CN103868460A - Parallax optimization algorithm-based binocular stereo vision automatic measurement method - Google Patents

Parallax optimization algorithm-based binocular stereo vision automatic measurement method Download PDF

Info

Publication number
CN103868460A
CN103868460A CN201410094119.XA CN201410094119A CN103868460A CN 103868460 A CN103868460 A CN 103868460A CN 201410094119 A CN201410094119 A CN 201410094119A CN 103868460 A CN103868460 A CN 103868460A
Authority
CN
China
Prior art keywords
parallax
binocular
pixel
target object
coordinate
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
CN201410094119.XA
Other languages
Chinese (zh)
Other versions
CN103868460B (en
Inventor
首照宇
唐望平
莫建文
张彤
袁华
陈利霞
欧阳宁
赵晖
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.)
Guilin University of Electronic Technology
Original Assignee
Guilin University of Electronic 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 Guilin University of Electronic Technology filed Critical Guilin University of Electronic Technology
Priority to CN201410094119.XA priority Critical patent/CN103868460B/en
Publication of CN103868460A publication Critical patent/CN103868460A/en
Application granted granted Critical
Publication of CN103868460B publication Critical patent/CN103868460B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Length Measuring Devices By Optical Means (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a parallax optimization algorithm-based binocular stereo vision automatic measurement method. The method comprises the steps of 1, obtaining a corrected binocular view; 2, matching by using a stereo matching algorithm and taking a left view as a base map to obtain a preliminary disparity map; 3, for the corrected left view, enabling a target object area to be a colorized master map and other non-target areas to be wholly black; 4, acquiring a complete disparity map of the target object area according to the target object area; 5, for the complete disparity map, obtaining a three-dimensional point cloud according to a projection model; 6, performing coordinate reprojection on the three-dimensional point cloud to compound a coordinate related pixel map; 7, using a morphology method to automatically measure the length and width of a target object. By adopting the method, a binocular measuring operation process is simplified, the influence of specular reflection, foreshortening, perspective distortion, low textures and repeated textures on a smooth surface is reduced, automatic and intelligent measuring is realized, the application range of binocular measuring is widened, and technical support is provided for subsequent robot binocular vision.

Description

Binocular stereo vision method for automatic measurement based on parallax optimized algorithm
Technical field
The present invention relates to the fields of measurement of binocular stereo vision, specifically the binocular stereo vision method for automatic measurement based on parallax optimized algorithm.
Background technology
In recent years, the application in the fields such as robot self-aiming, unmanned, hidden military surveillance, medical diagnosis and industrial detection is increasingly extensive, binocular stereo vision becomes gradually in Robotics research and enlivens the most one of branch, is also the important foundation of subsequent technology development.Measuring technique based on binocular stereo vision is a kind of efficient untouchable advanced detection, measurement, recognition technology, and development prospect is considerable, has wide range of applications.
Current, the application major part that binocular vision is measured concentrates on measuring distance, has certain limitation; And in the size dimension application aspect of measurement space object, need point to get target pixel points or special unique point is set, and can not realize the automatic extraction of object, automatically measure, hinder so industrial intellectuality, mechanization; And manual steps in traditional measuring method, not only increase labour cost but also made step more complicated; The qualified detection of part realizing aspect industrial detection, is also the detection under fixed scene, can not realize the automatic measurement of relative motion dimension of object size; And to the object moving, it is very inaccurate that manual point is got object pixel, can not realize real-time.The more important thing is, due to the impact that mirror-reflection, foreshortening, perspective distortion, low texture and the repetition texture etc. of smooth surface mate binocular, cause not necessarily effective three-dimensional information of target pixel points that manually point is got.
Summary of the invention
The object of the invention is for overcoming the deficiencies in the prior art, a kind of binocular stereo vision method for automatic measurement based on parallax optimized algorithm is provided, this method has not only been simplified the operation steps that binocular is measured, the metrical information of automatic acquisition target object more exactly, and the parallax producing after its coupling is optimized, reduce the mirror-reflection of smooth surface, foreshortening, perspective distortion, the ectocines such as low texture and repetition texture, make the three-dimensional point cloud information of target object more complete, realizing automation and intelligentification measures, expand greatly the range of application that binocular is measured, for follow-up Robot Binocular Vision provides technical support.
The technical scheme that realizes the object of the invention is:
Binocular stereo vision method for automatic measurement based on parallax optimized algorithm, comprises the steps:
1) obtain two-way RGB coloured image by binocular camera simultaneously, utilize chessboard calibration method to carry out binocular calibration to binocular camera camera, obtain the inside and outside parameter of two binocular camera cameras, according to these parameters, binocular view is carried out to binocular correction, remove fisheye effect and the site error impact of camera lens, the binocular view after being proofreaied and correct;
2) to the binocular view after proofreading and correct, utilize Stereo Matching Algorithm take left view as base figure mates, obtain preliminary disparity map;
3) to the left view after proofreading and correct, utilize background subtracting method to extract target object, target object region is colour original, other nontarget areas are black entirely;
4) according to target object region, utilize the parallax optimized algorithm based on foreground detection to fill the local no parallax of preliminary disparity map region, obtain the complete disparity map in target object region;
5), to complete disparity map, obtain three-dimensional point cloud according to projection model;
6) to three-dimensional point cloud, carry out coordinate re-projection, three-dimensional coordinate is projected to two dimensional surface, and by the method for image processing, the pixel coordinate of the world coordinates of two dimensional surface and picture is associated, and the two-dimensional coordinate that demonstrate re-projection after concrete with gray scale picture generates coordinate associated pixel figure;
7) to coordinate associated pixel figure, utilize morphologic method, adopt minimum boundary rectangle that the frame contour in pixel picture is lived, according to the relation of world coordinates and picture pixel, the pixel value of its length of side is converted to real length information, and automatically show, realize length and the width of automatic measurement target object.
Described binocular camera is the double-channel collection video equipment of being combined by two eyes of the camera simulation people of two same specifications, obtains picture pixel and is set to 640x480 pixel, keeps original RGB picture.
Described chessboard calibration method is the calibration algorithm that utilizes specific black and white gridiron pattern to realize, and binocular camera shooting head is demarcated, and obtains the inside and outside parameter of two cameras, as: the parameters such as focal length, distortion parameter, translation vector, rotation matrix; While using chessboard calibration method, the focal length of two video cameras is consistent, and chessboard adopts the black and white lattice of 9x6 lattice, and unit square length of side 30mm gathers picture 15-20 and opens; Binocular is proofreaied and correct zoom factor and is made as 0; Image after correction carries out zooming and panning, makes correcting image only show that valid pixel remove irregular corner areas.
Described binocular is proofreaied and correct and is referred to that the calibration of binocular camera shooting head not only will draw the inner parameter of each camera, also need to measure two relative positions between camera by demarcation, right camera is with respect to D translation vector t and the rotation matrix R of left camera; Calculate the parallax that impact point forms on left and right two views, first these two corresponding Pixel matchings on left and right view to be got up, very consuming time but mate corresponding point on two-dimensional space, in order to reduce match search scope, we utilize polar curve constraint to make the coupling of corresponding point reduce to linear search by two-dimensional search; The effect that binocular is proofreaied and correct is exactly will be the strictly row correspondence of two width images of eliminating after distortion, make two width images to polar curve just in the same horizontal line, on piece image, any point just must have identical line number with its corresponding point on another piece image like this, and only need carry out linear search at this row can match corresponding point.
Described Stereo Matching Algorithm is BM(Boyer-Moore) algorithm (local matching algorithm), or SGBM algorithm (half global registration algorithm), BM algorithm state parameter is respectively: the cutoff value (preFilterCap)=31 of pre-processing filter; SAD window size (SADWinSiz)=19; Minimum parallax (minDisp)=0; Parallax window (numberOfDisparities)=64; The judgment threshold (textureThreshold)=10 of low texture region, if the x derivative absolute value sum of all neighbor pixel points is less than assign thresholds in current SAD window, the parallax value of the pixel that this window is corresponding is 0; Parallax uniqueness number percent (uniquenessRatio)=25, when lowest costs is time low-cost (1+uniquenessRatio/100) times in parallax window ranges, parallax value corresponding to lowest costs is only the parallax of this pixel, otherwise the parallax of this pixel is 0; Parallax change threshold (speckleRange)=32, in the time that in window, parallax variation is greater than threshold value, the parallax zero clearing in this window.
The state parameter of SGBM algorithm is different from BM algorithm: SAD window size=7, and permissible range is [1,11]; Neighbor pixel parallax increases/subtracts the penalty coefficient P1 of 1 o'clock; Be the penalty coefficient P2 that neighbor pixel parallax changing value is greater than at 1 o'clock, P2 is greater than P1; FullDP is set to FALSE.
Described background subtracting method, it is frame difference method, under simple background, it is obvious that prospect and background luminance and color etc. differ, deduct that frame that only comprises background with a rear frame that comprises prospect, obtaining complete foreground area and background frames can choose at any time, and the target object extracting is colored original image, and other nontarget areas are black entirely.
Described extraction target object is that the form automatically to scratch figure is extracted, and the foreground target object extracting is original RGB image, and other background parts are entirely black, i.e. the coloured image of a display foreground object.
Described parallax optimized algorithm is in foreground area, detect effective parallax and invalid parallax by row, and record accessing, the known conditions that effectively parallax is least square method, invalid parallax part is carried out to fitting a straight line, and effectively parallax remains unchanged, reaching whole target object region has complete disparity map, and isolates the disparity map in this region.
Described coordinate associated pixel figure is the method for utilizing space projection, by take the left optical center of binocular camera as initial point, the three-dimensional coordinate of eyeglass plane in the world coordinate system of XY plane project to XY plane, realizes three-dimensional to two-dimentional conversion; Then in binaryzation picture with the corresponding 5cm of pixel, this respective value 5cm can revise according to the scope of measuring, and coordinate information is showed with the form of binaryzation pixel, makes it visual.
The above-mentioned binocular stereo vision method for automatic measurement based on parallax optimized algorithm, is applied in the coordinate associated pixel figure of generation, automatically measures the data of obtaining, along with the mobile tracking of target object shows.
The advantage of this binocular stereo vision method for automatic measurement based on parallax optimized algorithm is:
Utilize the steps such as foreground detection, spatial alternation, morphology processing to realize the metrical information of automatic acquisition target object exactly; Simplify binocular measurement procedure, expand its application prospect, and the parallax producing after its coupling is optimized, reduce mirror-reflection, foreshortening, perspective distortion, the low texture of smooth surface and repeated the ectocines such as texture, make the three-dimensional point cloud information of target object more complete, realize automation and intelligentification measurement, expanded greatly the range of application that binocular is measured, for follow-up Robot Binocular Vision provides technical support.
Accompanying drawing explanation
Fig. 1 is binocular stereo imaging principle schematic in embodiment.
Embodiment
Below in conjunction with drawings and Examples, content of the present invention is further elaborated, but is not limitation of the invention.
Embodiment:
Binocular stereo vision method for automatic measurement based on parallax optimized algorithm, comprises the following steps:
1) obtain two-way RGB coloured image by binocular camera simultaneously, utilize chessboard calibration method to carry out binocular calibration to binocular camera camera, obtain the inside and outside parameter of two binocular camera cameras, according to these parameters, binocular view is carried out to binocular correction, remove fisheye effect and the site error impact of camera lens, the binocular view after being proofreaied and correct;
Described binocular camera is the double-channel collection video equipment of being combined by two eyes of the camera simulation people of two same specifications, obtains picture pixel and is set to 640x480 pixel, keeps original RGB picture;
Adjust binocular camera and collect after two-way RGB image, utilizing black and white lattice chessboard to demarcate it, camera exists radial distortion because the characteristic of optical lens makes imaging:
x p = x ( 1 + k 1 r 2 + k 2 r 4 + k 3 r 6 ) y p = y ( 1 + k 1 r 2 + k 2 r 4 + k 3 r 6 ) - - - ( 1 )
Parameter k in formula (1) 1, k 2, k 3for radial distortion parameter, (x, y) is original coordinates, (x p, y p) be the new coordinate after proofreading and correct; R is radius;
Due to the error of assembling aspect, not completely parallel between sensor and optical lens, there is tangential distortion in imaging therefore:
x p = x + [ 2 p 1 y + p 2 ( r 2 + 2 x 2 ) ] y p = y + [ p 1 ( r 2 + 2 y 2 + 2 p 2 x ) ] - - - ( 2 )
Parameter p in formula (2) 1, p 2for tangential distortion parameter; The calibration of single camera is mainly the internal reference that calculates camera, i.e. focal distance f, imaging initial point c x, c yand five distortion parameters, and join outward, demarcate the world coordinates of thing.The calibration of binocular camera shooting head not only will draw the inner parameter of each camera, also needs to measure two relative positions between camera by demarcation, and right camera is with respect to D translation vector T and the rotation matrix R of left camera; Calculate the parallax that impact point forms on left and right two views, first these two corresponding Pixel matchings on left and right view will be got up.But it is very consuming time mating corresponding point on two-dimensional space, in order to reduce match search scope, we can utilize polar curve constraint to make the coupling of corresponding point reduce to linear search by two-dimensional search; And the effect that binocular is proofreaied and correct is exactly will be the strictly row correspondence of two width images of eliminating after distortion, make two width images to polar curve just in the same horizontal line, on piece image, any point just must have identical line number with its corresponding point on another piece image like this, and only need carry out linear search at this row can match corresponding point;
Then binocular correction is monocular internal reference data (focal length, imaging initial point, distortion factor) and the binocular relative position relation (rotation matrix and translation vector) obtaining according to after camera calibration, respectively left and right view is eliminated to distortion and row is aimed at, make the imaging origin of left and right view consistent, parallel, the left and right imaging plane of two camera optical axises is coplanar, to polar curve row alignment;
2) to the binocular view after proofreading and correct, utilize Stereo Matching Algorithm to mate take left view as base figure, obtain preliminary disparity map, this disparity map is due to mirror-reflection, foreshortening, perspective distortion, low texture and repeat impact generation sudden change parallax or the local no parallaxs such as texture;
Stereo Matching Algorithm comprises following step: first mates cost and calculates,
C(p,d)=C(x,y,d)=max{0,I L(p Li)-I ' max,I' min-I L(p Li)} （3）
In equation (3), C is coupling cost function, and d is parallax, p lirepresent the i pixel p of Zuo Tu li(x, y).In left view, the gray-scale intensity of i point is expressed as I l(pLi), I' maxand I' minrepresent respectively minimax intensity level, L represents a left side.
Then mate cost stack:
E ( D ) = Σ p C ( p , D p ) + Σ q ∈ Np P 1 T [ | D P - D q | = 1 ] + Σ q ∈ Np P 2 T [ | D P - D q | > 1 ] - - - ( 4 )
In formula (4), E is heat-supplied function, and D is whole disparity map, D pand D qrepresent respectively the parallax value that pixel p and q are corresponding, N pfor the field of pixel p, right side Section 1 represents the coupling cost sum of all pixels.The pixel depth difference being adjacent for pixel p has less variation and two kinds of situations of larger variation, and Section 2 and Section 3 are used respectively FACTOR P 1and P 2punish, here function T[] be that 1 and if only if that its parameter is is true, otherwise be 0.In fact, Section 2 and Section 3 are smoothness constraints mentioned above, and they require the depth value of adjacent pixel consistent as much as possible, keep level and smooth, obviously, and P 1<P 2;
Then directly original match cost is processed, to heat-supplied function (4), tried to achieve the minimum value of energy by different optimized algorithms, the parallax value of each point has also just been calculated simultaneously.After obtaining, initial parallax adopt some measures to carry out refinement to parallax.
3) to the left view after proofreading and correct, utilize background subtracting method to extract target object, target object region is colour original, other nontarget areas are black entirely;
After left view is proofreaied and correct, utilize frame difference method to extract target object, its principle is:
| i (t)-i (t-1) | <T background
| i (t)-i (t-1) | 3T prospect
Wherein i (t), i (t-1) is respectively t, the pixel value of t-1 moment corresponding pixel points, T is threshold value.Frame difference method is the one in background subtracting method, be only frame difference method and do not need modeling, because its background model is exactly the figure of previous frame, so speed is very fast, frame difference method is not very sensitive to the illumination of slow conversion in addition, and its shortcoming is quite a few certainly, easily occurs " slur " and " cavity " phenomenon, so next need effectively to improve slur and cavitation by morphology largest contours method, finally pluck out target object with flooding modulus method (mask).
4) according to target object region, utilize the parallax optimized algorithm based on foreground detection to fill the local no parallax of preliminary disparity map region, obtain the complete disparity map in target object region;
Particularly, by line scanning binaryzation foreground picture, record continuously uninterrupted white pixel count be greater than n(threshold value) the pixel coordinate of all continuity points, obtain coordinate set V.This part is that foreground picture is processed, obtain the pixel coordinate collection V of area-of-interest, wherein V just records the coordinate figure of each pixel of area-of-interest, because the area-of-interest in left view, disparity map and foreground picture is the same, so V is also the same.Then utilize the V obtaining above, preliminary disparity map is optimized to processing.Again by line scanning disparity map, whether obtain the parallax value corresponding to pixel coordinate of same a line (ordinate is identical) in pixel coordinate collection V, detecting is effective value, utilizes least square line matching by row, foreground area is carried out to parallax optimization, obtain the complete disparity map in target object region.
5), to complete disparity map, obtain three-dimensional point cloud according to projection model.Three-dimensional point cloud is to utilize binocular stereo imaging principle, be that projection model (relation between world coordinate system, image coordinate system and camera coordinate system) generates the three dimensional space coordinate take the left optical center of binocular camera point as initial point in conjunction with disparity map, the three-dimensional point cloud of acquisition comprises the much information between the representation space such as three-dimensional coordinate, characteristic information mid point a little.
As shown in Figure 1, left camera optical axis is parallel with right camera optical axis, and baseline is the distance of the projection centre line of two video cameras apart from B; Camera focus is f.
The image of existing two video cameras is in same plane, and the image coordinate Y coordinate of unique point P is identical, i.e. Y letf=Y right=Y is obtained by triangle geometric relationship:
X left = f x c z c X right = f ( x c - B ) z c Y = f y c z c - - - ( 5 )
Parallax is: Disparity=X left-X right, the ordinate of left view and the ordinate of right view is poor.
Can calculate thus the three-dimensional coordinate of unique point P under camera coordinates system is:
x c = B &CenterDot; X left Disparity y c = B &CenterDot; Y Disparity y c = B &CenterDot; Y Disparity - - - ( 6 )
Therefore, Disparity = B &CenterDot; f z c .
As long as the corresponding match point that a little exists on view, by above-mentioned computing, just can obtain its corresponding three-dimensional coordinate.
6) to three-dimensional point cloud, carry out coordinate re-projection, three-dimensional coordinate is projected to two dimensional surface, and by the method for image processing, the pixel coordinate of the world coordinates of two dimensional surface and picture is associated, the two-dimensional coordinate that demonstrate re-projection after concrete with gray scale picture generates coordinate associated pixel figure, and its pixel wide, length will directly reflect actual width and the length of object.
7) to coordinate associated pixel figure, utilize morphologic method, adopt minimum boundary rectangle that the frame contour in pixel picture is lived, according to the relation of world coordinates and picture pixel, the pixel value of its length of side is converted to real length information, and automatically show, realize length and the width of automatic measurement target object.
Described chessboard calibration method is the calibration algorithm that utilizes specific black and white gridiron pattern to realize, and binocular camera shooting head is demarcated, and obtains the inside and outside parameter of two cameras, as: the parameters such as focal length, distortion parameter, translation vector, rotation matrix; While using chessboard calibration method, the focal length of two video cameras is at same plane, and chessboard adopts the black and white lattice of 9x6 lattice, and unit square length of side 30mm gathers picture 15-20 and opens; Binocular is proofreaied and correct zoom factor and is made as 0; Image after correction carries out zooming and panning, makes correcting image only show that valid pixel remove irregular corner areas.
Described binocular is proofreaied and correct and is referred to that the calibration of binocular camera shooting head not only will draw the inner parameter of each camera, also need to measure two relative positions between camera by demarcation, right camera is with respect to D translation vector t and the rotation matrix R of left camera; Calculate the parallax that impact point forms on the view of two of left and right, first these two corresponding Pixel matchings on left and right view to be got up, very consuming time but mate corresponding point on two-dimensional space, in order to reduce match search scope, we utilize polar curve constraint to make the coupling of corresponding point reduce to linear search by two-dimensional search; The effect that binocular is proofreaied and correct is exactly will be the strictly row correspondence of two width images of eliminating after distortion, make two width images to polar curve just in the same horizontal line, on piece image, any point just must have identical line number with its corresponding point on another piece image like this, and only need carry out linear search at this row can match corresponding point.
Described Stereo Matching Algorithm is BM algorithm or SGBM algorithm, and BM algorithm state parameter is respectively: the cutoff value (preFilterCap)=31 of pre-processing filter; SAD window size (SADWinSiz)=19; Minimum parallax (minDisp)=0; Parallax window (numberOfDisparities)=64; The judgment threshold (textureThreshold)=10 of low texture region, if the x derivative absolute value sum of all neighbor pixel points is less than assign thresholds in current SAD window, the parallax value of the pixel that this window is corresponding is 0; Parallax uniqueness number percent (uniquenessRatio)=25, when lowest costs is time low-cost (1+uniquenessRatio/100) times in parallax window ranges, parallax value corresponding to lowest costs is only the parallax of this pixel, otherwise the parallax of this pixel is 0; Parallax change threshold (speckleRange)=32, in the time that in window, parallax variation is greater than threshold value, the parallax zero clearing in this window;
The state parameter of SGBM algorithm is different from BM algorithm: SAD window size=7, and permissible range is [1,11]; Neighbor pixel parallax increases/subtracts the penalty coefficient P1 of 1 o'clock; Be the penalty coefficient P2 that neighbor pixel parallax changing value is greater than at 1 o'clock, P2 is greater than P1; FullDP is set to FALSE.
Described background subtracting method, it is frame difference method, under simple background, it is obvious that prospect and background luminance and color etc. differ, deduct that frame that only comprises background with a rear frame that comprises prospect, obtaining complete foreground area and background frames can choose at any time, and the target object extracting is colored original image, and other nontarget areas are black entirely.
Described extraction target object is that the form automatically to scratch figure is extracted, and the foreground target object extracting is original RGB image, and other background parts are entirely black, i.e. the coloured image of a display foreground object.
Described parallax optimized algorithm is in foreground area, detect effective parallax and invalid parallax by row, and record accessing, the known conditions that effectively parallax is least square method, invalid parallax part is carried out to fitting a straight line, and effectively parallax remains unchanged, reaching whole target object region has complete disparity map, and isolates the disparity map in this region.
Described coordinate associated pixel figure is the method for utilizing space projection, by take the left optical center of binocular camera as initial point, the three-dimensional coordinate of eyeglass plane in the world coordinate system of XY plane project to XY plane, realizes three-dimensional to two-dimentional conversion; Then in binaryzation picture with the corresponding 5cm of pixel, this respective value 5cm can revise according to the scope of measuring, and coordinate information is showed with the form of binaryzation pixel, makes it visual.
This binocular stereo vision method for automatic measurement based on parallax optimized algorithm, is applied in the coordinate associated pixel figure of generation, automatically measures the data of obtaining, along with the mobile tracking of target object shows.
The above-mentioned binocular stereo vision method for automatic measurement based on parallax optimized algorithm, only demarcate in first use or adjusted out-of-date just needs of binocular camera, binocular parameter setting in binocular matching process is as long as arrange once, need not measure all and arrange at every turn, and background frames can be changed according to application scenarios at any time; When target object enters view, will be identified, and pluck out target object and can follow the tracks of and detect object and complete automatic measurement, the metrical information of display-object object in corresponding binaryzation view interface.

Claims (7)

1. the binocular stereo vision method for automatic measurement based on parallax optimized algorithm, is characterized in that, comprises the steps:
1) obtain two-way RGB coloured image by binocular camera simultaneously, utilize chessboard calibration method to carry out binocular calibration to binocular camera camera, obtain the inside and outside parameter of two binocular camera cameras, according to these parameters, binocular view is carried out to binocular correction, remove fisheye effect and the site error impact of camera lens, the binocular view after being proofreaied and correct;
2) to the binocular view after proofreading and correct, utilize Stereo Matching Algorithm take left view as base figure mates, obtain preliminary disparity map;
3) to the left view after proofreading and correct, utilize background subtracting method to extract target object, target object region is colour original, other nontarget areas are black entirely;
4) according to target object region, utilize the parallax optimized algorithm based on foreground detection to fill the local no parallax of preliminary disparity map region, obtain the complete disparity map in target object region;
5), to complete disparity map, obtain three-dimensional point cloud according to projection model;
6) to three-dimensional point cloud, carry out coordinate re-projection, three-dimensional coordinate is projected to two dimensional surface, and by the method for image processing, the pixel coordinate of the world coordinates of two dimensional surface and picture is associated, and the two-dimensional coordinate that demonstrate re-projection after concrete with gray scale picture generates coordinate associated pixel figure;
7) to coordinate associated pixel figure, utilize morphologic method, adopt minimum boundary rectangle that the frame contour in pixel picture is lived, according to the relation of world coordinates and picture pixel, the pixel value of its length of side is converted to real length information, and automatically show, realize length and the width of automatic measurement target object.
2. according to the binocular stereo vision method for automatic measurement based on parallax optimized algorithm described in claim 1, it is characterized in that, binocular camera obtains picture pixel and is set to 640x480 pixel, keeps original RGB picture.
3. according to the binocular stereo vision method for automatic measurement based on parallax optimized algorithm described in claim 1, it is characterized in that, while using chessboard calibration method, the focal length of two video cameras is consistent, and chessboard adopts the black and white lattice of 9x6 lattice, unit square length of side 30mm, gathers picture 15-20 and opens; Binocular is proofreaied and correct zoom factor and is made as 0.
4. according to the binocular stereo vision method for automatic measurement based on parallax optimized algorithm described in claim 1, it is characterized in that, described Stereo Matching Algorithm is BM algorithm or SGBM algorithm, and BM algorithm state parameter is respectively: cutoff value=31 of pre-processing filter; SAD window size=19; Minimum parallax=0; Parallax window=64; Judgment threshold=10 of low texture region, if the x derivative absolute value sum of all neighbor pixel points is less than assign thresholds in current SAD window, the parallax value of the pixel that this window is corresponding is 0; Parallax uniqueness number percent=25, when lowest costs is time low-cost (1+uniquenessRatio/100) times in parallax window ranges, parallax value corresponding to lowest costs is only the parallax of this pixel, otherwise the parallax of this pixel is 0; Parallax change threshold=32, in the time that in window, parallax variation is greater than threshold value, the parallax zero clearing in this window;
The state parameter of SGBM algorithm is different from BM algorithm: SAD window size=7, and permissible range is [1,11]; Neighbor pixel parallax increases/subtracts the penalty coefficient P1 of 1 o'clock; Be the penalty coefficient P2 that neighbor pixel parallax changing value is greater than at 1 o'clock, P2 is greater than P1; FullDP is set to FALSE.
5. according to the binocular stereo vision method for automatic measurement based on parallax optimized algorithm described in claim 1, it is characterized in that, described parallax optimized algorithm is in foreground area, detect effective parallax and invalid parallax by row, and record accessing, the known conditions that effectively parallax is least square method, invalid parallax part is carried out to fitting a straight line, and effectively parallax remains unchanged, reaching whole target object region has complete disparity map, and isolates the disparity map in this region.
6. according to the binocular stereo vision method for automatic measurement based on parallax optimized algorithm described in claim 1, it is characterized in that, described coordinate associated pixel figure is the method for utilizing space projection, by take the left optical center of binocular camera as initial point, the three-dimensional coordinate of eyeglass plane in the world coordinate system of XY plane project to XY plane, realizes three-dimensional to two-dimentional conversion; Then in binaryzation picture with the corresponding 5cm of pixel, this respective value 5cm can revise according to the scope of measuring, and coordinate information is showed with the form of binaryzation pixel, makes it visual.
7. the binocular stereo vision method for automatic measurement based on parallax optimized algorithm described in claim 1-6 any one, is applied in the coordinate associated pixel figure generating, and automatically measures the data of obtaining, along with the mobile tracking of target object shows.
CN201410094119.XA 2014-03-13 2014-03-13 Binocular stereo vision method for automatic measurement based on parallax optimized algorithm Expired - Fee Related CN103868460B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410094119.XA CN103868460B (en) 2014-03-13 2014-03-13 Binocular stereo vision method for automatic measurement based on parallax optimized algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410094119.XA CN103868460B (en) 2014-03-13 2014-03-13 Binocular stereo vision method for automatic measurement based on parallax optimized algorithm

Publications (2)

Publication Number Publication Date
CN103868460A true CN103868460A (en) 2014-06-18
CN103868460B CN103868460B (en) 2016-10-05

Family

ID=50907248

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410094119.XA Expired - Fee Related CN103868460B (en) 2014-03-13 2014-03-13 Binocular stereo vision method for automatic measurement based on parallax optimized algorithm

Country Status (1)

Country Link
CN (1) CN103868460B (en)

Cited By (97)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104236468A (en) * 2014-09-26 2014-12-24 上海未来伙伴机器人有限公司 Method and system for calculating coordinates of target space and mobile robot
CN104363375A (en) * 2014-11-28 2015-02-18 广东欧珀移动通信有限公司 Method, device and terminal for photograph noise reduction
CN104406538A (en) * 2014-12-01 2015-03-11 南京航空航天大学 Three-dimensional mark point matching method for point cloud registration and three-dimensional scanning method
CN104636724A (en) * 2015-02-02 2015-05-20 华中科技大学 Vehicle-mounted camera rapid pedestrian and vehicle detection method based on goal congruence
CN104794713A (en) * 2015-04-15 2015-07-22 同济大学 Greenhouse crop digital-imaging method based on ARM and binocular vision
CN105046749A (en) * 2015-09-10 2015-11-11 深圳市神州龙资讯服务有限公司 Method for automatically generating 3D model based on three-view aerial photos
CN105335955A (en) * 2014-07-17 2016-02-17 株式会社理光 Object detection method and object detection apparatus
CN105551020A (en) * 2015-12-03 2016-05-04 浙江大华技术股份有限公司 Method and device for detecting dimensions of target object
CN105550670A (en) * 2016-01-27 2016-05-04 兰州理工大学 Target object dynamic tracking and measurement positioning method
CN105651258A (en) * 2015-12-30 2016-06-08 杨正林 Initiative-view-angle binocular vision ranging system and initiative-view-angle binocular vision ranging method
CN105783731A (en) * 2016-03-08 2016-07-20 上海易景信息科技有限公司 Method for measuring length of measured object by means of double cameras
CN104111039B (en) * 2014-08-08 2016-08-24 电子科技大学 For arbitrarily putting the scaling method of fringe projection three-dimension measuring system
CN106504276A (en) * 2016-10-25 2017-03-15 桂林电子科技大学 The combinations matches cost algorithms of non local Stereo Matching Algorithm and parallax joint filling algorithm
CN106651911A (en) * 2016-11-17 2017-05-10 天津大学 Fish behavior acquiring method based on image tracking
CN106625713A (en) * 2017-01-11 2017-05-10 长春工业大学 Method of improving gumming accuracy of gumming industrial robot
CN106803913A (en) * 2017-03-10 2017-06-06 武汉东信同邦信息技术有限公司 A kind of detection method and its device of the action that taken the floor for Auto-Sensing student
CN106952332A (en) * 2017-03-06 2017-07-14 华侨大学 A kind of 3D based on perspective transform draws construction drawing automatic generation method
CN107256562A (en) * 2017-05-25 2017-10-17 山东师范大学 Image defogging method and device based on binocular vision system
CN107274400A (en) * 2017-06-21 2017-10-20 歌尔股份有限公司 Space positioning apparatus, location processing method and device, virtual reality system
CN107392898A (en) * 2017-07-20 2017-11-24 海信集团有限公司 Applied to the pixel parallax value calculating method and device in binocular stereo vision
CN107481267A (en) * 2017-08-14 2017-12-15 华南理工大学 A kind of shooting projection interactive system and method based on binocular vision
CN107578397A (en) * 2017-07-25 2018-01-12 西南交通大学 A kind of novel non-contact abrasion of contact wire detection method
CN107588721A (en) * 2017-08-28 2018-01-16 武汉科技大学 The measuring method and system of a kind of more sizes of part based on binocular vision
CN107636679A (en) * 2016-12-30 2018-01-26 深圳前海达闼云端智能科技有限公司 A kind of obstacle detection method and device
CN107862721A (en) * 2017-12-01 2018-03-30 杭州晶智能科技有限公司 A kind of secondary identifying system in meadow based on binocular stereo vision
CN107945220A (en) * 2017-11-30 2018-04-20 华中科技大学 A kind of method for reconstructing based on binocular vision
CN107992871A (en) * 2017-12-21 2018-05-04 陕西伟景机器人科技有限公司 The automatic accounting method in dining room based on image recognition
CN108010085A (en) * 2017-11-30 2018-05-08 西南科技大学 Target identification method based on binocular Visible Light Camera Yu thermal infrared camera
CN108171739A (en) * 2017-12-25 2018-06-15 清华大学苏州汽车研究院（吴江） Binocular vision solid matching method based on movable information
CN108230235A (en) * 2017-07-28 2018-06-29 北京市商汤科技开发有限公司 A kind of disparity map generation system, method and storage medium
CN108230372A (en) * 2017-11-30 2018-06-29 努比亚技术有限公司 A kind of image processing method, terminal and computer readable storage medium
CN108259881A (en) * 2018-01-30 2018-07-06 深圳市得色科技有限公司 3D synthetic methods and its system based on parallax estimation
CN108335350A (en) * 2018-02-06 2018-07-27 聊城大学 The three-dimensional rebuilding method of binocular stereo vision
CN108401460A (en) * 2017-09-29 2018-08-14 深圳市大疆创新科技有限公司 Generate method, system, storage medium and the computer program product of disparity map
CN108458668A (en) * 2018-01-05 2018-08-28 燕山大学 Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method
CN108921842A (en) * 2018-07-02 2018-11-30 上海交通大学 A kind of cereal flow detection method and device
CN108961383A (en) * 2017-05-19 2018-12-07 杭州海康威视数字技术股份有限公司 three-dimensional rebuilding method and device
CN109048926A (en) * 2018-10-24 2018-12-21 河北工业大学 A kind of intelligent robot obstacle avoidance system and method based on stereoscopic vision
CN109186947A (en) * 2018-09-26 2019-01-11 福州大学 A kind of electric appliance Three-Dimensional Dynamic characteristic Auto-Test System and method
CN109215044A (en) * 2017-06-30 2019-01-15 京东方科技集团股份有限公司 Image processing method and system, storage medium and mobile system
CN109389648A (en) * 2018-09-19 2019-02-26 晓智科技（成都）有限公司 A method of error of measured data is reduced by data iteration
CN109584312A (en) * 2018-11-30 2019-04-05 Oppo广东移动通信有限公司 Camera calibration method, device, electronic equipment and computer readable storage medium
CN109612437A (en) * 2019-01-14 2019-04-12 华南农业大学 The binocular position finding and detection method combined based on Bumblebee with total station
CN109903327A (en) * 2019-03-04 2019-06-18 西安电子科技大学 A kind of object dimension measurement method of sparse cloud
CN109974659A (en) * 2019-03-31 2019-07-05 徐州工程学院 A kind of embedded range-measurement system based on binocular machine vision
CN110120074A (en) * 2019-05-10 2019-08-13 清研同创机器人（天津）有限公司 A kind of hot line robot cable localization method under complex environment
CN110260801A (en) * 2019-05-13 2019-09-20 平安科技（深圳）有限公司 Method and apparatus for measuring volume of material
CN110675454A (en) * 2019-10-16 2020-01-10 深圳前海达闼云端智能科技有限公司 Object positioning method, device and storage medium
CN110838148A (en) * 2019-11-11 2020-02-25 杭州凌像科技有限公司 Binocular camera self-calibration method
CN110889873A (en) * 2019-11-26 2020-03-17 中国科学院光电研究院 Target positioning method and device, electronic equipment and storage medium
CN111047709A (en) * 2019-11-29 2020-04-21 暨南大学 Binocular vision naked eye 3D image generation method
CN111047638A (en) * 2018-10-12 2020-04-21 富华科精密工业（深圳）有限公司 Monocular distance measuring device
CN111198563A (en) * 2019-12-30 2020-05-26 广东省智能制造研究所 Terrain recognition method and system for dynamic motion of foot type robot
CN111243018A (en) * 2019-12-31 2020-06-05 北京航空航天大学 Method and system for automatically performing nevus-removing operation
US10681257B2 (en) 2015-08-26 2020-06-09 Zhejiang Dahua Technology Co., Ltd. Methods and systems for traffic monitoring
CN111351446A (en) * 2020-01-10 2020-06-30 奕目(上海)科技有限公司 Light field camera calibration method for three-dimensional topography measurement
CN111380458A (en) * 2018-12-29 2020-07-07 顺丰科技有限公司 Method and device for measuring carriage cargo volume
CN111402309A (en) * 2020-03-05 2020-07-10 中国科学院上海微系统与信息技术研究所 Calibration and depth image processing method for multi-view stereo camera
CN111429523A (en) * 2020-03-16 2020-07-17 天目爱视（北京）科技有限公司 Remote calibration method in 3D modeling
CN111508068A (en) * 2020-04-20 2020-08-07 华中科技大学 Three-dimensional reconstruction method and system applied to binocular endoscope image
CN111553252A (en) * 2020-04-24 2020-08-18 福建农林大学 Road pedestrian automatic identification and positioning method based on deep learning and U-V parallax algorithm
CN111627067A (en) * 2019-02-28 2020-09-04 海信集团有限公司 Calibration method of binocular camera and vehicle-mounted equipment
CN111721194A (en) * 2019-03-19 2020-09-29 北京伟景智能科技有限公司 Multi-laser-line rapid detection method
CN111739359A (en) * 2020-06-30 2020-10-02 上海乂学教育科技有限公司 Augmented reality courseware generation system
CN111899282A (en) * 2020-07-30 2020-11-06 平安科技（深圳）有限公司 Pedestrian trajectory tracking method and device based on binocular camera calibration
CN112053781A (en) * 2020-09-16 2020-12-08 四川大学华西医院 Dynamic and static stereoscopic vision testing method and terminal
CN112085802A (en) * 2020-07-24 2020-12-15 浙江工业大学 Method for acquiring three-dimensional finger vein image based on binocular camera
CN112097732A (en) * 2020-08-04 2020-12-18 北京中科慧眼科技有限公司 Binocular camera-based three-dimensional distance measurement method, system, equipment and readable storage medium
CN112171635A (en) * 2020-09-24 2021-01-05 上海思寒环保科技有限公司 Remote control robot
CN112258635A (en) * 2020-10-26 2021-01-22 北京石油化工学院 Three-dimensional reconstruction method and device based on improved binocular matching SAD algorithm
CN112013792B (en) * 2020-10-19 2021-02-02 南京知谱光电科技有限公司 Surface scanning three-dimensional reconstruction method for complex large-component robot
CN112379605A (en) * 2020-11-24 2021-02-19 中国人民解放军火箭军工程大学 Bridge crane semi-physical simulation control experiment system and method based on visual servo
CN112465778A (en) * 2020-11-26 2021-03-09 江苏国和智能科技有限公司 Underwater fish shoal observation device and method
CN112465899A (en) * 2020-11-25 2021-03-09 国网福建省电力有限公司电力科学研究院 Binocular vision-based automatic wire peeling and positioning method
CN112581542A (en) * 2020-12-24 2021-03-30 北京百度网讯科技有限公司 Method, device and equipment for evaluating automatic driving monocular calibration algorithm
CN112602118A (en) * 2019-03-14 2021-04-02 欧姆龙株式会社 Image processing apparatus and three-dimensional measurement system
CN112734652A (en) * 2020-12-22 2021-04-30 同济大学 Near-infrared blood vessel image projection correction method based on binocular vision
CN112767442A (en) * 2021-01-18 2021-05-07 中山大学 Pedestrian three-dimensional detection tracking method and system based on top view angle
CN112991369A (en) * 2021-03-25 2021-06-18 湖北工业大学 Method for detecting overall dimension of running vehicle based on binocular vision
CN113052898A (en) * 2021-04-08 2021-06-29 四川大学华西医院 Point cloud and strong-reflection target real-time positioning method based on active binocular camera
CN113077524A (en) * 2021-04-22 2021-07-06 中德（珠海）人工智能研究院有限公司 Automatic calibration method, device and equipment for binocular fisheye camera and storage medium
CN113099204A (en) * 2021-04-13 2021-07-09 北京航空航天大学青岛研究院 Remote live-action augmented reality method based on VR head-mounted display equipment
CN113177565A (en) * 2021-03-15 2021-07-27 北京理工大学 Binocular vision position measuring system and method based on deep learning
CN113340241A (en) * 2021-06-09 2021-09-03 河南德朗智能科技有限公司 Binocular vision concrete joint surface roughness measurement method and system
CN113379831A (en) * 2021-06-22 2021-09-10 北京航空航天大学青岛研究院 Augmented reality method based on binocular camera and humanoid robot
CN113393413A (en) * 2020-03-11 2021-09-14 河海大学 Water area measuring method and system based on monocular and binocular vision cooperation
CN113446958A (en) * 2021-06-02 2021-09-28 南京航空航天大学 Binocular vision system based on symmetrical arrangement and curved surface reconstruction method of DIC technology
WO2021196941A1 (en) * 2020-04-03 2021-10-07 浙江商汤科技开发有限公司 Method and apparatus for detecting three-dimensional target
CN113487679A (en) * 2021-06-29 2021-10-08 哈尔滨工程大学 Visual ranging signal processing method for automatic focusing system of laser marking machine
CN113610741A (en) * 2021-08-18 2021-11-05 梅卡曼德（北京）机器人科技有限公司 Point cloud processing method and device based on laser line scanning
CN113959398A (en) * 2021-10-09 2022-01-21 广东汇天航空航天科技有限公司 Vision-based distance measurement method and device, travelable equipment and storage medium
CN113963052A (en) * 2021-09-22 2022-01-21 西安交通大学 Large aerostat volume real-time monitoring method based on binocular vision
CN113989383A (en) * 2021-10-23 2022-01-28 深圳慧源创新科技有限公司 Method for improving accuracy and range of binocular distance measurement
CN114742876A (en) * 2022-06-13 2022-07-12 菏泽市土地储备中心 Land vision stereo measurement method
CN115049980A (en) * 2022-06-16 2022-09-13 威海经济技术开发区天智创新技术研究院 Target object determination method and device based on image and electronic equipment
CN116258759A (en) * 2023-05-15 2023-06-13 北京爱芯科技有限公司 Stereo matching method, device and equipment
CN111369447B (en) * 2020-03-09 2023-06-16 湖南警察学院 Method for correcting image point in monocular stereoscopic vision image

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109993781B (en) * 2019-03-28 2021-09-03 北京清微智能科技有限公司 Parallax image generation method and system based on binocular stereo vision matching
CN111121722A (en) * 2019-12-13 2020-05-08 南京理工大学 Binocular three-dimensional imaging method combining laser dot matrix and polarization vision

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009124308A (en) * 2007-11-13 2009-06-04 Tokyo Denki Univ Multi-viewpoint image creating system and multi-viewpoint image creating method
CN101887589A (en) * 2010-06-13 2010-11-17 东南大学 Stereoscopic vision-based real low-texture image reconstruction method
CN101976455A (en) * 2010-10-08 2011-02-16 东南大学 Color image three-dimensional reconstruction method based on three-dimensional matching

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009124308A (en) * 2007-11-13 2009-06-04 Tokyo Denki Univ Multi-viewpoint image creating system and multi-viewpoint image creating method
CN101887589A (en) * 2010-06-13 2010-11-17 东南大学 Stereoscopic vision-based real low-texture image reconstruction method
CN101976455A (en) * 2010-10-08 2011-02-16 东南大学 Color image three-dimensional reconstruction method based on three-dimensional matching

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
吴瑞敏: "大尺寸高温锻件双目视觉测量技术", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 5, 15 May 2009 (2009-05-15), pages 61 - 66 *
朱秋煜等: "基于视差和帧差的图割优化运动目标分割算法", 《电视技术》, vol. 36, no. 13, 2 July 2012 (2012-07-02), pages 135 - 139 *
许凤良: "基于双目立体视觉的弹目空间交会测量系统", 《中国优秀硕士学位论文全文数据库工程科技II辑》, no. 11, 15 November 2009 (2009-11-15) *

Cited By (151)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105335955A (en) * 2014-07-17 2016-02-17 株式会社理光 Object detection method and object detection apparatus
CN105335955B (en) * 2014-07-17 2018-04-10 株式会社理光 Method for checking object and object test equipment
CN104111039B (en) * 2014-08-08 2016-08-24 电子科技大学 For arbitrarily putting the scaling method of fringe projection three-dimension measuring system
CN104236468A (en) * 2014-09-26 2014-12-24 上海未来伙伴机器人有限公司 Method and system for calculating coordinates of target space and mobile robot
CN104363375A (en) * 2014-11-28 2015-02-18 广东欧珀移动通信有限公司 Method, device and terminal for photograph noise reduction
CN104363375B (en) * 2014-11-28 2018-03-27 广东欧珀移动通信有限公司 A kind of method, apparatus and terminal of photo noise reduction
CN104406538B (en) * 2014-12-01 2017-01-11 南京航空航天大学 Three-dimensional mark point matching method for point cloud registration and three-dimensional scanning method
CN104406538A (en) * 2014-12-01 2015-03-11 南京航空航天大学 Three-dimensional mark point matching method for point cloud registration and three-dimensional scanning method
CN104636724A (en) * 2015-02-02 2015-05-20 华中科技大学 Vehicle-mounted camera rapid pedestrian and vehicle detection method based on goal congruence
CN104636724B (en) * 2015-02-02 2018-09-04 华中科技大学 A kind of quick Pedestrians and vehicles detection method of in-vehicle camera based on goal congruence
CN104794713A (en) * 2015-04-15 2015-07-22 同济大学 Greenhouse crop digital-imaging method based on ARM and binocular vision
CN104794713B (en) * 2015-04-15 2017-07-11 同济大学 Chamber crop digitalized image method based on ARM and binocular vision
US11514680B2 (en) 2015-08-26 2022-11-29 Zhejiang Dahua Technology Co., Ltd. Methods and systems for traffic monitoring
US10681257B2 (en) 2015-08-26 2020-06-09 Zhejiang Dahua Technology Co., Ltd. Methods and systems for traffic monitoring
CN105046749A (en) * 2015-09-10 2015-11-11 深圳市神州龙资讯服务有限公司 Method for automatically generating 3D model based on three-view aerial photos
CN105551020A (en) * 2015-12-03 2016-05-04 浙江大华技术股份有限公司 Method and device for detecting dimensions of target object
CN105551020B (en) * 2015-12-03 2019-03-26 浙江大华技术股份有限公司 A kind of method and device detecting object size
CN105651258A (en) * 2015-12-30 2016-06-08 杨正林 Initiative-view-angle binocular vision ranging system and initiative-view-angle binocular vision ranging method
CN105651258B (en) * 2015-12-30 2018-07-13 杨正林 Active visual angle binocular range-measurement system and method
CN105550670B (en) * 2016-01-27 2019-07-12 兰州理工大学 A kind of target object dynamically track and measurement and positioning method
CN105550670A (en) * 2016-01-27 2016-05-04 兰州理工大学 Target object dynamic tracking and measurement positioning method
CN105783731A (en) * 2016-03-08 2016-07-20 上海易景信息科技有限公司 Method for measuring length of measured object by means of double cameras
CN106504276B (en) * 2016-10-25 2019-02-19 桂林电子科技大学 Non local solid matching method
CN106504276A (en) * 2016-10-25 2017-03-15 桂林电子科技大学 The combinations matches cost algorithms of non local Stereo Matching Algorithm and parallax joint filling algorithm
CN106651911A (en) * 2016-11-17 2017-05-10 天津大学 Fish behavior acquiring method based on image tracking
CN107636679B (en) * 2016-12-30 2021-05-25 达闼机器人有限公司 Obstacle detection method and device
CN107636679A (en) * 2016-12-30 2018-01-26 深圳前海达闼云端智能科技有限公司 A kind of obstacle detection method and device
CN106625713A (en) * 2017-01-11 2017-05-10 长春工业大学 Method of improving gumming accuracy of gumming industrial robot
CN106952332B (en) * 2017-03-06 2020-05-05 华侨大学 Automatic 3D picture construction drawing generation method based on perspective transformation
CN106952332A (en) * 2017-03-06 2017-07-14 华侨大学 A kind of 3D based on perspective transform draws construction drawing automatic generation method
CN106803913A (en) * 2017-03-10 2017-06-06 武汉东信同邦信息技术有限公司 A kind of detection method and its device of the action that taken the floor for Auto-Sensing student
CN108961383B (en) * 2017-05-19 2021-12-14 杭州海康威视数字技术股份有限公司 Three-dimensional reconstruction method and device
CN108961383A (en) * 2017-05-19 2018-12-07 杭州海康威视数字技术股份有限公司 three-dimensional rebuilding method and device
CN107256562A (en) * 2017-05-25 2017-10-17 山东师范大学 Image defogging method and device based on binocular vision system
US10699436B2 (en) 2017-06-21 2020-06-30 Goertek Inc. Spatial positioning device and positioning processing method and device
WO2018232900A1 (en) * 2017-06-21 2018-12-27 歌尔股份有限公司 Space positioning device, and positioning processing method and device
CN107274400A (en) * 2017-06-21 2017-10-20 歌尔股份有限公司 Space positioning apparatus, location processing method and device, virtual reality system
CN109215044B (en) * 2017-06-30 2020-12-15 京东方科技集团股份有限公司 Image processing method and system, storage medium, and mobile system
CN109215044A (en) * 2017-06-30 2019-01-15 京东方科技集团股份有限公司 Image processing method and system, storage medium and mobile system
CN107392898A (en) * 2017-07-20 2017-11-24 海信集团有限公司 Applied to the pixel parallax value calculating method and device in binocular stereo vision
CN107392898B (en) * 2017-07-20 2020-03-20 海信集团有限公司 Method and device for calculating pixel point parallax value applied to binocular stereo vision
CN107578397A (en) * 2017-07-25 2018-01-12 西南交通大学 A kind of novel non-contact abrasion of contact wire detection method
CN108230235A (en) * 2017-07-28 2018-06-29 北京市商汤科技开发有限公司 A kind of disparity map generation system, method and storage medium
CN108230235B (en) * 2017-07-28 2021-07-02 北京市商汤科技开发有限公司 Disparity map generation system, method and storage medium
CN107481267A (en) * 2017-08-14 2017-12-15 华南理工大学 A kind of shooting projection interactive system and method based on binocular vision
CN107588721A (en) * 2017-08-28 2018-01-16 武汉科技大学 The measuring method and system of a kind of more sizes of part based on binocular vision
CN108401460A (en) * 2017-09-29 2018-08-14 深圳市大疆创新科技有限公司 Generate method, system, storage medium and the computer program product of disparity map
CN108401460B (en) * 2017-09-29 2021-10-12 深圳市大疆创新科技有限公司 Method, system, storage medium, and computer program product for generating a disparity map
CN108230372A (en) * 2017-11-30 2018-06-29 努比亚技术有限公司 A kind of image processing method, terminal and computer readable storage medium
CN108230372B (en) * 2017-11-30 2022-01-14 努比亚技术有限公司 Image processing method, terminal and computer readable storage medium
CN108010085A (en) * 2017-11-30 2018-05-08 西南科技大学 Target identification method based on binocular Visible Light Camera Yu thermal infrared camera
CN107945220A (en) * 2017-11-30 2018-04-20 华中科技大学 A kind of method for reconstructing based on binocular vision
CN108010085B (en) * 2017-11-30 2019-12-31 西南科技大学 Target identification method based on binocular visible light camera and thermal infrared camera
CN107862721B (en) * 2017-12-01 2020-06-16 杭州晶一智能科技有限公司 Grassland secondary recognition system based on binocular stereoscopic vision
CN107862721A (en) * 2017-12-01 2018-03-30 杭州晶智能科技有限公司 A kind of secondary identifying system in meadow based on binocular stereo vision
WO2019119525A1 (en) * 2017-12-21 2019-06-27 陕西伟景机器人科技有限公司 Image recognition based method for self-checkout in restaurant
CN107992871A (en) * 2017-12-21 2018-05-04 陕西伟景机器人科技有限公司 The automatic accounting method in dining room based on image recognition
CN108171739A (en) * 2017-12-25 2018-06-15 清华大学苏州汽车研究院（吴江） Binocular vision solid matching method based on movable information
CN108458668A (en) * 2018-01-05 2018-08-28 燕山大学 Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method
CN108259881A (en) * 2018-01-30 2018-07-06 深圳市得色科技有限公司 3D synthetic methods and its system based on parallax estimation
CN108335350A (en) * 2018-02-06 2018-07-27 聊城大学 The three-dimensional rebuilding method of binocular stereo vision
CN108921842A (en) * 2018-07-02 2018-11-30 上海交通大学 A kind of cereal flow detection method and device
CN109389648A (en) * 2018-09-19 2019-02-26 晓智科技（成都）有限公司 A method of error of measured data is reduced by data iteration
CN109389648B (en) * 2018-09-19 2022-04-22 晓智未来(成都)科技有限公司 Method for reducing measurement data error through data iteration
CN109186947B (en) * 2018-09-26 2019-11-12 福州大学 A kind of electric appliance Three-Dimensional Dynamic characteristic Auto-Test System and method
CN109186947A (en) * 2018-09-26 2019-01-11 福州大学 A kind of electric appliance Three-Dimensional Dynamic characteristic Auto-Test System and method
CN111047638B (en) * 2018-10-12 2023-08-18 深圳富联富桂精密工业有限公司 Monocular distance measuring device
CN111047638A (en) * 2018-10-12 2020-04-21 富华科精密工业（深圳）有限公司 Monocular distance measuring device
CN109048926A (en) * 2018-10-24 2018-12-21 河北工业大学 A kind of intelligent robot obstacle avoidance system and method based on stereoscopic vision
CN109584312B (en) * 2018-11-30 2020-09-11 Oppo广东移动通信有限公司 Camera calibration method, device, electronic equipment and computer-readable storage medium
CN109584312A (en) * 2018-11-30 2019-04-05 Oppo广东移动通信有限公司 Camera calibration method, device, electronic equipment and computer readable storage medium
CN111380458A (en) * 2018-12-29 2020-07-07 顺丰科技有限公司 Method and device for measuring carriage cargo volume
CN109612437A (en) * 2019-01-14 2019-04-12 华南农业大学 The binocular position finding and detection method combined based on Bumblebee with total station
CN109612437B (en) * 2019-01-14 2020-07-31 华南农业大学 Binocular positioning detection method based on combination of Bumblebe and total station
CN111627067B (en) * 2019-02-28 2023-08-22 海信集团有限公司 Calibration method of binocular camera and vehicle-mounted equipment
CN111627067A (en) * 2019-02-28 2020-09-04 海信集团有限公司 Calibration method of binocular camera and vehicle-mounted equipment
CN109903327A (en) * 2019-03-04 2019-06-18 西安电子科技大学 A kind of object dimension measurement method of sparse cloud
CN112602118A (en) * 2019-03-14 2021-04-02 欧姆龙株式会社 Image processing apparatus and three-dimensional measurement system
CN112602118B (en) * 2019-03-14 2024-06-07 欧姆龙株式会社 Image processing device and three-dimensional measurement system
CN111721194A (en) * 2019-03-19 2020-09-29 北京伟景智能科技有限公司 Multi-laser-line rapid detection method
CN109974659A (en) * 2019-03-31 2019-07-05 徐州工程学院 A kind of embedded range-measurement system based on binocular machine vision
CN110120074A (en) * 2019-05-10 2019-08-13 清研同创机器人（天津）有限公司 A kind of hot line robot cable localization method under complex environment
CN110260801A (en) * 2019-05-13 2019-09-20 平安科技（深圳）有限公司 Method and apparatus for measuring volume of material
CN110675454A (en) * 2019-10-16 2020-01-10 深圳前海达闼云端智能科技有限公司 Object positioning method, device and storage medium
CN110838148B (en) * 2019-11-11 2023-05-05 杭州凌像科技有限公司 Binocular camera self-calibration method
CN110838148A (en) * 2019-11-11 2020-02-25 杭州凌像科技有限公司 Binocular camera self-calibration method
CN110889873A (en) * 2019-11-26 2020-03-17 中国科学院光电研究院 Target positioning method and device, electronic equipment and storage medium
CN111047709A (en) * 2019-11-29 2020-04-21 暨南大学 Binocular vision naked eye 3D image generation method
CN111047709B (en) * 2019-11-29 2023-05-05 暨南大学 Binocular vision naked eye 3D image generation method
CN111198563B (en) * 2019-12-30 2022-07-29 广东省智能制造研究所 Terrain identification method and system for dynamic motion of foot type robot
CN111198563A (en) * 2019-12-30 2020-05-26 广东省智能制造研究所 Terrain recognition method and system for dynamic motion of foot type robot
CN111243018A (en) * 2019-12-31 2020-06-05 北京航空航天大学 Method and system for automatically performing nevus-removing operation
CN111351446A (en) * 2020-01-10 2020-06-30 奕目(上海)科技有限公司 Light field camera calibration method for three-dimensional topography measurement
CN111351446B (en) * 2020-01-10 2021-09-21 奕目(上海)科技有限公司 Light field camera calibration method for three-dimensional topography measurement
CN111402309A (en) * 2020-03-05 2020-07-10 中国科学院上海微系统与信息技术研究所 Calibration and depth image processing method for multi-view stereo camera
CN111402309B (en) * 2020-03-05 2023-11-03 中国科学院上海微系统与信息技术研究所 Calibration and depth image processing method for multi-view stereo camera
CN111369447B (en) * 2020-03-09 2023-06-16 湖南警察学院 Method for correcting image point in monocular stereoscopic vision image
CN113393413B (en) * 2020-03-11 2022-09-13 河海大学 Water area measuring method and system based on monocular and binocular vision cooperation
CN113393413A (en) * 2020-03-11 2021-09-14 河海大学 Water area measuring method and system based on monocular and binocular vision cooperation
CN111429523A (en) * 2020-03-16 2020-07-17 天目爱视（北京）科技有限公司 Remote calibration method in 3D modeling
CN111429523B (en) * 2020-03-16 2021-06-15 天目爱视（北京）科技有限公司 Remote calibration method in 3D modeling
WO2021196941A1 (en) * 2020-04-03 2021-10-07 浙江商汤科技开发有限公司 Method and apparatus for detecting three-dimensional target
CN111508068A (en) * 2020-04-20 2020-08-07 华中科技大学 Three-dimensional reconstruction method and system applied to binocular endoscope image
CN111553252A (en) * 2020-04-24 2020-08-18 福建农林大学 Road pedestrian automatic identification and positioning method based on deep learning and U-V parallax algorithm
CN111553252B (en) * 2020-04-24 2022-06-07 福建农林大学 Road pedestrian automatic identification and positioning method based on deep learning and U-V parallax algorithm
CN111739359A (en) * 2020-06-30 2020-10-02 上海乂学教育科技有限公司 Augmented reality courseware generation system
CN112085802A (en) * 2020-07-24 2020-12-15 浙江工业大学 Method for acquiring three-dimensional finger vein image based on binocular camera
WO2021139176A1 (en) * 2020-07-30 2021-07-15 平安科技（深圳）有限公司 Pedestrian trajectory tracking method and apparatus based on binocular camera calibration, computer device, and storage medium
CN111899282A (en) * 2020-07-30 2020-11-06 平安科技（深圳）有限公司 Pedestrian trajectory tracking method and device based on binocular camera calibration
CN111899282B (en) * 2020-07-30 2024-05-14 平安科技（深圳）有限公司 Pedestrian track tracking method and device based on binocular camera calibration
CN112097732A (en) * 2020-08-04 2020-12-18 北京中科慧眼科技有限公司 Binocular camera-based three-dimensional distance measurement method, system, equipment and readable storage medium
CN112053781A (en) * 2020-09-16 2020-12-08 四川大学华西医院 Dynamic and static stereoscopic vision testing method and terminal
CN112053781B (en) * 2020-09-16 2023-04-28 四川大学华西医院 Dynamic and static stereoscopic vision testing method and terminal
CN112171635A (en) * 2020-09-24 2021-01-05 上海思寒环保科技有限公司 Remote control robot
CN112013792B (en) * 2020-10-19 2021-02-02 南京知谱光电科技有限公司 Surface scanning three-dimensional reconstruction method for complex large-component robot
CN112258635A (en) * 2020-10-26 2021-01-22 北京石油化工学院 Three-dimensional reconstruction method and device based on improved binocular matching SAD algorithm
CN112379605A (en) * 2020-11-24 2021-02-19 中国人民解放军火箭军工程大学 Bridge crane semi-physical simulation control experiment system and method based on visual servo
CN112465899A (en) * 2020-11-25 2021-03-09 国网福建省电力有限公司电力科学研究院 Binocular vision-based automatic wire peeling and positioning method
CN112465778A (en) * 2020-11-26 2021-03-09 江苏国和智能科技有限公司 Underwater fish shoal observation device and method
CN112734652B (en) * 2020-12-22 2023-03-31 同济大学 Near-infrared blood vessel image projection correction method based on binocular vision
CN112734652A (en) * 2020-12-22 2021-04-30 同济大学 Near-infrared blood vessel image projection correction method based on binocular vision
CN112581542A (en) * 2020-12-24 2021-03-30 北京百度网讯科技有限公司 Method, device and equipment for evaluating automatic driving monocular calibration algorithm
CN112767442A (en) * 2021-01-18 2021-05-07 中山大学 Pedestrian three-dimensional detection tracking method and system based on top view angle
CN112767442B (en) * 2021-01-18 2023-07-21 中山大学 Pedestrian three-dimensional detection tracking method and system based on top view angle
CN113177565A (en) * 2021-03-15 2021-07-27 北京理工大学 Binocular vision position measuring system and method based on deep learning
CN113177565B (en) * 2021-03-15 2023-03-24 北京理工大学 Binocular vision position measuring system and method based on deep learning
CN112991369B (en) * 2021-03-25 2023-11-17 湖北工业大学 Method for detecting outline size of running vehicle based on binocular vision
CN112991369A (en) * 2021-03-25 2021-06-18 湖北工业大学 Method for detecting overall dimension of running vehicle based on binocular vision
CN113052898B (en) * 2021-04-08 2022-07-12 四川大学华西医院 Point cloud and strong-reflection target real-time positioning method based on active binocular camera
CN113052898A (en) * 2021-04-08 2021-06-29 四川大学华西医院 Point cloud and strong-reflection target real-time positioning method based on active binocular camera
CN113099204A (en) * 2021-04-13 2021-07-09 北京航空航天大学青岛研究院 Remote live-action augmented reality method based on VR head-mounted display equipment
CN113077524B (en) * 2021-04-22 2023-12-08 中德（珠海）人工智能研究院有限公司 Automatic calibration method, device and equipment for binocular fisheye camera and storage medium
CN113077524A (en) * 2021-04-22 2021-07-06 中德（珠海）人工智能研究院有限公司 Automatic calibration method, device and equipment for binocular fisheye camera and storage medium
CN113446958A (en) * 2021-06-02 2021-09-28 南京航空航天大学 Binocular vision system based on symmetrical arrangement and curved surface reconstruction method of DIC technology
CN113340241A (en) * 2021-06-09 2021-09-03 河南德朗智能科技有限公司 Binocular vision concrete joint surface roughness measurement method and system
CN113340241B (en) * 2021-06-09 2022-12-02 河南德朗智能科技有限公司 Binocular vision concrete joint surface roughness measurement method and system
CN113379831A (en) * 2021-06-22 2021-09-10 北京航空航天大学青岛研究院 Augmented reality method based on binocular camera and humanoid robot
CN113379831B (en) * 2021-06-22 2022-09-09 北京航空航天大学青岛研究院 Augmented reality method based on binocular camera and humanoid robot
CN113487679B (en) * 2021-06-29 2023-01-03 哈尔滨工程大学 Visual ranging signal processing method for automatic focusing system of laser marking machine
CN113487679A (en) * 2021-06-29 2021-10-08 哈尔滨工程大学 Visual ranging signal processing method for automatic focusing system of laser marking machine
CN113610741A (en) * 2021-08-18 2021-11-05 梅卡曼德（北京）机器人科技有限公司 Point cloud processing method and device based on laser line scanning
CN113963052A (en) * 2021-09-22 2022-01-21 西安交通大学 Large aerostat volume real-time monitoring method based on binocular vision
CN113963052B (en) * 2021-09-22 2023-08-18 西安交通大学 Large aerostat volume real-time monitoring method based on binocular vision
CN113959398B (en) * 2021-10-09 2024-04-12 广东汇天航空航天科技有限公司 Distance measurement method and device based on vision, drivable equipment and storage medium
CN113959398A (en) * 2021-10-09 2022-01-21 广东汇天航空航天科技有限公司 Vision-based distance measurement method and device, travelable equipment and storage medium
CN113989383A (en) * 2021-10-23 2022-01-28 深圳慧源创新科技有限公司 Method for improving accuracy and range of binocular distance measurement
CN113989383B (en) * 2021-10-23 2024-06-04 深圳慧源创新科技有限公司 Method for improving accuracy and range of binocular range
CN114742876A (en) * 2022-06-13 2022-07-12 菏泽市土地储备中心 Land vision stereo measurement method
CN115049980A (en) * 2022-06-16 2022-09-13 威海经济技术开发区天智创新技术研究院 Target object determination method and device based on image and electronic equipment
CN116258759B (en) * 2023-05-15 2023-09-22 北京爱芯科技有限公司 Stereo matching method, device and equipment
CN116258759A (en) * 2023-05-15 2023-06-13 北京爱芯科技有限公司 Stereo matching method, device and equipment

Also Published As

Publication number Publication date
CN103868460B (en) 2016-10-05

Similar Documents

Publication Publication Date Title
CN103868460A (en) Parallax optimization algorithm-based binocular stereo vision automatic measurement method
CN110264567B (en) Real-time three-dimensional modeling method based on mark points
CN110569704A (en) Multi-strategy self-adaptive lane line detection method based on stereoscopic vision
CN104680496B (en) A kind of Kinect depth map restorative procedures based on color images
CN102999892B (en) Based on the depth image of region mask and the intelligent method for fusing of RGB image
CN105225482A (en) Based on vehicle detecting system and the method for binocular stereo vision
CN107560592B (en) Precise distance measurement method for photoelectric tracker linkage target
CN102997891B (en) Device and method for measuring scene depth
CN103971404A (en) 3D real-scene copying device having high cost performance
CN103993548A (en) Multi-camera stereoscopic shooting based pavement damage crack detection system and method
CN104463899A (en) Target object detecting and monitoring method and device
CN104299220A (en) Method for filling cavity in Kinect depth image in real time
CN105258673B (en) A kind of target ranging method based on binocular synthetic aperture focusing image, device
CN111027415B (en) Vehicle detection method based on polarization image
CN117036641A (en) Road scene three-dimensional reconstruction and defect detection method based on binocular vision
CN110288659A (en) A kind of Depth Imaging and information acquisition method based on binocular vision
CN106203429A (en) Based on the shelter target detection method under binocular stereo vision complex background
CN113643345A (en) Multi-view road intelligent identification method based on double-light fusion
CN104182968A (en) Method for segmenting fuzzy moving targets by wide-baseline multi-array optical detection system
CN112561996A (en) Target detection method in autonomous underwater robot recovery docking
CN104778673B (en) A kind of improved gauss hybrid models depth image enhancement method
CN105335959B (en) Imaging device quick focusing method and its equipment
CN115330684A (en) Underwater structure apparent defect detection method based on binocular vision and line structured light
CN110909571B (en) High-precision face recognition space positioning method
Liu et al. The applications and summary of three dimensional reconstruction based on stereo vision

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20161005