo da Vinci's family chip ARM+DSP architecture feature that the exploitation of system provides based on TI company
Set component software and framework standard.Carry out under this framework Leonardo da Vinci's application and development be capable of ARM and DSP real-time Communication for Power and
Co-ordination.The development difficulty of application can be simplified, shorten the construction cycle, ensure that the portability of application simultaneously.Data pass
Defeated detailed process is as shown in Figure 4.
USB interface camera: gather image, exports view data.Photographic head is internal own through completing in image capturing system
The collection of image, conversion, output function, finally by USB Slave parts disposal data and export.
Graphics processing unit: using the STM320DM8148 hardware platform of TI company, it has been internally integrated ARM's and DSP
Heterogeneous dual-core processor.In native system, arm processor carries (SuSE) Linux OS, as main control processor, uses inside
USB Host drives and receives photographic head data, it is possible to obtain complete image or video.The figure gathered by USB interface
As data leave in shared drive, in order to optimize view data storage in internal memory, improve the processing capability in real time of system,
Use EDMA controller that DSP needs those frame data to be processed copy DSP data section to from shared drive, will process simultaneously
Complete result sends back shared drive, it is simple to arm processor calls, and the CPU of dsp processor is served only for the calculating of view data.
The picture initial data and result that are stored in shared drive are exported by serial ports or network interface and are passed through by last arm processor
Display memory element carries out showing and storing.
System provided by the utility model combines following methods and uses, and concrete method is as follows:
The flow process of monocular vision pose measuring method based on Davinci technology is as in figure 2 it is shown, specifically comprise the following steps that
1, binaryzation.(form)
Spending without the concern for the time in PC end binaryzation, general employing Gaussian template carries out binaryzation, because of embedded flat
Platform is higher to rate request, it is considered to make into traditional use Gaussian template binaryzation to use Otsu method to calculate.Otsu method quilt
It is known as being that effect is best, the binarization method that application surface is the widest, the most practical to most of samples.Otsu method binaryzation main
Thought is from the grey level histogram of image, the collection of gray value to be share threshold value T to be divided into two classes, then putting down according to two classifications
The ratio of mean variance (inter-class variance) and all kinds of variances (variance within clusters) is that maximum is to determine threshold value T.
Because the difference of two two field pictures is little, threshold value can use the value that previous frame calculates, and so calculates threshold value and two
Value can be carried out parallel, and speed can be greatly improved.
2, contours extract
First extract all profiles in cooperative target picture, check whether as circle successively according to the character of circle, if circle
Then extract barycenter.From the point of view of in theory, profile not of uniform size, then the pixel sum on different profiles has the biggest difference
Not.The sum of the pixel on the profile of 4 annulus meets certain scope, travels through all of profile, it may be judged whether profile
Pixel sum is in a scope.By pixel sum, filter out a part and be unlikely to be round profile, so can enter
One step simplifies calculating.The area S of circle is equal to π γ2, girth C is equal to 2 π r, it is seen thatUse this proportionate relationship,
We can identify whether this profile is round.There is noise spot in the profile owing to extracting, the profile of the circle of extraction will not be strict
Meet this proportionate relationship, but the ratio of reality does not have the biggest fluctuation in the left and right of 1.Can be quick according to above method
Detection target circle.Use RANSAC algorithm to carry out Circular curve fitting, determine the center of circle.Sort successively according to annulus size, look for
To position corresponding relation between annulus.
3 poses resolve
Process, according to previous image, the characteristic parameter combining camera calibrating parameters obtained and solve relative pose.As it is shown on figure 3,
Set up the mutual relation between image coordinate and locus.OwRepresenting real space coordinate system, Oc represents that camera coordinates is former
Point, (U, V) is expressed as image plane.
From OwCoordinate is tied to the transformational relation such as formula (1) between (U, V) imaging plane, i.e. camera imaging model.Wherein,
R and T represents camera coordinates system and the attitude of world coordinate system and evolution matrix respectively.F is camera focus, dxAnd dyIt it is picture
Unit's size on xy direction.The central coordinate of circle in the cooperative target extracted and corresponding phase point coordinates is utilized to constitute two-dimensional imaging
Plane and three dimensional practicality spatial match point pair.In conjunction with the camera inside and outside parameter matrix in formula (1), P4P algorithm is utilized to carry out position
Appearance resolves, and obtains the posture information of cooperative target.
Claims (2)
1. a monocular vision pose measurement system, at least includes cooperative target template, pose image acquisition units, image procossing
Unit, power supply and display memory element, it is characterised in that: cooperative target template is mounted on object, described cooperative target
Template is four coplanar annulus, and the size of four annulus all differs；Described pose image acquisition units is base
In the COMS camera of USB interface, described COMS camera includes image sensing part, signal read circuit and control circuit, figure
As transducing part, signal read circuit and control circuit are integrated on one chip, pose image acquisition units and image procossing
Unit is connected, and pose view data is exported to graphics processing unit by USB interface；Described graphics processing unit is arranged
Have for the USB interface of received bit appearance view data with for transmitting network interface or the serial ports of data, described graphics processing unit
Using the STM320DM8148 hardware platform of TI company, it has been internally integrated the heterogeneous dual-core processor of ARM and DSP；At image
Reason unit is connected with display memory element, and described power supply is connected with graphics processing unit and powers to graphics processing unit.
Monocular vision pose measurement system the most according to claim 1, it is characterised in that: described display memory element is
Display screen adds SD card, or is PC end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620447304.7U CN205692214U (en) | 2016-05-17 | 2016-05-17 | A kind of monocular vision pose measurement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620447304.7U CN205692214U (en) | 2016-05-17 | 2016-05-17 | A kind of monocular vision pose measurement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205692214U true CN205692214U (en) | 2016-11-16 |
Family
ID=57262019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620447304.7U Expired - Fee Related CN205692214U (en) | 2016-05-17 | 2016-05-17 | A kind of monocular vision pose measurement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205692214U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109877827A (en) * | 2018-12-19 | 2019-06-14 | 东北大学 | A kind of non-fixed point material visual identity of link robot manipulator and grabbing device and method |
| CN111093037A (en) * | 2020-03-20 | 2020-05-01 | 深圳市中科先见医疗科技有限公司 | Image data receiving method, image capturing apparatus, and artificial retina apparatus |
-
2016
- 2016-05-17 CN CN201620447304.7U patent/CN205692214U/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109877827A (en) * | 2018-12-19 | 2019-06-14 | 东北大学 | A kind of non-fixed point material visual identity of link robot manipulator and grabbing device and method |
| CN109877827B (en) * | 2018-12-19 | 2022-03-29 | 东北大学 | Non-fixed point material visual identification and gripping device and method of connecting rod manipulator |
| CN111093037A (en) * | 2020-03-20 | 2020-05-01 | 深圳市中科先见医疗科技有限公司 | Image data receiving method, image capturing apparatus, and artificial retina apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105957090B (en) | A kind of monocular vision pose measuring method and system based on Davinci technology | |
| CN110458805B (en) | Plane detection method, computing device and circuit system | |
| CN106384383B (en) | A kind of RGB-D and SLAM scene reconstruction method based on FAST and FREAK Feature Correspondence Algorithm | |
| Ju et al. | Depth-aware salient object detection using anisotropic center-surround difference | |
| CN100487724C (en) | Quick target identification and positioning system and method | |
| CN104598897B (en) | Visual sensor, image processing method and device, visual interactive equipment | |
| CN102819864B (en) | Luminosity diagram-based geometry and surface material reconstructing method | |
| CN110555412B (en) | End-to-end human body gesture recognition method based on combination of RGB and point cloud | |
| Tian et al. | Depth estimation using a self-supervised network based on cross-layer feature fusion and the quadtree constraint | |
| Gao et al. | Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition | |
| Cui et al. | 3D semantic map construction using improved ORB-SLAM2 for mobile robot in edge computing environment | |
| CN105843386A (en) | Virtual fitting system in shopping mall | |
| Tian et al. | Robust 3-d human detection in complex environments with a depth camera | |
| Xiong et al. | S3D-CNN: skeleton-based 3D consecutive-low-pooling neural network for fall detection | |
| Ma et al. | Automatic branch detection of jujube trees based on 3D reconstruction for dormant pruning using the deep learning-based method | |
| WO2017020140A1 (en) | System for searching for images by sketches using histograms of cell orientations and extraction of contours based on mid-level features | |
| WO2022062238A1 (en) | Football detection method and apparatus, and computer-readable storage medium and robot | |
| Li et al. | Bifnet: Bidirectional fusion network for road segmentation | |
| CN112419326B (en) | Image segmentation data processing method, device, equipment and storage medium | |
| CN106373086A (en) | Augmented reality-based ring 2D online real-time trying method and system | |
| Weiyao et al. | Human action recognition using multilevel depth motion maps | |
| CN108038447A (en) | A kind of pedestrian detecting system based on Zynq-7000 | |
| CN205692214U (en) | A kind of monocular vision pose measurement system | |
| Li et al. | A multi-modal dataset for gait recognition under occlusion | |
| Ghidoni et al. | A multi-viewpoint feature-based re-identification system driven by skeleton keypoints |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161116 Termination date: 20170517 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |