CN109544622A - A kind of binocular vision solid matching method and system based on MSER - Google Patents

A kind of binocular vision solid matching method and system based on MSER Download PDF

Info

Publication number
CN109544622A
CN109544622A CN201811314491.1A CN201811314491A CN109544622A CN 109544622 A CN109544622 A CN 109544622A CN 201811314491 A CN201811314491 A CN 201811314491A CN 109544622 A CN109544622 A CN 109544622A
Authority
CN
China
Prior art keywords
pixel
parallax value
image
function
matching
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.)
Pending
Application number
CN201811314491.1A
Other languages
Chinese (zh)
Inventor
赵勇
陈天健
李福池
俞正中
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.)
Shenzhen Aipei Science And Technology Co Ltd
Original Assignee
Shenzhen Aipei Science And Technology Co Ltd
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 Shenzhen Aipei Science And Technology Co Ltd filed Critical Shenzhen Aipei Science And Technology Co Ltd
Priority to CN201811314491.1A priority Critical patent/CN109544622A/en
Publication of CN109544622A publication Critical patent/CN109544622A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/593—Depth or shape recovery from multiple images from stereo images
    • G06T7/596—Depth or shape recovery from multiple images from stereo images from three or more stereo images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20228—Disparity calculation for image-based rendering

Abstract

A kind of binocular vision solid matching method and system based on MSER, the binocular vision solid matching method include the steps that obtaining, estimation, conversion, segmentation, polymerization, calculate.Since other pixels in any one pixel and the neighborhood of pixel points may not be on same depth curved surface, some not pixels in same depth can be removed after being so split by MSER algorithm to the neighborhood of pixel points as much as possible, by evading the method for extraordinary image vegetarian refreshments interference come in the robustness for improving matching cost, to which cost polymerize to obtain the higher matching cost function of robustness, so according to matching cost function calculate pixel best parallax value.The accuracy of Stereo matching can be improved conducive to matched corresponding points are correctly found in different visual point images in this way, error hiding occurs when can effectively solve the problems, such as Stereo matching.

Description

A kind of binocular vision solid matching method and system based on MSER
Technical field
The present invention relates to binocular stereo vision fields, and in particular to a kind of binocular vision solid matching method based on MSER And system.
Background technique
It is well known that the light in scene is collected in this accurate imaging system of human eye, pass through nerve center quilt Feeding includes to have been obtained real-time, high-resolution, accurate sense of depth in the brain of hundreds of millions of neurons by parallel processing Feel information.This greatly improves the mankind to the adaptability of environment, and many complicated movements can be accomplished: as walked, Sports drive vehicle and progress scientific experiment etc..
And computer vision is exactly the subject for simulating the vision system of people using computer, it is therefore an objective to according to the two of acquisition Width flat image restores 3D rendering.Currently, the level of computer stereo vision is also far apart with the binocular vision level of the mankind, It therefore is still a very active neighborhood to its research.
Binocular stereo vision (Binocular Stereo Vision) is a kind of important form of computer vision, it is Based on principle of parallax and two images of the imaging device from different position acquisition testees are utilized, it is corresponding by calculating image Position deviation between point, the method to obtain object dimensional geological information.It follows that it by simulate people vision system come The Coping with Reality world, research matched for stereoscopic vision can greatly enhance the perception of computer or robot to environment Ability allows the robot to preferably to adapt to environment, more intelligent, so as to preferably be that people service.By for many years Technology development, binocular stereo vision is in robot vision, aerial mapping, reverse engineering, Military application, medical imaging and work It is applied in the neighborhoods such as industry detection.
Currently, binocular stereo vision has merged the image of two imaging equipments acquisition and has observed the difference between them, makes to count Calculation machine can obtain accurate depth information, establish the corresponding relationship between feature, by the same space physical points in different images Photosites be mapped, this difference is usually referred to as parallax (disparity).However, most important in binocular stereo vision But extremely difficult problem is exactly stereoscopic vision matching problem, i.e., matched corresponding points are found from different visual point images.
Summary of the invention
The present invention solves the technical problem of how to find matched corresponding points from different visual point images, to mention The accuracy of high binocular vision Stereo matching.
According in a first aspect, provide a kind of binocular vision solid matching method based on MSER in a kind of embodiment, including Following steps:
Obtain the image under at least two viewpoints；
Cost estimation is carried out to each pixel in wherein piece image respectively according to preset multiple parallax values, is obtained The corresponding cost function image of each parallax value；
Function conversion is carried out to the corresponding cost function image of each parallax value, obtains the corresponding transfer function of the parallax value Image；
Any one pixel neighborhood of a point on the transfer function image is split according to preset MSER algorithm, is obtained Cut zone where the pixel；
Cost polymerization is carried out to the transfer function image in the cut zone, obtains any one pixel pair The matching cost function answered；
The best parallax value of any one pixel is calculated according to the matching cost function.
It is described that cost estimation is carried out to each pixel in wherein piece image respectively according to preset multiple parallax values, Obtain the corresponding cost function image of each parallax value, comprising:
For a preset parallax value, face of each pixel in wherein piece image under the parallax value is obtained Color, gradient and/or ranking calculate the corresponding functional image of the parallax value according to the color, gradient and/or ranking of the pixel.
For each pixel I (y, x) in wherein piece image, the corresponding cost function image of a parallax value d is calculated, It is formulated as
C (y, x, d)=w1*c_color(y,x,d)+w2*c_grad(y,x,d)+w3*c_rank(y,x,d)
Wherein, w1、w2、w3It is weighted value set by user, c_color is color function, and c_grad is gradient function, C_rank is ranking function, and d is the parallax value of pixel in the row direction；
Parallax value d ∈ 0,1 ..., dmaxAnd dmaxWhen for preset maximum disparity value, it is corresponding to obtain each parallax value Cost function image.
It is described that function conversion is carried out to the corresponding cost function image of each parallax value, obtain the corresponding conversion of the parallax value Functional image, comprising:
Pixel I (y, x) on cost function image c (y, x, d) corresponding for each parallax value, constructs the pixel The neighborhood R (y, x) of I (y, x), so that
R (y, x)={ r (i, j), i ∈ (y-b, y+b), j ∈ (x-b, x+b) }
Wherein, r (i, j) is arbitrary pixel in neighborhood R (y, x), and i, y are the row coordinate of pixel, and j, x are picture The column coordinate of vegetarian refreshments, b are the radius of neighborhood R (y, x)；
Cost function image c (y, x, d) corresponding to each parallax value carries out index conversion, and it is corresponding to obtain the parallax value The only transfer function image sensitive to certain errors, is formulated as
Wherein, e (y, x, d) is the transfer function image after conversion, and exp indicates that exponential function, σ are the ash of neighborhood R (y, x) Spend variance.
It is described that any one pixel neighborhood of a point on the transfer function image is split according to preset MSER algorithm, Obtain the cut zone where the pixel, comprising:
Functional image e (y, x, d) after and conversion corresponding for each parallax value, according to preset MSER algorithm to this The neighborhood R (y, x) of pixel I (y, x) on functional image e (y, x, d) is split, where obtaining pixel I (y, x) Cut zone R ' (y, x).
Cost polymerization is carried out to the transfer function image in the cut zone, obtains any one pixel pair The matching cost function answered, comprising:
On cut zone R ' (y, x), cost polymerization is carried out to the corresponding transfer function image of each parallax value, obtains picture The mathematic(al) representation of the corresponding matching cost function of vegetarian refreshments I (y, x)
Wherein, (i, j) ∈ R ' (y, x) indicates that the pixel in cut zone R ' (y, x), N are in cut zone R ' (y, x) Pixel number, parallax value d ∈ { 0,1 ..., dmax}。
The best parallax value of any one pixel is calculated according to the matching cost function, comprising:
Parallax value d value range 0,1 ..., dmaxIn calculate matching cost function C (y, x, d), obtain minimum letter Parallax value when numerical value, and using the parallax value as best parallax value d*.
According to second aspect, a kind of embodiment provides a kind of binocular vision stereo matching system based on MSER, comprising:
Memory, for storing program；
Processor, for the program by executing the memory storage to realize side described in above-mentioned first aspect Method.
According to the third aspect, a kind of embodiment provides a kind of computer readable storage medium, including program, described program energy It is enough executed by processor to realize method described in above-mentioned first aspect.
The beneficial effect of the application is:
According to a kind of binocular vision solid matching method and system based on MSER of above-described embodiment, the binocular vision is vertical Body matching process includes the steps that obtaining, estimation, conversion, segmentation, polymerization, calculate.Due to any one pixel and the pixel Other pixels in neighborhood may not be on same depth curved surface, then being divided by MSER algorithm the neighborhood of pixel points It can remove some not in the pixel of same depth after cutting, mentioned by evading the method for extraordinary image vegetarian refreshments interference as much as possible The robustness of high matching cost, so that cost polymerize to obtain the higher matching cost function of robustness, and then according to matching cost Function calculate pixel best parallax value.In this way, error hiding occurs when can effectively solve the problems, such as Stereo matching, it is conducive to Matched corresponding points are correctly found in different visual point images, and the accuracy of Stereo matching can be improved.Further, since into MSER algorithm is used when row image segmentation to extract provincial characteristics, is not only more favorable for finding the pixel of same depth, and And can also parametrization setting up procedure in set algorithm optimal parameter, reach the mesh that different settings are carried out for different scenes , it can be improved the application experience of user.
Detailed description of the invention
Fig. 1 is the flow chart of binocular vision solid matching method；
Fig. 2 is the specific flow chart of estimating step and switch process；
Fig. 3 is the specific flow chart of segmentation step；
Fig. 4 is the structure diagram of binocular vision stereo matching system.
Specific embodiment
Below by specific embodiment combination attached drawing, invention is further described in detail.Wherein different embodiments Middle similar component uses associated similar element numbers.In the following embodiments, many datail descriptions be in order to The application is better understood.However, those skilled in the art can recognize without lifting an eyebrow, part of feature It is dispensed, or can be substituted by other elements, material, method in varied situations.In some cases, this Shen Please it is relevant it is some operation there is no in the description show or describe, this is the core in order to avoid the application by mistake More descriptions are flooded, and to those skilled in the art, these relevant operations, which are described in detail, not to be necessary, they Relevant operation can be completely understood according to the general technology knowledge of description and this field in specification.
It is formed respectively in addition, feature described in this description, operation or feature can combine in any suitable way Kind embodiment.Meanwhile each step in method description or movement can also can be aobvious and easy according to those skilled in the art institute The mode carry out sequence exchange or adjustment seen.Therefore, the various sequences in the description and the appended drawings are intended merely to clearly describe a certain A embodiment is not meant to be necessary sequence, and wherein some sequentially must comply with unless otherwise indicated.
It is herein component institute serialization number itself, such as " first ", " second " etc., is only used for distinguishing described object, Without any sequence or art-recognized meanings.And " connection ", " connection " described in the application, unless otherwise instructed, include directly and It is indirectly connected with (connection).
In the Stereo matching of binocular vision, a critical issue is the match point found in left images, to obtain The horizontal position of respective pixel is poor in two images, also referred to as parallax, so that the depth of the pixel may further be calculated Degree.
It is entirely possible to have identical color, texture and gradient etc. not in the pixel of same depth, so this can usually lead It causes that mispairing occurs when Stereo matching, so that further resulting in disparity computation biggish mistake occurs, leverages binocular vision Application in depth measurement.In order to overcome this point, in the solid matching method of existing binocular image, can generally use The pixel of pixel neighboring area estimates the pixel, due to neighboring area pixel there may be with center pixel not In the situation of same depth, therefore there are also biggish not robustness for existing method.For the robustness for improving matching cost, this Shen Please be split using existing MSER algorithm to the neighborhood of center vegetarian refreshments in the technology of existing method, can so use up can The removal of energy ground is some not in the pixel of same depth, improves matching cost by evading the method for extraordinary image vegetarian refreshments interference Robustness, so that cost polymerize to obtain the higher matching cost function of robustness, conducive to the accurate of each pixel is calculated The higher best parallax value of rate.By technical method provided by the present application, can effectively solve that error hiding occurs when Stereo matching The problem of, conducive to matched corresponding points are correctly found in different visual point images, improve the accuracy of Stereo matching.It is another Aspect extracts provincial characteristics due to using MSER algorithm when performing image segmentation, is not only more favorable for finding same depth The pixel of degree, but also can parametrization setting up procedure in set algorithm optimal parameter, reach for different scenes carry out The purpose of difference setting can be improved the application experience of user.
Embodiment one:
Referring to FIG. 1, the application discloses a kind of binocular vision solid matching method based on MSER comprising step S110-S160 illustrates separately below.
Step S110, obtaining step, the main image obtained under at least two viewpoints.In one embodiment, pass through binocular Camera carries out capture to Stereo matching object, since binocular camera constitutes two capture viewpoints, then in the two capture viewpoints Under respectively obtain a frame image.
In another embodiment, capture can be carried out to Stereo matching object by multiple cameras, so can get more Image under a viewpoint.It will be understood to those skilled in the art that the acquisition of binocular vision solid matching method is one in image The best parallax value of a pixel can find the matching corresponding points in another image according to the best parallax value, then, it can To be continued to calculate the best parallax value of all pixels point in image according to this method, between so achievable two width or multiple image The Stereo matching one by one of pixel, and then achieve the effect that image Stereo matching.
Step S120, estimating step, mainly according to preset multiple parallax values respectively to wherein each of piece image Pixel carries out cost estimation, obtains the corresponding cost function image of each parallax value.In one embodiment, see Fig. 2, the step S120 may include step S121-S123, be respectively described below.
Step S121 obtains each pixel in wherein piece image in the parallax for a preset parallax value Color, gradient and/or ranking under value, it is corresponding to calculate the parallax value with the color, gradient and/or ranking according to the pixel Cost function image.For example, c_color can be obtained according to parallax value d for each pixel I (y, x) in wherein piece image (y, x, d), c_grad (y, x, d), c_rank (y, x, d), those functions respectively indicate pixel I (y, x) in the face of parallax value d Color, gradient and ranking.
It should be noted that the present embodiment find left and right two images in match point when, the parallax of definition be two width or The horizontal position of respective pixel is poor in multiple image.
Step S122 calculates the corresponding cost function image of each parallax value.
For each pixel I (y, x) in wherein piece image, the corresponding cost function image of a parallax value d is calculated, It is formulated as
C (y, x, d)=w1*c_color(y,x,d)+w2*c_grad(y,x,d)+w3*c_rank(y,x,d) (1-1)
Wherein, w1、w2、w3It is weighted value set by user, c_color is color function, and c_grad is gradient function, C_rank is ranking function, and d is the parallax value of pixel in the row direction.
Step S123, according to the calculation formula illustrated in step S122, in parallax value d ∈ { 0,1 ..., dmaxAnd dmaxFor When preset maximum disparity value, the corresponding cost function image of each parallax value is obtained, those cost function images can still use c (y, x, d) is indicated, and only there are difference by the d in formula.
Step S130, switch process carry out function conversion to the corresponding cost function image of each parallax value, obtain the view The corresponding transfer function image of difference.In one embodiment, seeing Fig. 2, step S130 may include step S131-S132, below Illustrate respectively.
Step S131 constructs any one pixel neighborhood of a point in cost function image.
In one embodiment, the pixel I on cost function image c (y, x, d) corresponding for each parallax value (y, x) constructs the neighborhood R (y, x) of pixel I (y, x), so that
R (y, x)={ r (i, j), i ∈ (y-b, y+b), j ∈ (x-b, x+b) } (1-2)
Wherein, r (i, j) is arbitrary pixel in neighborhood R (y, x), and i, y are the row coordinate of pixel, and j, x are picture The column coordinate of vegetarian refreshments, b are the radius of neighborhood R (y, x).
Step S132, cost function image c (y, x, d) corresponding to each parallax value carry out function conversion, obtain the view The corresponding only transfer function image sensitive to certain errors of difference, is formulated as
Wherein, e (y, x, d) is the transfer function image after conversion, and exp indicates that exponential function, σ are the ash of neighborhood R (y, x) Spend variance.
It should be noted that according to other parallax value d ∈ { 0,1 ..., dmaxObtained transfer function image can still use e (y, x, d) is indicated, and only there are difference by the d in formula.
It should be noted that transfer function image e (y, x, d) is only sensitive to certain errors, it is embodied in, to biggish Error is insensitive, and to lesser error sensitive, this phenomenon is determined by the solution characteristic of exponential function, is turned here using index The mode changed is conducive to enhance the treatment effect of cost function image c (y, x, d).
It should be noted that being a kind of preferred processing to cost function image c (y, x, the d) method for carrying out index conversion Mode can save step S125 in another embodiment, directly carry out subsequent figure with cost function image c (y, x, d) and cut Processing.
Step S140 divides pixel neighborhood of a point any one on transfer function image according to preset MSER algorithm It cuts, obtains the cut zone where the pixel.In one embodiment, see Fig. 3, step S130 may include step S131- S132 is respectively described below.
Step S141, transfer function image e (y, x, d) corresponding for each parallax value, according to MSER algorithm to this turn The neighborhood R (y, x) of the pixel I (y, x) changed on functional image e (y, x, d) is split, and obtains the place pixel I (y, x) Cut zone R ' (y, x).
It should be noted that MSER (Maximally Stable Extremal Regions, most stable extremal region) is calculated Method be it is a kind of the best extracted region algorithm of performance is considered by industry, which mainly uses different gray thresholds Most stable of region is obtained when carrying out binaryzation to image, has following characteristics: being had not for the affine variation of image grayscale The support collection versus grayscale variation of denaturation, region has stability, can detecte the region of different fine degrees.It is calculated with MSER Method carries out the process of characteristic area extraction to image are as follows: (1) carries out binary conversion treatment to image using a series of gray thresholds； (2) bianry image obtained for each threshold value obtains corresponding black region and white area；(3) than wider gray scale It is exactly MSER that the region of dimensionally stable is kept in threshold range；(4) using specific judgment criteria, (such as dA/dt, A indicate two-value Image-region area, t indicate gray threshold) MSER is evaluated.In fact, MSER is the concept based on watershed: to figure As carrying out binaryzation, binarization threshold taken [0,255], such binary image just undergo one from completely black to complete white process (aerial view constantly risen just as water level), and in this process, the variation that some connected region areas rise with threshold value is very It is small, just it is this region to MSER at this time.Concrete application about MSER algorithm can refer to document (J.Matasa, O.Chuma, M.Urbana,T.Pajdla,“Robust Wide Baseline Stereo from Maximally Stable Extremal Regions ", BMVC2002), since the MSER algorithm is current common image processing techniques, here no longer to its into Row further instruction.
Step S142, according to MSER algorithm described in step S141, transfer function image corresponding to other parallax values Respectively carry out MSER algorithm processing, with the neighborhood R (y, x) to the same pixel I (y, x) on other transfer function images into Row segmentation, still obtains the cut zone R ' (y, x) where pixel I (y, x).
Step S150, polymerization procedure mainly carry out cost polymerization to transfer function image in cut zone, obtain any The corresponding matching cost function of one pixel.
In one embodiment, on cut zone R ' (y, x), to the corresponding transfer function image of each parallax value into The polymerization of row cost, obtains the mathematic(al) representation of the corresponding matching cost function of pixel I (y, x)
Wherein, (i, j) ∈ R ' (y, x) indicates that the pixel in cut zone R ' (y, x), N are in cut zone R ' (y, x) Pixel number, parallax value d ∈ { 0,1 ..., dmax}。
Step S160 calculates step, calculates any one pixel according to the matching cost function C (y, x, d) in step S140 The best parallax value of point.
In one embodiment, in value range { 0, the 1 ..., d of parallax dmaxIn calculate matching cost function C (y, X, d), parallax when minimum function value is obtained, and using the parallax as best parallax value d*.
Correspondingly, disclosed herein as well is a kind of binocular vision stereo matching system 30 based on MSER.Referring to FIG. 5, The system includes memory 301 and processor 302, wherein memory 301 is for storing program, and processor 302 is for passing through The program of the storage of memory 301 is executed to realize method described in step S110-S150.
It will be understood by those skilled in the art that all or part of function of various methods can pass through in above embodiment The mode of hardware is realized, can also be realized by way of computer program.When function all or part of in above embodiment When being realized by way of computer program, which be can be stored in a computer readable storage medium, and storage medium can To include: read-only memory, random access memory, disk, CD, hard disk etc., it is above-mentioned to realize which is executed by computer Function.For example, program is stored in the memory of equipment, when executing program in memory by processor, can be realized State all or part of function.In addition, when function all or part of in above embodiment is realized by way of computer program When, which also can store in storage mediums such as server, another computer, disk, CD, flash disk or mobile hard disks In, through downloading or copying and saving into the memory of local device, or version updating is carried out to the system of local device, when logical When crossing the program in processor execution memory, all or part of function in above embodiment can be realized.
Use above specific case is illustrated the present invention, is merely used to help understand the present invention, not to limit The system present invention.For those skilled in the art, according to the thought of the present invention, can also make several simple It deduces, deform or replaces.

Claims (9)

1. a kind of binocular vision solid matching method based on MSER, which comprises the following steps:
Obtain the image under at least two viewpoints；
Cost estimation is carried out to each pixel in wherein piece image respectively according to preset multiple parallax values, is obtained each The corresponding cost function image of parallax value；
Function conversion is carried out to the corresponding cost function image of each parallax value, obtains the corresponding transfer function figure of the parallax value Picture；
Any one pixel neighborhood of a point on the transfer function image is split according to preset MSER algorithm, obtains the picture Cut zone where vegetarian refreshments；
Cost polymerization is carried out to the transfer function image in the cut zone, it is corresponding to obtain any one pixel Matching cost function；
The best parallax value of any one pixel is calculated according to the matching cost function.
2. binocular vision solid matching method as described in claim 1, which is characterized in that described according to preset multiple parallaxes Value carries out cost estimation to each pixel in wherein piece image respectively, obtains the corresponding cost function figure of each parallax value Picture, comprising:
For a preset parallax value, color of each pixel in wherein piece image under the parallax value, ladder are obtained Degree and/or ranking, calculate the corresponding functional image of the parallax value according to the color, gradient and/or ranking of the pixel.
3. binocular vision solid matching method as claimed in claim 2, which is characterized in that
For each pixel I (y, x) in wherein piece image, the corresponding cost function image of a parallax value d is calculated, with public affairs Formula is expressed as
C (y, x, d)=w1*c_color(y,x,d)+w2*c_grad(y,x,d)+w3*c_rank(y,x,d)
Wherein, w1、w2、w3It is weighted value set by user, c_color is color function, and c_grad is gradient function, c_ Rank is ranking function, and d is the parallax value of pixel in the row direction；
Parallax value d ∈ 0,1 ..., dmaxAnd dmaxWhen for preset maximum disparity value, each parallax value corresponding generation is obtained Valence functional image.
4. binocular vision solid matching method as claimed in claim 3, which is characterized in that described corresponding to each parallax value Cost function image carries out function conversion, obtains the corresponding transfer function image of the parallax value, comprising:
Pixel I (y, x) on cost function image c (y, x, d) corresponding for each parallax value, construct pixel I (y, X) neighborhood R (y, x), so that
R (y, x)={ r (i, j), i ∈ (y-b, y+b), j ∈ (x-b, x+b) }
Wherein, r (i, j) is arbitrary pixel in neighborhood R (y, x), and i, y are the row coordinate of pixel, and j, x are pixel Column coordinate, b be neighborhood R (y, x) radius；
Cost function image c (y, x, d) corresponding to each parallax value carries out index conversion, and it is corresponding only right to obtain the parallax value The transfer function image of certain errors sensitivity, is formulated as
Wherein, e (y, x, d) is the transfer function image after conversion, and exp indicates that exponential function, σ are the gray scale side of neighborhood R (y, x) Difference.
5. binocular vision solid matching method as claimed in claim 4, which is characterized in that described according to preset MSER algorithm Any one pixel neighborhood of a point on the transfer function image is split, the cut zone where the pixel is obtained, is wrapped It includes:
Functional image e (y, x, d) after and conversion corresponding for each parallax value, according to preset MSER algorithm to the function The neighborhood R (y, x) of pixel I (y, x) on image e (y, x, d) is split, and obtains the segmentation where pixel I (y, x) Region R ' (y, x).
6. binocular vision solid matching method as claimed in claim 5, which is characterized in that described in the cut zone Transfer function image carries out cost polymerization, obtains the corresponding matching cost function of any one pixel, comprising:
On cut zone R ' (y, x), cost polymerization is carried out to the corresponding transfer function image of each parallax value, obtains pixel The mathematic(al) representation of the corresponding matching cost function of I (y, x)
Wherein, (i, j) ∈ R ' (y, x) indicates that the pixel in cut zone R ' (y, x), N are the picture in cut zone R ' (y, x) The number of vegetarian refreshments, parallax value d ∈ { 0,1 ..., dmax}。
7. binocular vision solid matching method as described in claim 1, which is characterized in that according to the matching cost function meter Calculate the best parallax value of any one pixel, comprising:
Parallax value d value range 0,1 ..., dmaxIn calculate matching cost function C (y, x, d), obtain minimum function value When parallax value, and using the parallax value as best parallax value d*.
8. a kind of binocular vision stereo matching system based on MSER characterized by comprising
Memory, for storing program；
Processor, for the program by executing the memory storage to realize as of any of claims 1-7 Method.
9. a kind of computer readable storage medium, which is characterized in that including program, described program can be executed by processor with reality Now such as method of any of claims 1-7.
CN201811314491.1A 2018-11-06 2018-11-06 A kind of binocular vision solid matching method and system based on MSER Pending CN109544622A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811314491.1A CN109544622A (en) 2018-11-06 2018-11-06 A kind of binocular vision solid matching method and system based on MSER

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811314491.1A CN109544622A (en) 2018-11-06 2018-11-06 A kind of binocular vision solid matching method and system based on MSER

Publications (1)

Publication Number Publication Date
CN109544622A true CN109544622A (en) 2019-03-29

Family

ID=65846140

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811314491.1A Pending CN109544622A (en) 2018-11-06 2018-11-06 A kind of binocular vision solid matching method and system based on MSER

Country Status (1)

Country Link
CN (1) CN109544622A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110443186A (en) * 2019-07-31 2019-11-12 深圳市道通智能航空技术有限公司 Solid matching method, picture processing chip and mobile carrier
CN111295667A (en) * 2019-04-24 2020-06-16 深圳市大疆创新科技有限公司 Image stereo matching method and driving assisting device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7991228B2 (en) * 2005-08-02 2011-08-02 Microsoft Corporation Stereo image segmentation
CN107301642A (en) * 2017-06-01 2017-10-27 中国人民解放军国防科学技术大学 A kind of full-automatic prospect background segregation method based on binocular vision
CN108305280A (en) * 2018-01-04 2018-07-20 北京大学深圳研究生院 A kind of solid matching method and system of the binocular image based on minimum spanning tree

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7991228B2 (en) * 2005-08-02 2011-08-02 Microsoft Corporation Stereo image segmentation
CN107301642A (en) * 2017-06-01 2017-10-27 中国人民解放军国防科学技术大学 A kind of full-automatic prospect background segregation method based on binocular vision
CN108305280A (en) * 2018-01-04 2018-07-20 北京大学深圳研究生院 A kind of solid matching method and system of the binocular image based on minimum spanning tree

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111295667A (en) * 2019-04-24 2020-06-16 深圳市大疆创新科技有限公司 Image stereo matching method and driving assisting device
CN110443186A (en) * 2019-07-31 2019-11-12 深圳市道通智能航空技术有限公司 Solid matching method, picture processing chip and mobile carrier
CN110443186B (en) * 2019-07-31 2022-04-15 深圳市道通智能航空技术股份有限公司 Stereo matching method, image processing chip and mobile carrier

Similar Documents

Publication Publication Date Title
Tao et al. Depth from combining defocus and correspondence using light-field cameras
JP6295645B2 (en) Object detection method and object detection apparatus
CN112634341B (en) Method for constructing depth estimation model of multi-vision task cooperation
Hua et al. Holopix50k: A large-scale in-the-wild stereo image dataset
CN109978934B (en) Binocular vision stereo matching method and system based on matching cost weighting
Sheng et al. Geometric occlusion analysis in depth estimation using integral guided filter for light-field image
CA2650557A1 (en) System and method for three-dimensional object reconstruction from two-dimensional images
CN102982334B (en) The sparse disparities acquisition methods of based target edge feature and grey similarity
CN108596975A (en) A kind of Stereo Matching Algorithm for weak texture region
WO2014180255A1 (en) Data processing method, apparatus, computer storage medium and user terminal
Liu et al. High quality depth map estimation of object surface from light-field images
Baig et al. Im2depth: Scalable exemplar based depth transfer
CN110443228B (en) Pedestrian matching method and device, electronic equipment and storage medium
CN104243970A (en) 3D drawn image objective quality evaluation method based on stereoscopic vision attention mechanism and structural similarity
CN109544622A (en) A kind of binocular vision solid matching method and system based on MSER
CN115375745A (en) Absolute depth measurement method based on polarization microlens light field image parallax angle
CN109961092B (en) Binocular vision stereo matching method and system based on parallax anchor point
CN109522833A (en) A kind of binocular vision solid matching method and system for Road Detection
CN109544619A (en) A kind of binocular vision solid matching method cut based on figure and system
CN108062765A (en) Binocular image processing method, imaging device and electronic equipment
Yang et al. An Occlusion and Noise-aware Stereo Framework Based on Light Field Imaging for Robust Disparity Estimation
KR101154436B1 (en) Line matching method based on intersection context
CN109978928B (en) Binocular vision stereo matching method and system based on weighted voting
CN113808185B (en) Image depth recovery method, electronic device and storage medium
Park et al. A tensor voting approach for multi-view 3D scene flow estimation and refinement

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190329