CN101936760A - Vision measuring system for large stockyard and stockpile - Google Patents
Vision measuring system for large stockyard and stockpile Download PDFInfo
- Publication number
- CN101936760A CN101936760A CN200910054129XA CN200910054129A CN101936760A CN 101936760 A CN101936760 A CN 101936760A CN 200910054129X A CN200910054129X A CN 200910054129XA CN 200910054129 A CN200910054129 A CN 200910054129A CN 101936760 A CN101936760 A CN 101936760A
- Authority
- CN
- China
- Prior art keywords
- image
- binocular vision
- server
- image information
- information processing
- 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.)
- Granted
Links
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of non-contact volume measurement, in particular to a vision measuring system for large stockyards and stockpiles, which comprises a first binocular vision subsystem, a second binocular vision subsystem and a server, wherein the output interfaces of the first binocular vision subsystem and the second binocular vision subsystem are respectively connected with the input interface of the server; left view analog signals and right view analog signals collected by the first binocular vision subsystem and the second binocular vision subsystem are inputted in parallel to the server; an image information treatment module in the server processes, identifies and understands the digital image signals, and finally outputs the characteristic calculation and the measurement result of the image information. The relative measurement error of the vision measuring system is less than 0.1 percent. The invention saves manual labor to the maximum, and realizes automatic non-contact stockpile measurement. Workload previously needing several days of manual labor can be fully completed in several minutes after the vision measuring system is invented. The invention improves the working efficiency, and at the same time, the intellectualization of raw materials storage and program management can be realized.
Description
Technical field
What the present invention relates to is a kind of noncontact cubing field, relates in particular to a kind of material stack volume vision measurement system.
Background technology
Up to now, the heap of the large-scale stock yards that enterprise had such as iron and steel, chemical industry, power plant is got material operation and input and output material planning, basically still rely on management and construction pattern, therefore influenced the lifting of these whole enterprise robotizations and informationization technology level dramatically based on manually-operated.
Because the raw material of being stacked in this type of stock ground is bulk materials; as iron ore sand, coke, lime etc.; in process of production; its volume is in a kind of dynamic change state all the time; generally speaking; enterprise measures these storage of raw materials amounts and dynamic management all relies on the method for manual measurement to carry out, and inefficiency also will be shut down at regular intervals and be carried out the continuity that manual measurement influences enterprise's production.Therefore, the automatic management that realize the stock ground certainly will at first realize the automatic measurement technology in stock ground.Begun to adopt laser ranging technique to realize measuring automatically and dynamic observing in the prior art to the stock ground volume, because there is the device complexity in the application of laser technology in this field, working environment required condition restriction such as harshness, price be high, makes the popularization of this technology that significant limitation be arranged.Measuring technique based on machine vision is current a kind of emerging technology, but because its technology is not perfect, therefore the beyond example still of the application in the management system of stock ground does not have ready-made mature technology to use for reference in addition.
Find by prior art documents, Chinese invention patent number is 200510026197.7 patent, patent name is: the vision system of the computer automatic analysis that the stock ground is measured, this patent disclosure the vision system of the computer automatic analysis measured of a kind of stock ground, utilization is arranged on the CCD camera that has the corresponding height place with the stockpile both ends of the surface, as high-order vision collecting point, gather the stockpile panoramic picture, be arranged on the walking chassis with stacker-reclaimer towards the CCD camera of stockpile with the long rails walking of stacker-reclaimer, the moving-vision collection point is set on stacker-reclaimer, all CCD camera image signals transfer to image pick-up card by vision cable separately, image pick-up card is connected with the Flame Image Process front end by pci bus, the picture signal of each CCD camera being carried out the digital information of image in the Flame Image Process front end expresses, the image digitazation of Flame Image Process front end output is expressed by the IEEE1394 protocol interface and is connected to the mutual of host computer realization image information, realizes and export the three-dimensional geometry yardstick of tested stockpile.Can affirm, this invention technology is effective in the computer automatic analysis process that realizes the stock ground, this Technology Need relies on " being arranged on the CCD camera that has the corresponding height place with the stockpile both ends of the surface; as high-order vision collecting point; gather the stockpile panoramic picture; be arranged on the walking chassis with stacker-reclaimer towards the CCD camera of stockpile with the long rails walking of stacker-reclaimer; the moving-vision collection point is set on stacker-reclaimer " to carry out the collection to the stock ground image information, although the collection of image information is comprehensive, but, owing to tend to be subjected to the restriction of objective environment condition in actual field, be difficult to " being arranged on the CCD camera that has the corresponding height place with the stockpile both ends of the surface; as high-order vision collecting point ", the technology that makes is difficult to carry out, and this just needs the stronger new technology of a kind of environmental suitability.
Summary of the invention
Technical matters to be solved by this invention provides a kind of large-scale stock ground stockpile vision measurement system, the vision subsystem of this system is installed in the existing stacker-reclaimer walking mechanism of stock ground, in the stacker-reclaimer operation process, gather the stockpile image automatically, by the computing machine subsequent treatment, realization is measured and dynamic management automatically to the contactless of stock ground, and the technology that makes has more environmental suitability.
A kind of large-scale stock ground stockpile vision measurement system, comprise the first binocular vision subsystem, the second binocular vision subsystem and server three parts, the output interface of first and second binocular vision subsystem connects the input interface that causes server respectively, the left and right view simulating signal that first and second binocular vision subsystem collects is by the parallel server of transporting to, image information processing module in the server is handled, is discerned and understand data image signal, final output image information feature calculation and measurement result.
The described first binocular vision subsystem and the second binocular vision subsystem, both inside is formed with connected mode in full accord;
Described binocular vision subsystem comprises: two ccd video cameras, image pick-up card, front end signal processor, two photoelectric commutators and optical fiber; Wherein, the output interface of two ccd video cameras connects two input channels of image pick-up card respectively, and the output interface of image pick-up card is connected with the input slot of front end signal processor; Front end signal processor is connected to the input interface of server by the photoelectric commutator → optical fiber → photoelectric commutator that connects in turn.
Described front end signal processor comprises image signal input interface, image pretreatment module and processor output interface; Image signal input interface is the input signal slot, its output terminal is connected to image pretreatment module input port, image pretreatment module output port is connected with the input port of processor output interface, and the output port of processor output interface is the output interface of front end signal processor; Described image pretreatment module is born the picture signal that receives is removed noise and intensive treatment.
When the second left and right ccd video camera in the first left and right ccd video camera in the described first binocular vision subsystem and the second binocular vision subsystem was installed, the photocentre of left and right two video cameras was in same surface level and isosceles triangle of two optical axises and the formation of two photocentre lines.
Described server comprises two input interfaces, image information processing module, Industrial Ethernet network interface and display interface device; First, second input interface receives the data image signal from first, second binocular vision subsystem output respectively, its output port is connected with the input port of image information processing module, and the output port of image information processing module is connected with peripheral interfaces such as Industrial Ethernet network interface and display interface devices by data bus to be convenient to carry out data interaction with other webserver; First, second input interface of server second photoelectric commutator from first, second binocular vision subsystem respectively obtains to deliver to image information processing module separately behind the data image signal, so, signal successively carries out computing through video camera geometric model and parameter calibration, image distortion correction, unique point searching and coupling, three-dimensional coordinate calculating sub module, comprises in the digital picture of computing acquisition that object point 3 d space coordinate information can export and show by Industrial Ethernet network and display interface device and peripherals.
Image information processing module in the described server comprises video camera geometric model and parameter calibration submodule, image distortion correction submodule, unique point searching and matched sub-block and three-dimensional coordinate calculating sub module; The input end of video camera geometric model and parameter calibration submodule is the input end of image information processing module, that is the input interface of server, the video camera geometric model is connected with the input end of image distortion correction submodule with the output terminal of parameter calibration submodule, the output terminal of image distortion correction submodule is sought with unique point and is connected with the input end of matched sub-block, unique point is sought and is connected with the input end of three-dimensional coordinate calculating sub module with the output terminal of matched sub-block, the output terminal of three-dimensional coordinate calculating sub module is the output terminal of image information processing module, that is the output interface of server.
Video camera geometric model in the described image information processing module and parameter calibration submodule are to set up the prerequisite that the video camera geometric model is demarcated video camera, and camera parameters is demarcated, and at first will set up the coordinate data relation of stereo vision imaging; This submodule is exactly to realize the demarcation of the inside and outside parameter of video camera by setting up transformational relation between empty imaging plane coordinate system of world coordinate system, camera coordinate system, normalization and the computer picture coordinate system.
Image distortion correction submodule in the described image information processing module is proofreaied and correct by the point coordinate of inversion operation after will being subjected to radially to influence with tangential distortion of distortion equation and is distortionless coordinate, this computation process is called " going distortion " again, and the image of eliminating after distorting can give expression to actual scenery time of day to greatest extent.
Unique point searching in the described image information processing module and matched sub-block directly adopt the Corner Detection Algorithm based on gradation of image, promptly reach the purpose that detects angle point by calculating curvature and gradient; Subsequently, carry out the coupling of common point in left and right view, according to outer utmost point geometrical constraint principle, according to the corresponding relation and the least error criterion of point and outer polar curve, the common point that finally obtains left and right view is right; The so-called outer utmost point how much, promptly at binocular vision system from two same points of angular observation, seek the relevant geometry problem that the outer polar curve between two imaging points retrains.
Three-dimensional coordinate calculating sub module in the described image information processing module according to the left and right view common point that obtains to by the video camera geometric model, it is the coordinate data transformational relation, obtain two calculated values of common point to pairing object point world coordinate system, get the mean value of these two calculated values again, finally obtain the pairing 3 d space coordinate of left and right view common point.
Adopt the binocular vision subsystem images acquired of two groups of simulation human eyes among the present invention, image information is comprehensive, can eliminate the image non-linear distortion that optical lens causes automatically, automatically realize the common point coupling of left and right view and can realize the definite of object point three-dimensional coordinate automatically, measuring relative errors is less than 0.1%; Save manpower to greatest extent, realize the stockpile measurement that robotization is contactless, original labor workload that needs several days, only need the time of a few minutes just can all finish after adopting the present invention, and can provide digital picture and digital feature information thereof for digital management, realized that when having improved work efficiency stockpile gets the intellectuality with planning management.
Description of drawings
The system construction drawing that Fig. 1 adopts for the embodiment of the invention;
Fig. 2 is the first binocular vision subsystem structure figure in the system of the present invention;
Fig. 3 is the second binocular vision subsystem structure figure in the system of the present invention;
Fig. 4 is the server module structural drawing in the system of the present invention;
Fig. 5 is the sub modular structure figure in the server module
Fig. 6 is the horizontal installation diagram of left and right CCD camera in the binocular vision system;
Fig. 7 is the working state figure (vertical view) of left and right CCD camera on heap, reclaimer;
Fig. 8 is that left and right CCD camera is installed the side direction view with duty on reclaimer.
Among the figure: 1 first binocular vision subsystem, 11 first left ccd video cameras, 12 first right ccd video cameras, 13 first image pick-up cards, 14 first front end signal processor, 15 first photoelectric commutators, 16 first optical fiber, 17 second photoelectric commutators, 2 second binocular vision subsystems, 21 second left ccd video cameras, 22 second right ccd video cameras, 23 second image pick-up cards, 24 second front end signal processor, 25 the 3rd photoelectric commutators, 26 second optical fiber, 27 the 4th photoelectric commutators, 3 servers, 31 first input interfaces, 32 second input interfaces, 33 image information processing module, 34 Industrial Ethernet network interfaces, 35 display interface devices, 36 parameter calibration submodules, 37 image distortion correction submodules, 38 unique points are sought and matched sub-block, 39 three-dimensional coordinate calculating sub module.
Embodiment
Below in conjunction with specific embodiment, further set forth the present invention.Should be understood that these embodiment only to be used to the present invention is described and be not used in and limit the scope of the invention.Should be understood that in addition those skilled in the art can make various changes or modifications the present invention after the content of having read the present invention's statement, these equivalent form of values fall within the application's appended claims institute restricted portion equally.
As shown in Figure 1, this large-scale stock ground stockpile vision measurement system comprises: the first binocular vision subsystem 1, the second binocular vision subsystem 2 and server 3.The output interface that the output interface of the first binocular vision subsystem 1 connects first input interface, 31, the second binocular vision subsystems 2 that cause server 3 connects second input interface 32 that causes server 3.
As shown in Figure 2, the first binocular vision subsystem in the present embodiment comprises: first left ccd video camera 11, the first right ccd video camera 12, first image pick-up card 13, first front end signal processor 14, first photoelectric commutator 15, first optical fiber 16, second photoelectric commutator 17; The output interface of the first left ccd video camera 11 is connected with first input channel of first image pick-up card 13, and the output interface of the first right ccd video camera 12 is connected with second input channel of first image pick-up card 13; The output interface of first image pick-up card 13 is connected with the input slot of first front end signal processor 14; The output interface of first front end signal processor 14 is connected with the electric signal interface of first photoelectric commutator 15, the optical signal interface of first photoelectric commutator 15 is connected with the input port of first optical fiber 16, the output port of first optical fiber 16 is connected with the optical signal interface of second photoelectric commutator 17, and the electric signal interface of the second photoelectric commutator 17 i.e. output interface of the first binocular vision subsystem 1 is connected with first input interface 31 of server 3.Wherein, the first left and right ccd video camera 11,12 walks abreast the left and right view that is collected in sampling instant and inputs to first image pick-up card 13; First image pick-up card 13 converts original image to data image signal and transports to first front end signal processor 14; 14 pairs of digital pictures of first front end signal processor are removed pre-service such as noise and reinforcement; Convert the electrical signal to light signal through pretreated data image signal through first photoelectric commutator 15, light signal is transferred to second photoelectric commutator 17 by first optical fiber 16; Second photoelectric commutator 17 converts image light signals to electric signal again, and last, electric signal inputs to the image information processing module 33 of server 3 by first input interface 31 of server 3.Four-headed arrow among the figure is represented: utilize same physical medium to send to the moment of first image pick-up card 13 in order to the control image acquisition along the reverse direction of signal transmission from the still exportable steering order of server 3.
As shown in Figure 3, the second binocular vision subsystem in the present embodiment comprises: second left ccd video camera 21, the second right ccd video camera 22, second image pick-up card 23, second front end signal processor 24, the 3rd photoelectric commutator 25, second optical fiber 26, the 4th photoelectric commutator 27; The output interface of the second left ccd video camera 21 is connected with first input channel of second image pick-up card 23, and the output interface of the second right ccd video camera 22 is connected with second input channel of second image pick-up card 23; The output interface of second image pick-up card 23 is connected with the input slot of second front end signal processor 24; The output interface of second front end signal processor 24 is connected with the electric signal interface of the 3rd photoelectric commutator 25, the optical signal interface of the 3rd photoelectric commutator 25 is connected with the input port of second optical fiber 26, the output port of second optical fiber 26 is connected with the optical signal interface of the 4th photoelectric commutator 27, and the electric signal interface of the 4th photoelectric commutator 27 i.e. output interface of the second binocular vision subsystem 2 is connected with second input interface 32 of server 3.Wherein, the second left and right ccd video camera 21,22 walks abreast the left and right view that is collected in sampling instant and inputs to second image pick-up card 23; Second image pick-up card 23 converts original image to data image signal and transports to second front end signal processor 24; 24 pairs of digital pictures of second front end signal processor are removed pre-service such as noise and reinforcement; Convert the electrical signal to light signal through pretreated data image signal through the 3rd photoelectric commutator 25, light signal is transferred to the 4th photoelectric commutator 27 by second optical fiber 26; The 4th photoelectric commutator 27 converts image light signals to electric signal again, and last, electric signal inputs to the image information processing module 33 of server 3 by second input interface 32 of server 3.Four-headed arrow among the figure is represented: utilize same physical medium to send to the moment of second image pick-up card 23 in order to the control image acquisition along the reverse direction of signal transmission from the still exportable steering order of server 3.
CCD, promptly the core sensor spare of imageing sensor is a kind of photosensitive charge coupled semiconductor device, the abbreviation CCD of the English Charge Couple Device of unified employing represents in the industry.Two ccd video cameras in each binocular vision subsystem are corresponding people's images of left and right eyes respectively; Each binocular vision subsystem can be gathered two width of cloth images by two ccd video cameras wherein simultaneously in each sampling instant, and will be exported to the input interface of server after this two width of cloth image process pre-service by the output interface of binocular vision subsystem.Therefore, server can receive four width of cloth images simultaneously in each sampling instant, comprise each two width of cloth image from first, second binocular vision subsystem, per two width of cloth images divide left and right two width of cloth images again, between whole sampling period, all images that collect form two groups of left and right sides views of first, second binocular vision subsystem respectively to sequence.Left and right ccd video camera walks abreast the left and right view that is collected in sampling instant and inputs to image pick-up card; Image pick-up card converts original image data image signal to and transports to front end signal processor; Front end signal processor is removed pre-service such as noise and reinforcement to digital picture; Convert the electrical signal to light signal through first photoelectric commutator through pretreated data image signal, light signal by Optical Fiber Transmission to second photoelectric commutator; Second photoelectric commutator converts image light signals to electric signal again, and last, electric signal inputs to the image information processing module of server by the input interface of server.
As shown in Figure 4, the server 3 in the present embodiment comprises: first input interface 31, second input interface 32, image information processing module 33, Industrial Ethernet network interface 34, display interface device 35.The electric signal interface output signal that first input interface 31 receives from second photoelectric commutator 17 in first vision subsystem, the electric signal interface output signal that second input interface 32 receives from the 4th photoelectric commutator 27 in second vision subsystem, the output terminal of first, second input interface 31,32 is connected with the input end of image information processing module 33, and the output terminal of image information processing module 33 is connected with Industrial Ethernet network interface 34 and display interface device 35.Server is the parallel image information processing module of delivering in the server 3 33 of data image signal of second, four photoelectric commutators, 17,27 acquisitions from first, second binocular vision subsystem 1,2 respectively, data image signal is through the computing of image information processing module 33, and information such as acquisition object point 3 d space coordinate are by Industrial Ethernet network interface 34 and display interface device 35 outputs and demonstration.
As shown in Figure 5, the image information processing module 33 in the present embodiment server 3 comprises: video camera geometric model and parameter calibration submodule 36, image distortion correction submodule 37, unique point are sought and matched sub-block 38, three-dimensional coordinate calculating sub module 39.First of server 3, second input interface 31,32 output terminal is connected with the input end of video camera geometric model with parameter calibration submodule 36, the video camera geometric model is connected with the input end of image distortion correction submodule 37 with the output terminal of parameter calibration submodule 36, the output terminal of image distortion correction submodule 37 is sought with unique point and is connected with the input end of matched sub-block 38, unique point is sought and is connected with the input end of three-dimensional coordinate calculating sub module 39 with the output terminal of matched sub-block 38, and the output terminal of three-dimensional coordinate calculating sub module 39 is connected with Industrial Ethernet network interface 34 and display interface device 35.Server 3 parallel video camera geometric model and parameter calibration submodule 36, image distortion correction submodule 37, the unique point searching of delivering in server 3 image information processing module 33 of data image signal of second, four photoelectric commutators, 17,27 acquisitions from first, second binocular vision subsystem 1,2 respectively carries out computing successively with matched sub-block 38 and three-dimensional coordinate calculating sub module 39, and information such as computing acquisition object point 3 d space coordinate are exported by Industrial Ethernet network interface 34 and display interface device 35 and shown.
Video camera geometric model in the described image information processing module and parameter calibration submodule are to set up the prerequisite that the video camera geometric model is demarcated video camera, and camera parameters is demarcated, and at first will set up the coordinate data relation of stereo vision imaging; This submodule is exactly to realize the demarcation of the inside and outside parameter of video camera by setting up transformational relation between empty imaging plane coordinate system of world coordinate system, camera coordinate system, normalization and the computer picture coordinate system.
Image distortion correction submodule in the described image information processing module is proofreaied and correct by the point coordinate of inversion operation after will being subjected to radially to influence with tangential distortion of distortion equation and is distortionless coordinate, this computation process is called " going distortion " again, and the image of eliminating after distorting can give expression to actual scenery time of day to greatest extent.
Unique point searching in the described image information processing module and matched sub-block directly adopt the Corner Detection Algorithm based on gradation of image, promptly reach the purpose that detects angle point by calculating curvature and gradient; Subsequently, carry out the coupling of common point in left and right view, according to outer utmost point geometrical constraint principle, according to the corresponding relation and the least error criterion of point and outer polar curve, the common point that finally obtains left and right view is right; The so-called outer utmost point how much, promptly at binocular vision system from two same points of angular observation, seek the relevant geometry problem that the outer polar curve between two imaging points retrains.
Three-dimensional coordinate calculating sub module in the described image information processing module according to the left and right view common point that obtains to by the video camera geometric model, it is the coordinate data transformational relation, obtain two calculated values of common point to pairing object point world coordinate system, get the mean value of these two calculated values again, finally obtain the pairing 3 d space coordinate of left and right view common point.
As shown in Figure 6, the installation of first left and right CCD camera 11,12 in the first binocular vision subsystem or the second left and right CCD camera 21,22 in the second binocular vision subsystem should be followed: the photocentre of two video cameras is in same surface level principle and two optical axises and two photocentre lines and forms an isosceles triangle principle.
As shown in Figure 7, be the first left and right CCD camera 11,12 in the first binocular vision subsystem and the second left and right CCD camera 21,22 in the second binocular vision subsystem working state figure on heap, reclaimer.
The first left and right CCD camera 11,12 in the first binocular vision subsystem is installed on the stacker, and geometric relationship between the two determines that method is as follows:
1. the level interval between the first left CCD camera 11 and the first right CCD camera 12, be distance between both the camera coordinate system initial point: greatly about about 20m, therefore can determine that two camera lens level intervals are 20m according to the maximum extensible width of stacker platform.
2. camera lens vertical direction angle: according to stockpile be the 16m height, the angle of repose that is about 4m, stockpile from the fore-and-aft distance of material pin as the upright position of head is that 26 °, the highest available height of stationary platform of stacker are about 6m, camera lens can only be installed on the platform of 6m height, the coboundary line of vertical field of view is parallel with the stock ground slope, greatly about about 2.926m, the following depression angle that therefore can budget goes out camera lens is 19 ° apart from the camera lens vertical point for the lower limb line of vertical field of view and the intersection point of stock ground bottom line.
Described angle of repose is the side of stockpile and the angle of bottom surface, i.e. tgA=H/L, and in the formula: A is an angle of repose, and H is the height of stockpile, and L is half of stockpile bottom surface length.
3. camera lens horizontal direction angle: according to the universal law of stereoscopic vision, the principle that two cameras in the binocular vision device and measured object point should be formed an isosceles triangle, according to above-mentioned level interval and camera lens vertical direction angle, camera lens horizontal direction angle is 32 ° on the stacker.
The second left and right CCD camera 21,22 in the second binocular vision subsystem is installed on the reclaimer, and geometric relationship between the two determines that method is as follows:
1. the level interval between the second left CCD camera 21 and the second right CCD camera 22, be distance between both the camera coordinate system initial point: according to the maximum extensible width of reclaimer platform greatly about about 10m, limit by it, can only determine that two camera lens level intervals are 10m.
2. the same on camera lens vertical direction angle and the stacker.
3. camera lens horizontal direction angle: according to the universal law of stereoscopic vision, the principle that two cameras in the binocular vision device and measured object point should be formed an isosceles triangle, according to above-mentioned level interval and camera lens vertical direction angle, camera lens horizontal direction angle is 17.35 ° on the reclaimer.
As shown in Figure 8, be the duty side direction view of the second left and right CCD camera 21,22 on reclaimer in the second binocular vision subsystem.
The present invention is in implementation process, the left side that the first binocular vision subsystem 1 collects, the right view simulating signal is by parallel first image pick-up card of transporting in the native system 13, first image pick-up card 13 converts image analoging signal to data image signal and transports to first front end signal processor 14 in the native system, 14 pairs of digital pictures of first front end signal processor are removed pre-service such as noise and reinforcement, convert the electrical signal to light signal through first photoelectric commutator 15 of pretreated data image signal in native system, light signal is transferred to second photoelectric commutator 17 in the native system by first optical fiber 16, second photoelectric commutator 17 converts image light signals to electric signal again, at last, electric signal inputs to the image information processing module of server 3 by first input interface 31 of server 3; The left side that the second binocular vision subsystem 2 collects, the right view simulating signal is by parallel second image pick-up card of transporting in the native system 23, second image pick-up card 23 converts image analoging signal to data image signal and transports to second front end signal processor 24 in the native system, 24 pairs of digital pictures of second front end signal processor are removed pre-service such as noise and reinforcement, convert the electrical signal to light signal through the 3rd photoelectric commutator 25 of pretreated data image signal in native system, light signal is transferred to the 4th photoelectric commutator 27 in the native system by second optical fiber 26, the 4th photoelectric commutator 27 converts image light signals to electric signal again, at last, electric signal inputs to the image information processing module of server 3 by second input interface 32 of server 3; Server with data image signal handle with computing after output finally to identification, understanding and the measurement result of image information.
The process of circulation of data image signal in server is: first of server, second input interface is respectively from first, electric transducer in the second binocular vision subsystem obtains to deliver to image information processing module separately behind the data image signal, so, signal successively passes through video camera geometric model and parameter calibration submodule, the image distortion correction submodule, unique point is sought and matched sub-block, the three-dimensional coordinate calculating sub module is carried out computing, comprises in the digital picture that computing obtains that information such as object point 3 d space coordinate can export and show by Industrial Ethernet network and display interface device and peripherals.
Claims (10)
1. one kind large-scale stock ground stockpile vision measurement system, it is characterized in that: comprise the first binocular vision subsystem, the second binocular vision subsystem and server three parts, the output interface of first and second binocular vision subsystem connects the input interface that causes server respectively, the left and right view simulating signal that first and second binocular vision subsystem collects is by the parallel server of transporting to, image information processing module in the server is handled, is discerned and understand data image signal, final output image information feature calculation and measurement result.
2. large-scale stock ground according to claim 1 stockpile vision measurement system is characterized in that: the described first binocular vision subsystem and the second binocular vision subsystem, and both inside is formed with connected mode in full accord;
Described binocular vision subsystem comprises: two ccd video cameras, image pick-up card, front end signal processor, two photoelectric commutators and optical fiber; Wherein, the output interface of two ccd video cameras connects two input channels of image pick-up card respectively, and the output interface of image pick-up card is connected with the input slot of front end signal processor; Front end signal processor is connected to the input interface of server by the photoelectric commutator → optical fiber → photoelectric commutator that connects in turn.
3. large-scale stock ground according to claim 1 and 2 stockpile vision measurement system, it is characterized in that: described front end signal processor comprises image signal input interface, image pretreatment module and processor output interface; Image signal input interface is the input signal slot, its output terminal is connected to image pretreatment module input port, image pretreatment module output port is connected with the input port of processor output interface, and the output port of processor output interface is the output interface of front end signal processor; Described image pretreatment module is born the picture signal that receives is removed noise and intensive treatment.
4. large-scale stock ground according to claim 1 and 2 stockpile vision measurement system, it is characterized in that: when the second left and right ccd video camera in the first left and right ccd video camera in the described first binocular vision subsystem and the second binocular vision subsystem was installed, the photocentre of left and right two video cameras was in same surface level and isosceles triangle of two optical axises and the formation of two photocentre lines.
5. large-scale stock ground according to claim 1 stockpile vision measurement system, it is characterized in that: described server comprises two input interfaces, image information processing module, Industrial Ethernet network interface and display interface device; First, second input interface receives the data image signal from first, second binocular vision subsystem output respectively, its output port is connected with the input port of image information processing module, and the output port of image information processing module is connected with peripheral interfaces such as Industrial Ethernet network interface and display interface devices by data bus to be convenient to carry out data interaction with other webserver; First, second input interface of server second photoelectric commutator from first, second binocular vision subsystem respectively obtains to deliver to image information processing module separately behind the data image signal, so, signal successively carries out computing through video camera geometric model and parameter calibration, image distortion correction, unique point searching and coupling, three-dimensional coordinate calculating sub module, comprises in the digital picture of computing acquisition that object point 3 d space coordinate information can export and show by Industrial Ethernet network and display interface device and peripherals.
6. large-scale according to claim 1 or 5 stock ground stockpile vision measurement system is characterized in that: the image information processing module in the described server comprises video camera geometric model and parameter calibration submodule, image distortion correction submodule, unique point searching and matched sub-block and three-dimensional coordinate calculating sub module; The input end of video camera geometric model and parameter calibration submodule is the input end of image information processing module, that is the input interface of server, the video camera geometric model is connected with the input end of image distortion correction submodule with the output terminal of parameter calibration submodule, the output terminal of image distortion correction submodule is sought with unique point and is connected with the input end of matched sub-block, unique point is sought and is connected with the input end of three-dimensional coordinate calculating sub module with the output terminal of matched sub-block, the output terminal of three-dimensional coordinate calculating sub module is the output terminal of image information processing module, that is the output interface of server.
7. large-scale stock ground according to claim 6 stockpile vision measurement system, it is characterized in that: video camera geometric model in the described image information processing module and parameter calibration submodule are to set up the prerequisite that the video camera geometric model is demarcated video camera, camera parameters is demarcated, at first will be set up the coordinate data relation of stereo vision imaging; This submodule is exactly to realize the demarcation of the inside and outside parameter of video camera by setting up transformational relation between empty imaging plane coordinate system of world coordinate system, camera coordinate system, normalization and the computer picture coordinate system.
8. large-scale stock ground according to claim 6 stockpile vision measurement system, it is characterized in that: the image distortion correction submodule in the described image information processing module is proofreaied and correct by the point coordinate of inversion operation after will being subjected to radially to influence with tangential distortion of distortion equation and is distortionless coordinate, this computation process is called " going distortion " again, and the image of eliminating after distorting can give expression to actual scenery time of day to greatest extent.
9. large-scale stock ground according to claim 6 stockpile vision measurement system, it is characterized in that: the unique point in the described image information processing module is sought and the direct Corner Detection Algorithm that adopts based on gradation of image of matched sub-block, promptly reaches the purpose that detects angle point by calculating curvature and gradient; Subsequently, carry out the coupling of common point in left and right view, according to outer utmost point geometrical constraint principle, according to the corresponding relation and the least error criterion of point and outer polar curve, the common point that finally obtains left and right view is right; The so-called outer utmost point how much, promptly at binocular vision system from two same points of angular observation, seek the relevant geometry problem that the outer polar curve between two imaging points retrains.
10. large-scale stock ground according to claim 6 stockpile vision measurement system, it is characterized in that: the three-dimensional coordinate calculating sub module in the described image information processing module according to the left and right view common point that obtains to by the video camera geometric model, it is the coordinate data transformational relation, obtain two calculated values of common point to pairing object point world coordinate system, get the mean value of these two calculated values again, finally obtain the pairing 3 d space coordinate of left and right view common point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910054129XA CN101936760B (en) | 2009-06-30 | 2009-06-30 | Vision measuring system for large stockyard and stockpile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910054129XA CN101936760B (en) | 2009-06-30 | 2009-06-30 | Vision measuring system for large stockyard and stockpile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101936760A true CN101936760A (en) | 2011-01-05 |
| CN101936760B CN101936760B (en) | 2012-03-28 |
Family
ID=43390209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910054129XA Active CN101936760B (en) | 2009-06-30 | 2009-06-30 | Vision measuring system for large stockyard and stockpile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101936760B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014032443A1 (en) * | 2012-08-30 | 2014-03-06 | International Business Machines Corporation | Method and apparatus for managing to-be-stored items |
| CN105547389A (en) * | 2016-01-14 | 2016-05-04 | 中国航空动力机械研究所 | Lubricating oil nozzle flow two-CCD-camera measure system and method |
| CN105551064A (en) * | 2015-12-08 | 2016-05-04 | 济南中维世纪科技有限公司 | Method for estimating volume change rate of stacked materials based on image features |
| CN108225502A (en) * | 2017-12-06 | 2018-06-29 | 中南大学 | A kind of truck loads ore quality method of estimation and system |
| CN108896125A (en) * | 2018-05-08 | 2018-11-27 | 浙江大学 | A method of the gravity stream volume of two interactions of measurement |
| CN110703074A (en) * | 2019-09-03 | 2020-01-17 | 国网浙江省电力有限公司嘉兴供电公司 | High-voltage circuit breaker comprehensive detection system and method based on ubiquitous power Internet of things |
| CN111739081A (en) * | 2020-08-06 | 2020-10-02 | 成都极米科技股份有限公司 | Feature point matching method, splicing method and device, electronic equipment and storage medium |
| CN112387982A (en) * | 2020-10-21 | 2021-02-23 | 上海交通大学 | Laser additive process power combined regulation and control method |
| CN113103228A (en) * | 2021-03-29 | 2021-07-13 | 航天时代电子技术股份有限公司 | Teleoperation robot |
| CN113959332A (en) * | 2021-09-22 | 2022-01-21 | 西安交通大学 | Large aerostat volume real-time monitoring system based on binocular vision |
-
2009
- 2009-06-30 CN CN200910054129XA patent/CN101936760B/en active Active
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014032443A1 (en) * | 2012-08-30 | 2014-03-06 | International Business Machines Corporation | Method and apparatus for managing to-be-stored items |
| CN105551064A (en) * | 2015-12-08 | 2016-05-04 | 济南中维世纪科技有限公司 | Method for estimating volume change rate of stacked materials based on image features |
| CN105551064B (en) * | 2015-12-08 | 2018-04-20 | 济南中维世纪科技有限公司 | A kind of method based on characteristics of image estimation windrow volume change |
| CN105547389A (en) * | 2016-01-14 | 2016-05-04 | 中国航空动力机械研究所 | Lubricating oil nozzle flow two-CCD-camera measure system and method |
| CN108225502A (en) * | 2017-12-06 | 2018-06-29 | 中南大学 | A kind of truck loads ore quality method of estimation and system |
| CN108896125A (en) * | 2018-05-08 | 2018-11-27 | 浙江大学 | A method of the gravity stream volume of two interactions of measurement |
| CN110703074A (en) * | 2019-09-03 | 2020-01-17 | 国网浙江省电力有限公司嘉兴供电公司 | High-voltage circuit breaker comprehensive detection system and method based on ubiquitous power Internet of things |
| CN111739081A (en) * | 2020-08-06 | 2020-10-02 | 成都极米科技股份有限公司 | Feature point matching method, splicing method and device, electronic equipment and storage medium |
| CN112387982A (en) * | 2020-10-21 | 2021-02-23 | 上海交通大学 | Laser additive process power combined regulation and control method |
| CN112387982B (en) * | 2020-10-21 | 2021-10-12 | 上海交通大学 | Laser additive process power combined regulation and control method |
| CN113103228A (en) * | 2021-03-29 | 2021-07-13 | 航天时代电子技术股份有限公司 | Teleoperation robot |
| CN113103228B (en) * | 2021-03-29 | 2023-08-15 | 航天时代电子技术股份有限公司 | Teleoperation robot |
| CN113959332A (en) * | 2021-09-22 | 2022-01-21 | 西安交通大学 | Large aerostat volume real-time monitoring system based on binocular vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101936760B (en) | 2012-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101936760B (en) | Vision measuring system for large stockyard and stockpile | |
| CN101936761B (en) | Visual measuring method of stockpile in large-scale stock ground | |
| CN103198477B (en) | Apple fruitlet bagging robot visual positioning method | |
| CN100504288C (en) | Article geometrical size measuring device and method based on multi-source image fusion | |
| CN100414249C (en) | Computer automatic measuring visual system for stock ground measuring | |
| CN104626151B (en) | A kind of mechanical hand wafer centring means and method | |
| CN103425969A (en) | Detection system and detection method for identifying type of wheel hub | |
| CN111640152A (en) | Fish growth monitoring method and system | |
| CN206312166U (en) | Robot vision image preprocessing system and robot | |
| CN110756462B (en) | Power adapter test method, device, system, control device and storage medium | |
| CN101510295B (en) | Design method for machine vision system based on PCIe and Vision Assistan | |
| CN100427876C (en) | Automatic measuring method of computer visual system for stock ground measuring | |
| CN102759530A (en) | Online detection device for surface quality image | |
| CN110245539A (en) | A kind of automatic scan code system of Power Material | |
| CN112652020A (en) | Visual SLAM method based on AdaLAM algorithm | |
| CN110827355A (en) | Moving target rapid positioning method and system based on video image coordinates | |
| CN107990825B (en) | High-precision position measuring device and method based on priori data correction | |
| CN111465188A (en) | Method and device for inserting special-shaped circuit board and components | |
| CN103179332A (en) | Visual target self-adaption detection controller based on field programmable gate array (FPGA) technology | |
| CN109571898A (en) | A kind of manipulator of injection machine precision compensation system and method | |
| CN105354582A (en) | Image corner extraction method and device and image corner extraction pick-up device | |
| CN202565373U (en) | CB industrial camera | |
| CN204373626U (en) | A kind of system of dimensional measurement | |
| CN113989428A (en) | Metallurgical reservoir area global three-dimensional reconstruction method and device based on depth vision | |
| CN203164738U (en) | Machine vision control system based on cloud computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |