CN107869954A - A kind of binocular vision volume weight measuring system and its implementation - Google Patents

A kind of binocular vision volume weight measuring system and its implementation Download PDF

Info

Publication number
CN107869954A
CN107869954A CN201710994098.0A CN201710994098A CN107869954A CN 107869954 A CN107869954 A CN 107869954A CN 201710994098 A CN201710994098 A CN 201710994098A CN 107869954 A CN107869954 A CN 107869954A
Authority
CN
China
Prior art keywords
industrial camera
camera
mrow
mtr
mtd
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
Application number
CN201710994098.0A
Other languages
Chinese (zh)
Other versions
CN107869954B (en
Inventor
谈季
刘信宏
萧植涛
雷亮
何苗
刘树成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong University of Technology
Original Assignee
Guangdong University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong University of Technology filed Critical Guangdong University of Technology
Priority to CN201710994098.0A priority Critical patent/CN107869954B/en
Publication of CN107869954A publication Critical patent/CN107869954A/en
Application granted granted Critical
Publication of CN107869954B publication Critical patent/CN107869954B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01G—WEIGHING
    • G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
    • G01G19/002—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for postal parcels and letters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G06T7/85—Stereo camera calibration
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a kind of binocular vision volume weight measuring system, including Installation cabinet, and it is arranged on the first industrial camera, the second industrial camera, LASER Light Source, LED bar graph light source, signal processing system, measuring table and Bluetooth electronic scale in the Installation cabinet, wherein, the measuring table is arranged on the bottom of the Installation cabinet, and the Bluetooth electronic scale is arranged on the lower section of the measuring table；Second industrial camera is arranged on the top of the Installation cabinet, and the LASER Light Source is arranged side by side with second industrial camera, and the shooting direction keeping parallelism of the radiation direction of the LASER Light Source and second industrial camera；The present invention is compared to traditional artificial tape measure mode, and the advantage such as have quick, accurate, non-contact and cost cheap suitable for the automatic measurement of batch, greatly reduces cost of labor, improves production efficiency.

Description

A kind of binocular vision volume weight measuring system and its implementation
Technical field
The present invention relates to non-contact intelligent observation and control technology field, and in particular to a kind of binocular vision volume weight measuring system And its implementation.
Background technology
As logistic industry is fast-developing at home, quick measurement and sorting to various box for material circulation size and weight, Logistics traffic congestion is avoided, has become urgent problem.Measurement for box for material circulation at present also in manually measuring respectively The process of box for material circulation volume and weight, and in e measurement technology, in general laser ranging technique is only capable of obtaining the depth letter of object Breath, can not provide object area.It is right and although laser scanner technique can establish threedimensional model by scanning body surface It is harsh in the requirement of body surface, such as need to coat developer in body surface, so that laser produces diffusing reflection with it, This method is troublesome in poeration, using limitation being present.
The content of the invention
The shortcomings that it is an object of the invention to overcome prior art and deficiency, there is provided a kind of binocular vision volume weight measurement System.
Another object of the present invention is to provide a kind of implementation method of binocular vision volume weight measuring system.
The purpose of the present invention is achieved through the following technical solutions：
A kind of binocular vision volume weight measuring system, including Installation cabinet, and first be arranged in the Installation cabinet Industrial camera, the second industrial camera, LASER Light Source, LED bar graph light source, signal processing system, measuring table and Bluetooth electronic scale, Wherein, the measuring table is arranged on the bottom of the Installation cabinet, and the Bluetooth electronic scale is arranged under the measuring table Side；Second industrial camera is arranged on the top of the Installation cabinet, and the LASER Light Source and second industrial camera are side by side Set, and the shooting direction keeping parallelism of the radiation direction of the LASER Light Source and second industrial camera；Second work Industry camera and the LASER Light Source are arranged on the surface of the measuring table, and the shooting direction of second industrial camera with The radiation direction of the LASER Light Source is all both perpendicular to the measuring table；First industrial camera is arranged on the installation The top of cabinet, first industrial camera are located at the oblique upper of the measuring table, and first industrial camera and the survey Platform is measured to set in 45 degree of overturning angles；First industrial camera and the second industrial camera shoot the visual field model of the measuring table Enclose identical；The LED bar graph light source is provided with four, and two of which LED bar graph light source levels are arranged on second industrial camera Front and rear sides, two other LED bar graph light source is vertically arranged in the front and rear sides of first industrial camera；
First industrial camera, the second industrial camera, LASER Light Source and Bluetooth electronic scale respectively with the signal transacting System is connected；The signal processing system is provided with display screen.
Preferably, the measuring table is by painting and being polished into black smooth surface；Logistics can be ensured by so setting Case disengaging measuring table is steadily smooth, and can reduce the ambient interferences in image processing process.
A kind of implementation method by above-mentioned binocular vision volume weight measuring system, comprise the steps：
Step 1, start binocular vision volume weight measuring system, the first industrial camera, the second industrial camera, laser light Source, Bluetooth electronic scale, LED bar graph light source and signal processing system are started working；
Step 2, carry out the mark of the intrinsic parameter of the first industrial camera and the second industrial camera, outer parameter and distortion factor It is fixed, and calibration result is sent to signal processing system, specific workflow is as follows：
(1) first industrial camera and the second industrial camera meet pinhole camera model, if image coordinate vector isWherein (u, v) is the pixel coordinate of target point；Camera Intrinsic Matrix isWherein fx,fy, cx,cyRespectively x is to focal length, and y is to focal length and optical axis center coordinate；Camera extrinsic matrix number is (R | T), and wherein R is camera photocentre For coordinate system relative to 3 × 3 spin matrixs of world coordinate system, T is camera photocentre coordinate system relative to the 3 × 1 of world coordinate system Translation matrix；World coordinates vector isWherein X, Y, Z are the world coordinates of target point；Camera imaging model meets Relational expression：
Wherein zcFor scale factor；In addition, camera distortion model meets following relation：
Wherein, (x, y) be distortion rectification before image physical coordinates, (xcor,ycor) be distortion rectification after image physics Coordinate, r=x2+y2,k1,k2,k3,p1,p2For 3 coefficient of radial distortion and 2 tangential distortion coefficients of camera；
First industrial camera and the purpose of the second industrial camera demarcation are to solve camera intrinsic parameter, outer parameter and distortion Number, is set to zero plane, using Zhang Zhengyou chessboard plane reference methods, by the position and the angle shot that change chessboard by measuring table 20 images, the demarcation of camera is carried out, and solve and obtain camera intrinsic parameter, outer parameter and distortion factor；
Step 3, box for material circulation is placed on measuring table, LASER Light Source irradiation box for material circulation, and in the upper surface shape of box for material circulation Into laser spots, Bluetooth electronic scale detects the weight of box for material circulation, and when the data stabilization of Bluetooth electronic scale, record box for material circulation weight is simultaneously Data are transferred to signal processing system by the bluetooth module on electronic scale, signal processing system transmits weight data afterwards To the first industrial camera and the side elevation image C1 of its collection box for material circulation is triggered, the first industrial camera is defaulted as small aperture pattern, this Sample can ensure that the brightness of image of collection is low, be easy to extraction of the later stage to laser spots in image；Two first are carried out to side elevation image C1 Value handles to obtain side elevation image C2, then carries out laser spots contours extract to side elevation image C2, is taken after obtaining the profile of laser spots Its smallest enclosing circle shape, and the center of circle pixel coordinate of smallest enclosing circle shape is determined, this center of circle pixel coordinate is side elevation image spy Point R pixel coordinate (u1, v1) is levied, side elevation image characteristic point R pixel coordinates (u1, v1) are transferred to by the first industrial camera afterwards Weight data and side elevation image characteristic point R pixel coordinates (u1, v1) are transferred to second by signal processing system, signal processing system Industrial camera；
Step 4, after the second industrial camera receives weight data and side elevation image characteristic point R pixel coordinates (u1, v1), The overhead view image of the second industrial camera collection box for material circulation is triggered, specific workflow is as follows：
(1) second industrial camera is defaulted as small aperture pattern, and small aperture pattern can ensure that the brightness of image of collection is low, easily The pixel coordinate of laser spots is obtained in the later stage；LASER Light Source irradiates box for material circulation, and forms laser spots in the upper surface of box for material circulation；The Two industrial cameras gather the overhead view image F1 of first box for material circulation, and first carrying out binary conversion treatment to overhead view image F1 obtains top view Laser spots contours extract is carried out as F2, then to overhead view image F2, its smallest enclosing circle shape is taken after obtaining the profile of laser spots, and really Determine the center of circle pixel coordinate of smallest enclosing circle shape, this center of circle pixel coordinate be overhead view image characteristic point L pixel coordinates (u2, v2)；
(2) second industrial cameras are automatically converted to large aperture pattern, ensure that the brightness of image of collection is high, can clearly distinguish Box for material circulation and background；Second industrial camera gathers the overhead view image F2 of second box for material circulation, and carrying out edge to overhead view image F2 carries Overhead view image F3 is obtained, then contours extract is carried out to overhead view image F3 and in the multiple profiles extracted by judging profile Girth reject background impurities interference, finally obtain only include box for material circulation profile an overhead view image F4, now, if overhead view image Closed contour number is 0 in F4, then returns to error message to signal processing system, represent that box for material circulation is not fully located at first camera , it is necessary to put again in field range；Finally to its minimum enclosed rectangle of correct overhead view image F4 contours extract, and obtain Image length and width the data l and w of minimum enclosed rectangle；
Step 5, the second industrial camera carry out the three-dimensionalreconstruction algorithm of laser feature Point matching, and specific workflow is as follows：
(1), can by the first industrial camera in step 2 and the second industrial camera intrinsic parameter obtained by calibrating and outer parameter The corresponding relation established between laser feature point pixel coordinate (u, v) and three-dimensional world coordinate (X, Y, Z), i.e.,：
Wherein A is Intrinsic Matrix(R | T) it is outer parameter matrix, R is camera photocentre coordinate system phase For 3 × 3 spin matrixs of world coordinate system, T is 3 × 1 translation matrix of the camera photocentre coordinate system relative to world coordinate system；
First industrial camera and the second industrial camera intrinsic parameter obtained by calibrating in (2) second industrial camera obtaining steps two It is special using the side elevation image characteristic point R pixel coordinates (u1, v1) and overhead view image that are obtained in step 3 and step 4 with outer parameter Point L pixel coordinates (u2, v2) are levied, the relational expression substituted into respectively in step 5 (1), a pair of laser feature point pixels can be established and sat The equation group of mark and the three-dimensional world coordinate, world coordinates (X, Y, Z) is solved by least square method so as to reduce laser spy Actual position of the sign point in world coordinate system, completes the three-dimensionalreconstruction process of laser feature Point matching, wherein Z is box for material circulation Altitude information；
Step 6, the second industrial camera carry out the true length and width data of box for material circulation and calculated, the image obtained by step 4 (2) Length and width data l, w and the camera heights H and camera focus f measured in advance, according to the meter of similar triangles in optical imagery model Calculate formula：
Wherein pix represents long or wide number of pixels in image, and Δ represents pixel size, image length and width data l's or w It is focal length to be worth for its each self-corresponding pix* Δs, i.e. l=pix* Δs or w=pix* Δs, f, and H is camera away from measuring table height Degree, h are box for material circulation height, and so as to which the actual length and width information L and W of box for material circulation is calculated, then box for material circulation volume V is V=L*W* Z, by box for material circulation volume information transfer to signal processing system；
Step 7, the display screen of signal processing system show that box for material circulation volume and weight information, or display put mistake Prompt message.
The operation principle of the present invention：
During work, step 1, start binocular vision volume weight measuring system, the first industrial camera, the second industrial camera, LASER Light Source, Bluetooth electronic scale, LED bar graph light source and signal processing system are started working；
Step 2, carry out the mark of the intrinsic parameter of the first industrial camera and the second industrial camera, outer parameter and distortion factor It is fixed, and calibration result is sent to signal processing system, specific workflow is as follows：
(1) first industrial camera and the second industrial camera meet pinhole camera model, if image coordinate vector isWherein (u, v) is the pixel coordinate of target point；Camera Intrinsic Matrix isWherein fx,fy, cx,cyRespectively x is to focal length, and y is to focal length and optical axis center coordinate；Camera extrinsic matrix number is (R | T), and wherein R is camera photocentre For coordinate system relative to 3 × 3 spin matrixs of world coordinate system, T is camera photocentre coordinate system relative to the 3 × 1 of world coordinate system Translation matrix；World coordinates vector isWherein X, Y, Z are the world coordinates of target point；Camera imaging model meets Relational expression：
Wherein zcFor scale factor；In addition, camera distortion model meets following relation：
Wherein, (x, y) be distortion rectification before image physical coordinates, (xcor,ycor) be distortion rectification after image physics Coordinate, r=x2+y2,k1,k2,k3,p1,p2For 3 coefficient of radial distortion and 2 tangential distortion coefficients of camera；
First industrial camera and the purpose of the second industrial camera demarcation are to solve camera intrinsic parameter, outer parameter and distortion Number, is set to zero plane, using Zhang Zhengyou chessboard plane reference methods, by the position and the angle shot that change chessboard by measuring table 20 images, the demarcation of camera is carried out, and solve and obtain camera intrinsic parameter, outer parameter and distortion factor；
Step 3, box for material circulation is placed on measuring table, LASER Light Source irradiation box for material circulation, and in the upper surface shape of box for material circulation Into laser spots, Bluetooth electronic scale detects the weight of box for material circulation, and when the data stabilization of Bluetooth electronic scale, record box for material circulation weight is simultaneously Data are transferred to signal processing system by the bluetooth module on electronic scale, signal processing system transmits weight data afterwards To the first industrial camera and the side elevation image C1 of its collection box for material circulation is triggered, the first industrial camera is defaulted as small aperture pattern, this Sample can ensure that the brightness of image of collection is low, be easy to extraction of the later stage to laser spots in image；Two first are carried out to side elevation image C1 Value handles to obtain side elevation image C2, then carries out laser spots contours extract to side elevation image C2, is taken after obtaining the profile of laser spots Its smallest enclosing circle shape, and the center of circle pixel coordinate of smallest enclosing circle shape is determined, this center of circle pixel coordinate is side elevation image spy Point R pixel coordinate (u1, v1) is levied, side elevation image characteristic point R pixel coordinates (u1, v1) are transferred to by the first industrial camera afterwards Weight data and side elevation image characteristic point R pixel coordinates (u1, v1) are transferred to second by signal processing system, signal processing system Industrial camera；
Step 4, after the second industrial camera receives weight data and side elevation image characteristic point R pixel coordinates (u1, v1), The overhead view image of the second industrial camera collection box for material circulation is triggered, specific workflow is as follows：
(1) second industrial camera is defaulted as small aperture pattern, and small aperture pattern can ensure that the brightness of image of collection is low, easily The pixel coordinate of laser spots is obtained in the later stage；LASER Light Source irradiates box for material circulation, and forms laser spots in the upper surface of box for material circulation；The Two industrial cameras gather the overhead view image F1 of first box for material circulation, and first carrying out binary conversion treatment to overhead view image F1 obtains top view Laser spots contours extract is carried out as F2, then to overhead view image F2, its smallest enclosing circle shape is taken after obtaining the profile of laser spots, and really Determine the center of circle pixel coordinate of smallest enclosing circle shape, this center of circle pixel coordinate be overhead view image characteristic point L pixel coordinates (u2, v2)；
(2) second industrial cameras are automatically converted to large aperture pattern, ensure that the brightness of image of collection is high, can clearly distinguish Box for material circulation and background；Second industrial camera gathers the overhead view image F2 of second box for material circulation, and carrying out edge to overhead view image F2 carries Overhead view image F3 is obtained, then contours extract is carried out to overhead view image F3 and in the multiple profiles extracted by judging profile Girth reject background impurities interference, finally obtain only include box for material circulation profile an overhead view image F4, now, if overhead view image Closed contour number is 0 in F4, then returns to error message to signal processing system, represent that box for material circulation is not fully located at first camera , it is necessary to put again in field range；Finally to its minimum enclosed rectangle of correct overhead view image F4 contours extract, and obtain Image length and width the data l and w of minimum enclosed rectangle；
Step 5, the second industrial camera carry out the three-dimensionalreconstruction algorithm of laser feature Point matching, and specific workflow is as follows：
(1), can by the first industrial camera in step 2 and the second industrial camera intrinsic parameter obtained by calibrating and outer parameter The corresponding relation established between laser feature point pixel coordinate (u, v) and three-dimensional world coordinate (X, Y, Z), i.e.,：
Wherein A is Intrinsic Matrix(R | T) it is outer parameter matrix, R is camera photocentre coordinate system phase For 3 × 3 spin matrixs of world coordinate system, T is 3 × 1 translation matrix of the camera photocentre coordinate system relative to world coordinate system；
First industrial camera and the second industrial camera intrinsic parameter obtained by calibrating in (2) second industrial camera obtaining steps two It is special using the side elevation image characteristic point R pixel coordinates (u1, v1) and overhead view image that are obtained in step 3 and step 4 with outer parameter Point L pixel coordinates (u2, v2) are levied, the relational expression substituted into respectively in step 5 (1), a pair of laser feature point pixels can be established and sat The equation group of mark and the three-dimensional world coordinate, world coordinates (X, Y, Z) is solved by least square method so as to reduce laser spy Actual position of the sign point in world coordinate system, completes the three-dimensionalreconstruction process of laser feature Point matching, wherein Z is box for material circulation Altitude information；
Step 6, the second industrial camera carry out the true length and width data of box for material circulation and calculated, the image obtained by step 4 (2) Length and width data l, w and the camera heights H and camera focus f measured in advance, according to the meter of similar triangles in optical imagery model Calculate formula：
Wherein pix represents long or wide number of pixels in image, and Δ represents pixel size, image length and width data l's or w It is focal length to be worth for its each self-corresponding pix* Δs, i.e. l=pix* Δs or w=pix* Δs, f, and H is camera away from measuring table height Degree, h are box for material circulation height, and so as to which the actual length and width information L and W of box for material circulation is calculated, then box for material circulation volume V is V=L*W* Z, by box for material circulation volume information transfer to signal processing system；
Step 7, the display screen of signal processing system show that box for material circulation volume and weight information, or display put mistake Prompt message.
The present invention has following beneficial effect compared with prior art：
(1) present invention has quick, accurate, non-contact and cost cheap compared to traditional artificial tape measure mode Etc. advantage, suitable for the automatic measurement of batch, cost of labor is greatly reduced, improves production efficiency；
(2) present invention fully relies on vision technique can and realizes object without using traditional laser ranging module Length and width high measurement, closely, in the measuring environment of small size, binocular vision 3 D reconfiguration technique is than laser ranging technique precision Higher, cost is lower；
(3) compared to being related in general three-dimensionalreconstruction Feature Points Matching by illumination, texture, optical distortion and noise etc. The problem of factor influences, the algorithm for the LASER Light Source guiding Stereo matching that the present invention uses, greatly reduces Feature Points Matching Difficulty, error hiding is reduced, leak the problems such as matching, improve the stability and reliability of system.
Brief description of the drawings
Fig. 1 is the overall structure diagram of the present invention；
Fig. 2 is the system structure diagram of the present invention；
Fig. 3 is the three-dimensionalreconstruction algorithm flow chart of the present invention；
The box for material circulation length and width that Fig. 4 is the present invention calculate schematic diagram.
Reference is in figure：1st, the first industrial camera；2nd, signal processing system；3rd, LED bar graph light source；4th, Bluetooth electronic Scale；5th, measuring table；6th, the second industrial camera；7th, LASER Light Source；8th, laser spots；9th, box for material circulation.
Embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are unlimited In this.
As shown in figures 1-4, a kind of binocular vision volume weight measuring system, including Installation cabinet, and it is arranged on the peace The first industrial camera 1, the second industrial camera 6 in dress cabinet, LASER Light Source 7, LED bar graph light source 3, signal processing system 2, measurement Platform 5 and Bluetooth electronic scale 4, wherein, the measuring table 5 is arranged on the bottom of the Installation cabinet, and the measuring table 5 passes through Paint and be polished into black smooth surface, so setting can ensure that the disengaging measuring table 5 of box for material circulation 9 is steadily smooth, and can Reduce the ambient interferences in image processing process；The Bluetooth electronic scale 4 is arranged on the lower section of the measuring table 5；Described Two industrial cameras 6 are arranged on the top of the Installation cabinet, and the LASER Light Source 7 is arranged side by side with second industrial camera 6, and The shooting direction keeping parallelism of the radiation direction of the LASER Light Source 7 and second industrial camera 6；Second industrial camera 6 and the LASER Light Source 7 be arranged on the surface of the measuring table 5, and the shooting direction of second industrial camera 6 and institute The radiation direction of LASER Light Source 7 is stated all both perpendicular to the measuring table 5；First industrial camera 1 is arranged on the peace The top of cabinet is filled, first industrial camera 1 is located at the oblique upper of the measuring table 5, and first industrial camera 1 and institute Measuring table 5 is stated to set in 45 degree of overturning angles；The industrial camera 6 of first industrial camera 1 and second shoots the measuring table 5 Field range it is identical；The LED bar graph light source 3 is provided with four, and two of which LED bar graph light source 3 is horizontally set on described the The front and rear sides of two industrial cameras 6, two other LED bar graph light source 3 are vertically arranged in front and rear the two of first industrial camera 1 Side, the setting of these LED bar graph light sources 3 can realize that uniform polishing obtains for the first industrial camera 1 and the second industrial camera 6 Qualitative picture；First industrial camera 1, the second industrial camera 6, LASER Light Source 7 and Bluetooth electronic scale 4 respectively with the signal Processing system 2 is connected；The signal processing system 2 is provided with display screen.
Binocular stereo vision is one of key technology of computer vision, be based on principle of parallax and using imaging device from The two images of different position acquisition testees, by calculating the position deviation between image corresponding points, to obtain object three The method for tieing up geological information, and the measuring method of computer vision is utilized, do not influenceed by artifact, precision is not marked by measurement The limitation of the object of reference precision such as chi, compared to traditional artificial tape measure, have quick, accurate, non-contact and cost cheap Etc. advantage, suitable for the automatic measurement of batch, cost of labor is greatly reduced, improves production efficiency.It is proposed by the present invention double Visually feel that e measurement technology has that efficiency high, precision are suitable, system architecture is simple, low cost and other advantages, be very suitable for manufacture and show Online, the non-contact Product checking of field and quality control.
During work, step 1, start binocular vision volume weight measuring system, the first industrial camera 1, the second industrial camera 6th, LASER Light Source 7, Bluetooth electronic scale 4, LED bar graph light source 3 and signal processing system 2 are started working；
Step 2, carry out the intrinsic parameter of the first industrial camera 1 and the second industrial camera 6, outer parameter and distortion factor Demarcation, and calibration result is sent to signal processing system 2, specific workflow is as follows：
(1) first industrial camera 1 and the second industrial camera 6 meet pinhole camera model, if image coordinate vector isWherein (u, v) is the pixel coordinate of target point；Camera Intrinsic Matrix isWherein fx,fy, cx,cyRespectively x is to focal length, and y is to focal length and optical axis center coordinate；Camera extrinsic matrix number is (R | T), and wherein R is camera photocentre For coordinate system relative to 3 × 3 spin matrixs of world coordinate system, T is camera photocentre coordinate system relative to the 3 × 1 of world coordinate system Translation matrix；World coordinates vector isWherein X, Y, Z are the world coordinates of target point；
Camera imaging model meets relational expression：
Wherein zcFor scale factor；In addition, camera distortion model meets following relation：
Wherein, (x, y) be distortion rectification before image physical coordinates, (xcor,ycor) be distortion rectification after image physics Coordinate, r=x2+y2,k1,k2,k3,p1,p2For 3 coefficient of radial distortion and 2 tangential distortion coefficients of camera；
First industrial camera 1 and the purpose of the second industrial camera 6 demarcation are to solve camera intrinsic parameter, outer parameter and distortion Number, zero plane is set to by measuring table 5, using Zhang Zhengyou chessboard plane reference methods, is clapped by the position and angle that change chessboard 20 images are taken the photograph, carry out the demarcation of camera, and solve and obtain camera intrinsic parameter, outer parameter and distortion factor；
Step 3, box for material circulation 9 being placed on measuring table 5, LASER Light Source 7 irradiates box for material circulation 9, and in the upper of box for material circulation 9 Surface forms laser spots 8, and Bluetooth electronic scale 4 detects the weight of box for material circulation 9, when the data stabilization of Bluetooth electronic scale 4, records thing Data are simultaneously transferred to signal processing system 2 by the stream weight of case 9 by the bluetooth module on electronic scale, afterwards signal processing system 2 Weight data is transferred to the first industrial camera 1 and triggers it and gathers the side elevation image C1 of box for material circulation 9, the first industrial camera 1 is silent Think small aperture pattern, can so ensure that the brightness of image of collection is low, be easy to extraction of the later stage to laser spots in image 8；First Binary conversion treatment is carried out to side elevation image C1 and obtains side elevation image C2, then the contours extract of laser spots 8 is carried out to side elevation image C2, is obtained Its smallest enclosing circle shape is taken after obtaining the profile of laser spots 8, and determines the center of circle pixel coordinate of smallest enclosing circle shape, this center of circle pixel Coordinate is side elevation image characteristic point R pixel coordinate (u1, v1), and the first industrial camera 1 is by side elevation image characteristic point R pictures afterwards Plain coordinate (u1, v1) is transferred to signal processing system 2, and signal processing system 2 is by weight data and side elevation image characteristic point R pixels Coordinate (u1, v1) is transferred to the second industrial camera 6；
Step 4, after the second industrial camera 6 receives weight data and side elevation image characteristic point R pixel coordinates (u1, v1), The overhead view image of the second industrial camera 6 collection box for material circulation 9 is triggered, specific workflow is as follows：
(1) second industrial camera 6 is defaulted as small aperture pattern, and small aperture pattern can ensure that the brightness of image of collection is low, It is easy to the pixel coordinate of later stage acquisition laser spots 8；LASER Light Source 7 irradiates box for material circulation 9, and is formed in the upper surface of box for material circulation 9 sharp Luminous point 8；Second industrial camera 6 gathers the overhead view image F1 of first box for material circulation 9, first carries out binary conversion treatment to overhead view image F1 Overhead view image F2 is obtained, then the contours extract of laser spots 8 is carried out to overhead view image F2, takes it minimum after obtaining the profile of laser spots 8 Circle is surrounded, and determines the center of circle pixel coordinate of smallest enclosing circle shape, this center of circle pixel coordinate is overhead view image characteristic point L pictures Plain coordinate (u2, v2)；
(2) second industrial cameras 6 are automatically converted to large aperture pattern, ensure that the brightness of image of collection is high, can clearly distinguish Effluent stream case 9 and background；Second industrial camera 6 gathers the overhead view image F2 of second box for material circulation 9, and side is carried out to overhead view image F2 Edge extracts to obtain overhead view image F3, then carries out contours extract to overhead view image F3 and pass through judgement in the multiple profiles extracted The girth of profile rejects the interference of background impurities, the overhead view image F4 for only including the profile of box for material circulation 9 is finally obtained, now, if bowing Closed contour number is 0 in visible image F4, then returns to error message to signal processing system 2, represent that box for material circulation 9 is not fully located at , it is necessary to put again in first camera field range；Finally to its minimum external square of correct overhead view image F4 contours extract Shape, and obtain image length and width the data l and w of minimum enclosed rectangle；
Step 5, the second industrial camera 6 carry out the three-dimensionalreconstruction algorithm of laser feature Point matching, and specific workflow is such as Under：
(1) by the first industrial camera 1 in step 2 and 6 intrinsic parameter obtained by calibrating of the second industrial camera and outer parameter, The corresponding relation that can be established between laser feature point pixel coordinate (u, v) and three-dimensional world coordinate (X, Y, Z), i.e.,：
Wherein A is Intrinsic Matrix(R | T) it is outer parameter matrix, R is camera photocentre coordinate system phase For 3 × 3 spin matrixs of world coordinate system, T is 3 × 1 translation matrix of the camera photocentre coordinate system relative to world coordinate system；
First industrial camera 1 and the second industrial camera 6 are obtained by calibrating interior in the obtaining step two of (2) second industrial camera 6 Parameter and outer parameter, utilize the side elevation image characteristic point R pixel coordinates (u1, v1) and top view obtained in step 3 and step 4 As characteristic point L pixel coordinates (u2, v2), the relational expression substituted into respectively in step 5 (1), a pair of laser feature point pictures can be established The equation group of plain coordinate and the three-dimensional world coordinate, it is sharp so as to reduce to solve world coordinates (X, Y, Z) by least square method Actual position of the light characteristic point in world coordinate system, the three-dimensionalreconstruction process of laser feature Point matching is completed, wherein Z is thing Flow the altitude information of case 9；
Step 6, the second industrial camera 6 carry out the true length and width data of box for material circulation 9 and calculated, the figure obtained by step 4 (2) As length and width data l, w and the camera heights H and camera focus f that measure in advance, according to similar triangles in optical imagery model Calculation formula：
Wherein pix represents long or wide number of pixels in image, and Δ represents pixel size, image length and width data l's or w It is focal length to be worth for its each self-corresponding pix* Δs, i.e. l=pix* Δs or w=pix* Δs, f, and H is that camera is high away from measuring table 5 Degree, h are the height of box for material circulation 9, and so as to which the actual length and width information L and W of box for material circulation 9 is calculated, then the volume V of box for material circulation 9 is V=L* W*Z, the volume information of box for material circulation 9 is transferred to signal processing system 2；
Step 7, the display screen of signal processing system 2 show that the volume of box for material circulation 9 and weight information, or display put mistake Prompt message by mistake.
The present invention has quick, accurate, non-contact and cost cheap etc. excellent compared to traditional artificial tape measure mode Gesture, suitable for the automatic measurement of batch, cost of labor is greatly reduced, improves production efficiency；Without using traditional laser Range finder module, the length and width high measurement that vision technique can realizes object is fully relied on, closely, the measuring environment of small size In, binocular vision 3 D reconfiguration technique is higher than laser ranging technique precision, and cost is lower；Compared to general three-dimensionalreconstruction feature Be related in Point matching by illumination, texture, the problem of factor such as optical distortion and noise influences, the laser light that the present invention uses The problems such as source guides the algorithm of Stereo matching, greatly reduces the difficulty of Feature Points Matching, reduces error hiding, and leakage matches, carries The high stability and reliability of system.
Above-mentioned is the preferable embodiment of the present invention, but embodiments of the present invention are not limited by the above, its His any Spirit Essence without departing from the present invention with made under principle change, modification, replacement, combine, simplification, should be The substitute mode of effect, is included within protection scope of the present invention.

Claims (3)

1. a kind of binocular vision volume weight measuring system, it is characterised in that including Installation cabinet, and be arranged on the Installation cabinet Interior the first industrial camera, the second industrial camera, LASER Light Source, LED bar graph light source, signal processing system, measuring table and indigo plant Tooth electronic scale, wherein, the measuring table is arranged on the bottom of the Installation cabinet, and the Bluetooth electronic scale is arranged on the measurement The lower section of platform；Second industrial camera is arranged on the top of the Installation cabinet, the LASER Light Source and the described second industry Camera is arranged side by side, and the shooting direction keeping parallelism of the radiation direction of the LASER Light Source and second industrial camera；Institute State the second industrial camera and the LASER Light Source is arranged on the surface of the measuring table, and the bat of second industrial camera The radiation direction of direction and the LASER Light Source is taken the photograph all both perpendicular to the measuring table；First industrial camera is arranged on The top of the Installation cabinet, first industrial camera are located at the oblique upper of the measuring table, and first industrial camera Set with the measuring table in 45 degree of overturning angles；First industrial camera and the second industrial camera shoot the measuring table Field range it is identical；The LED bar graph light source is provided with four, and two of which LED bar graph light source levels are arranged on described second The front and rear sides of industrial camera, two other LED bar graph light source are vertically arranged in the front and rear sides of first industrial camera；
First industrial camera, the second industrial camera, LASER Light Source and Bluetooth electronic scale respectively with the signal processing system It is connected；The signal processing system is provided with display screen.
2. binocular vision volume weight measuring system according to claim 1, it is characterised in that the measuring table passes through Paint and be polished into black smooth surface.
3. a kind of implementation method by any one of the claim 1~2 binocular vision volume weight measuring system, its feature exists In comprising the steps：
Step 1, start binocular vision volume weight measuring system, the first industrial camera, the second industrial camera, LASER Light Source, indigo plant Tooth electronic scale, LED bar graph light source and signal processing system are started working；
Step 2, the demarcation of the intrinsic parameter of the first industrial camera and the second industrial camera, outer parameter and distortion factor is carried out, and Calibration result is sent to signal processing system, specific workflow is as follows：
(1) first industrial camera and the second industrial camera meet pinhole camera model, if image coordinate vector isIts In (u, v) be target point pixel coordinate；Camera Intrinsic Matrix isWherein fx,fy,cx,cyRespectively X is to focal length, and y is to focal length and optical axis center coordinate；Camera extrinsic matrix number is (R | T), and wherein R is that camera photocentre coordinate system is relative In 3 × 3 spin matrixs of world coordinate system, T is 3 × 1 translation matrix of the camera photocentre coordinate system relative to world coordinate system；Generation Boundary's coordinate vector isWherein X, Y, Z are the world coordinates of target point；Camera imaging model meets relational expression：
<mrow> <msup> <mi>m</mi> <mo>&amp;prime;</mo> </msup> <mo>=</mo> <mfrac> <mn>1</mn> <msub> <mi>z</mi> <mi>c</mi> </msub> </mfrac> <mi>A</mi> <mrow> <mo>(</mo> <mi>R</mi> <mo>|</mo> <mi>T</mi> <mo>)</mo> </mrow> <msup> <mi>M</mi> <mo>&amp;prime;</mo> </msup> <mo>,</mo> </mrow>
Wherein zcFor scale factor；In addition, camera distortion model meets following relation：
<mrow> <mfenced open = "(" close = ")"> <mtable> <mtr> <mtd> <msub> <mi>x</mi> <mrow> <mi>c</mi> <mi>o</mi> <mi>r</mi> </mrow> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>y</mi> <mrow> <mi>c</mi> <mi>o</mi> <mi>r</mi> </mrow> </msub> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>+</mo> <msub> <mi>k</mi> <mn>1</mn> </msub> <msup> <mi>r</mi> <mn>2</mn> </msup> <mo>+</mo> <msub> <mi>k</mi> <mn>2</mn> </msub> <msup> <mi>r</mi> <mn>4</mn> </msup> <mo>+</mo> <msub> <mi>k</mi> <mn>3</mn> </msub> <msup> <mi>r</mi> <mn>6</mn> </msup> <mo>)</mo> </mrow> <mfenced open = "(" close = ")"> <mtable> <mtr> <mtd> <mi>x</mi> </mtd> </mtr> <mtr> <mtd> <mi>y</mi> </mtd> </mtr> </mtable> </mfenced> <mo>+</mo> <mfenced open = "(" close = ")"> <mtable> <mtr> <mtd> <mn>2</mn> <msub> <mi>p</mi> <mn>1</mn> </msub> <mi>x</mi> <mi>y</mi> <mo>+</mo> <msub> <mi>p</mi> <mn>2</mn> </msub> <mo>(</mo> <msup> <mi>r</mi> <mn>2</mn> </msup> <mo>+</mo> <mn>2</mn> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> </mtd> </mtr> <mtr> <mtd> <msub> <mi>p</mi> <mn>1</mn> </msub> <mo>(</mo> <msup> <mi>r</mi> <mn>2</mn> </msup> <mo>+</mo> <mn>2</mn> <msup> <mi>y</mi> <mn>2</mn> </msup> <mo>)</mo> <mo>+</mo> <mn>2</mn> <msub> <mi>p</mi> <mn>2</mn> </msub> <mi>x</mi> <mi>y</mi> </mtd> </mtr> </mtable> </mfenced> <mo>,</mo> </mrow>
Wherein, (x, y) be distortion rectification before image physical coordinates, (xcor,ycor) be distortion rectification after image physical coordinates, R=x2+y2,k1,k2,k3,p1,p2For 3 coefficient of radial distortion and 2 tangential distortion coefficients of camera；
First industrial camera and the purpose of the second industrial camera demarcation, will to solve camera intrinsic parameter, outer parameter and distortion factor Measuring table is set to zero plane, using Zhang Zhengyou chessboard plane reference methods, is opened by the position and angle shot 20 that change chessboard Image, the demarcation of camera is carried out, and solve and obtain camera intrinsic parameter, outer parameter and distortion factor；
Step 3, box for material circulation is placed on measuring table, LASER Light Source irradiation box for material circulation, and formed in the upper surface of box for material circulation sharp Luminous point, Bluetooth electronic scale detects the weight of box for material circulation, when the data stabilization of Bluetooth electronic scale, records box for material circulation weight and by number Signal processing system is transferred to according to by the bluetooth module on electronic scale, weight data is transferred to by signal processing system afterwards One industrial camera and the side elevation image C1 for triggering its collection box for material circulation, the first industrial camera are defaulted as small aperture pattern, such energy The brightness of image of enough guarantee collections is low, is easy to extraction of the later stage to laser spots in image；Binaryzation first is carried out to side elevation image C1 Processing obtains side elevation image C2, then carries out laser spots contours extract to side elevation image C2, and it is taken most after obtaining the profile of laser spots It is small to surround circle, and the center of circle pixel coordinate of smallest enclosing circle shape is determined, this center of circle pixel coordinate is side elevation image characteristic point R Pixel coordinate (u1, v1), afterwards the first industrial camera side elevation image characteristic point R pixel coordinates (u1, v1) are transferred to signal Weight data and side elevation image characteristic point R pixel coordinates (u1, v1) are transferred to the second industry by processing system, signal processing system Camera；
Step 4, after the second industrial camera receives weight data and side elevation image characteristic point R pixel coordinates (u1, v1), triggering Second industrial camera gathers the overhead view image of box for material circulation, and specific workflow is as follows：
(1) second industrial camera is defaulted as small aperture pattern, and small aperture pattern can ensure that the brightness of image of collection is low, after being easy to Phase obtains the pixel coordinate of laser spots；LASER Light Source irradiates box for material circulation, and forms laser spots in the upper surface of box for material circulation；Second work Industry camera gathers the overhead view image F1 of first box for material circulation, and first carrying out binary conversion treatment to overhead view image F1 obtains overhead view image F2, then laser spots contours extract is carried out to overhead view image F2, its smallest enclosing circle shape is taken after obtaining the profile of laser spots, and determine The center of circle pixel coordinate of smallest enclosing circle shape, this center of circle pixel coordinate are overhead view image characteristic point L pixel coordinates (u2, v2)；
(2) second industrial cameras are automatically converted to large aperture pattern, ensure that the brightness of image of collection is high, can circle of good definition separate logistics Case and background；Second industrial camera gathers the overhead view image F2 of second box for material circulation, and carrying out edge extracting to overhead view image F2 obtains To overhead view image F3, then contours extract is carried out to overhead view image F3 and in the multiple profiles extracted by judging week of profile The long interference for rejecting background impurities, finally obtains the overhead view image F4 for only including box for material circulation profile, now, if in overhead view image F4 Closed contour number is 0, then returns to error message to signal processing system, represent that box for material circulation is not fully located at first camera visual field In the range of, it is necessary to put again；Finally to its minimum enclosed rectangle of correct overhead view image F4 contours extract, and obtain minimum Image length and width the data l and w of boundary rectangle；
Step 5, the second industrial camera carry out the three-dimensionalreconstruction algorithm of laser feature Point matching, and specific workflow is as follows：
(1) by the first industrial camera in step 2 and the second industrial camera intrinsic parameter obtained by calibrating and outer parameter, can establish Corresponding relation between laser feature point pixel coordinate (u, v) and three-dimensional world coordinate (X, Y, Z), i.e.,：
<mrow> <mi>Z</mi> <mi>c</mi> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mi>u</mi> </mtd> </mtr> <mtr> <mtd> <mi>v</mi> </mtd> </mtr> <mtr> <mtd> <mn>1</mn> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mi>A</mi> <mrow> <mo>(</mo> <mi>R</mi> <mo>|</mo> <mi>T</mi> <mo>)</mo> </mrow> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mi>X</mi> </mtd> </mtr> <mtr> <mtd> <mi>Y</mi> </mtd> </mtr> <mtr> <mtd> <mi>Z</mi> </mtd> </mtr> <mtr> <mtd> <mn>1</mn> </mtd> </mtr> </mtable> </mfenced> <mo>,</mo> </mrow>
Wherein A is Intrinsic Matrix(R | T) is outer parameter matrix, R be camera photocentre coordinate system relative to 3 × 3 spin matrixs of world coordinate system, T are 3 × 1 translation matrix of the camera photocentre coordinate system relative to world coordinate system；
First industrial camera and the second industrial camera intrinsic parameter obtained by calibrating and outer in (2) second industrial camera obtaining steps two Parameter, utilize the side elevation image characteristic point R pixel coordinates (u1, v1) and overhead view image characteristic point obtained in step 3 and step 4 L pixel coordinates (u2, v2), the relational expression substituted into respectively in step 5 (1), can establish a pair of laser feature point pixel coordinates and The equation group of the three-dimensional world coordinate, world coordinates (X, Y, Z) is solved by least square method so as to reduce laser feature point Actual position in world coordinate system, the three-dimensionalreconstruction process of laser feature Point matching is completed, wherein Z is the height of box for material circulation Degrees of data；
Step 6, the second industrial camera carry out the true length and width data of box for material circulation and calculated, the image length and width obtained by step 4 (2) Data l, w and the camera heights H and camera focus f measured in advance, it is public according to the calculating of similar triangles in optical imagery model Formula：
<mrow> <mfrac> <mrow> <mi>p</mi> <mi>i</mi> <mi>x</mi> <mo>*</mo> <mi>&amp;Delta;</mi> </mrow> <mrow> <mi>L</mi> <mrow> <mo>(</mo> <mi>W</mi> <mo>)</mo> </mrow> </mrow> </mfrac> <mo>=</mo> <mfrac> <mi>f</mi> <mrow> <mi>H</mi> <mo>-</mo> <mi>h</mi> </mrow> </mfrac> <mo>,</mo> </mrow>
Wherein pix represents long or wide number of pixels in image, and Δ represents pixel size, and image length and width data l or w value are Its each self-corresponding pix* Δs, i.e. l=pix* Δs or w=pix* Δs, f are focal length, and H is that camera is away from measuring table height, h Box for material circulation height, so as to which the actual length and width information L and W of box for material circulation is calculated, then box for material circulation volume V is V=L*W*Z, by thing Flow casing and accumulate information transfer to signal processing system；
Step 7, the display screen of signal processing system show that box for material circulation volume and weight information, or display put carrying for mistake Show information.
CN201710994098.0A 2017-10-23 2017-10-23 Binocular vision volume weight measurement system and implementation method thereof Active CN107869954B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710994098.0A CN107869954B (en) 2017-10-23 2017-10-23 Binocular vision volume weight measurement system and implementation method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710994098.0A CN107869954B (en) 2017-10-23 2017-10-23 Binocular vision volume weight measurement system and implementation method thereof

Publications (2)

Publication Number Publication Date
CN107869954A true CN107869954A (en) 2018-04-03
CN107869954B CN107869954B (en) 2023-05-16

Family

ID=61752504

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710994098.0A Active CN107869954B (en) 2017-10-23 2017-10-23 Binocular vision volume weight measurement system and implementation method thereof

Country Status (1)

Country Link
CN (1) CN107869954B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109000563A (en) * 2018-07-19 2018-12-14 工极（北京）智能科技有限公司 Intelligent three-dimensional stereometer type instrument based on monocular cam combination
CN110558988A (en) * 2018-06-05 2019-12-13 北京远见医疗技术发展有限责任公司 head and face whole body parameter measuring method and equipment
CN110751620A (en) * 2019-08-28 2020-02-04 宁波海上鲜信息技术有限公司 Method for estimating volume and weight, electronic device, and computer-readable storage medium
CN111307659A (en) * 2020-03-11 2020-06-19 河南理工大学 Rapid density measuring system for irregular rigid object
CN111595264A (en) * 2020-05-29 2020-08-28 广西玉柴机器股份有限公司 Method for digital rapid detection and analysis of sand core
CN114313748A (en) * 2022-01-29 2022-04-12 浙江凯乐士科技集团股份有限公司 Automatic warehousing system
CN114985304A (en) * 2022-05-25 2022-09-02 杭州电子科技大学 Waste television specification detection method based on machine vision
CN115035201A (en) * 2022-06-06 2022-09-09 易麦斯智能科技(无锡)有限公司 Automatic shoelace threading method and system based on 3D vision

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101266131A (en) * 2008-04-08 2008-09-17 长安大学 Volume measurement device based on image and its measurement method
CN102063718A (en) * 2010-12-24 2011-05-18 江南大学 Field calibration and precision measurement method for spot laser measuring system
US20120218437A1 (en) * 2009-10-17 2012-08-30 Alexander Thomas Hermary Enhanced imaging method and apparatus
CN102679915A (en) * 2012-05-24 2012-09-19 河北工业大学 Method and system for measuring volumes and weights of continuously conveyed long objects based on optical measurement
CN202853580U (en) * 2012-08-28 2013-04-03 成都志诚弘毅科技有限公司 Apparatus for dynamic measurement of vehicle outer contour dimension and weight
CN104457569A (en) * 2014-11-27 2015-03-25 大连理工大学 Geometric parameter visual measurement method for large composite board
CN104457574A (en) * 2014-12-11 2015-03-25 天津大学 Device for measuring volume of irregular object in non-contact measurement mode and method
CN104655249A (en) * 2015-03-16 2015-05-27 武汉大学 System and method for automatically measuring dimension and weight of road vehicle
CN104897060A (en) * 2015-06-17 2015-09-09 大连理工大学 large Large field of view global measurement method using coordinates tracking control board
CN204630950U (en) * 2015-05-29 2015-09-09 杭州利珀科技有限公司 A kind of crown cap defect intelligent detection equipment
CN106052820A (en) * 2016-06-03 2016-10-26 广州市中崎商业机器股份有限公司 Logistic freight automatic calculating system and method
US20170154436A1 (en) * 2015-05-27 2017-06-01 Zhuhai Ritech Technology Co. Ltd. Stereoscopic vision three dimensional measurement method and system for calculating laser speckle as texture
CN106839975A (en) * 2015-12-03 2017-06-13 杭州海康威视数字技术股份有限公司 Volume measuring method and its system based on depth camera
CN107255498A (en) * 2017-06-02 2017-10-17 西安理工大学 Conveyer belt weight of material measuring system and measuring method based on binocular vision

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101266131A (en) * 2008-04-08 2008-09-17 长安大学 Volume measurement device based on image and its measurement method
US20120218437A1 (en) * 2009-10-17 2012-08-30 Alexander Thomas Hermary Enhanced imaging method and apparatus
CN102063718A (en) * 2010-12-24 2011-05-18 江南大学 Field calibration and precision measurement method for spot laser measuring system
CN102679915A (en) * 2012-05-24 2012-09-19 河北工业大学 Method and system for measuring volumes and weights of continuously conveyed long objects based on optical measurement
CN202853580U (en) * 2012-08-28 2013-04-03 成都志诚弘毅科技有限公司 Apparatus for dynamic measurement of vehicle outer contour dimension and weight
CN104457569A (en) * 2014-11-27 2015-03-25 大连理工大学 Geometric parameter visual measurement method for large composite board
CN104457574A (en) * 2014-12-11 2015-03-25 天津大学 Device for measuring volume of irregular object in non-contact measurement mode and method
CN104655249A (en) * 2015-03-16 2015-05-27 武汉大学 System and method for automatically measuring dimension and weight of road vehicle
US20170154436A1 (en) * 2015-05-27 2017-06-01 Zhuhai Ritech Technology Co. Ltd. Stereoscopic vision three dimensional measurement method and system for calculating laser speckle as texture
CN204630950U (en) * 2015-05-29 2015-09-09 杭州利珀科技有限公司 A kind of crown cap defect intelligent detection equipment
CN104897060A (en) * 2015-06-17 2015-09-09 大连理工大学 large Large field of view global measurement method using coordinates tracking control board
CN106839975A (en) * 2015-12-03 2017-06-13 杭州海康威视数字技术股份有限公司 Volume measuring method and its system based on depth camera
CN106052820A (en) * 2016-06-03 2016-10-26 广州市中崎商业机器股份有限公司 Logistic freight automatic calculating system and method
CN107255498A (en) * 2017-06-02 2017-10-17 西安理工大学 Conveyer belt weight of material measuring system and measuring method based on binocular vision

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
CHANG WANG等: "Design of Dynamic Volume Measure System Based on Binocular Vision" *
QIONG LIU等: "Structural Parameters Optimal Design and Accuracy Analysis for Binocular Vision Measure System" *
毛佳红等: "基于线结构光的双目三维体积测量系统" *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110558988A (en) * 2018-06-05 2019-12-13 北京远见医疗技术发展有限责任公司 head and face whole body parameter measuring method and equipment
CN109000563A (en) * 2018-07-19 2018-12-14 工极（北京）智能科技有限公司 Intelligent three-dimensional stereometer type instrument based on monocular cam combination
CN109000563B (en) * 2018-07-19 2024-04-09 工极（北京）智能科技有限公司 Intelligent three-dimensional measuring instrument based on monocular camera combination
CN110751620A (en) * 2019-08-28 2020-02-04 宁波海上鲜信息技术有限公司 Method for estimating volume and weight, electronic device, and computer-readable storage medium
CN110751620B (en) * 2019-08-28 2021-03-16 宁波海上鲜信息技术有限公司 Method for estimating volume and weight, electronic device, and computer-readable storage medium
CN111307659A (en) * 2020-03-11 2020-06-19 河南理工大学 Rapid density measuring system for irregular rigid object
CN111595264A (en) * 2020-05-29 2020-08-28 广西玉柴机器股份有限公司 Method for digital rapid detection and analysis of sand core
CN114313748A (en) * 2022-01-29 2022-04-12 浙江凯乐士科技集团股份有限公司 Automatic warehousing system
CN114985304A (en) * 2022-05-25 2022-09-02 杭州电子科技大学 Waste television specification detection method based on machine vision
CN114985304B (en) * 2022-05-25 2023-10-13 杭州电子科技大学 Machine vision-based waste television specification detection method
CN115035201A (en) * 2022-06-06 2022-09-09 易麦斯智能科技(无锡)有限公司 Automatic shoelace threading method and system based on 3D vision
CN115035201B (en) * 2022-06-06 2023-09-29 易麦斯智能科技(无锡)有限公司 Automatic shoelace threading method and system based on 3D vision

Also Published As

Publication number Publication date
CN107869954B (en) 2023-05-16

Similar Documents

Publication Publication Date Title
CN107869954A (en) A kind of binocular vision volume weight measuring system and its implementation
CN106091984B (en) A kind of three dimensional point cloud acquisition methods based on line laser
CN107945268B (en) A kind of high-precision three-dimensional method for reconstructing and system based on binary area-structure light
CN105627926B (en) Four-camera group planar array feature point three-dimensional measurement system and measurement method
CN103411553B (en) The quick calibrating method of multi-linear structured light vision sensors
CN104331896B (en) A kind of system calibrating method based on depth information
CN104034263B (en) A kind of non-contact measurement method of forging&#39;s block dimension
CN104930985B (en) Binocular vision 3 D topography measurement method based on space-time restriction
CN104463899B (en) A kind of destination object detection, monitoring method and its device
CN106969706A (en) Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision
CN106485757A (en) A kind of Camera Calibration of Stereo Vision System platform based on filled circles scaling board and scaling method
CN109443209A (en) A kind of line-structured light system calibrating method based on homography matrix
CN107169475A (en) A kind of face three-dimensional point cloud optimized treatment method based on kinect cameras
CN106361345A (en) System and method for measuring height of human body in video image based on camera calibration
CN109859272A (en) A kind of auto-focusing binocular camera scaling method and device
CN109961485A (en) A method of target positioning is carried out based on monocular vision
CN106408556A (en) Minimal object measurement system calibration method based on general imaging model
CN107607053B (en) A kind of standing tree tree breast diameter survey method based on machine vision and three-dimensional reconstruction
CN107816943A (en) A kind of box for material circulation volume weight measuring system and its implementation
CN106340044A (en) Camera external parameter automatic calibration method and calibration device
CN103530880A (en) Camera calibration method based on projected Gaussian grid pattern
CN106091983A (en) Comprise the complete scaling method of Vision Measuring System With Structured Light Stripe of scanning direction information
CN110879080A (en) High-precision intelligent measuring instrument and measuring method for high-temperature forge piece
CN105043720B (en) The measuring method of infrared fileter refractive index based on single camera
CN106705849A (en) Calibration method of linear-structure optical sensor

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant