阅读说明：本技术 双目立体视觉三维测量方法及系统、服务器及存储介质 (Binocular stereo vision three-dimensional measurement method and system, server and storage medium ) 是由 彭凯 丁毅 薛彧 冯锐 冯文顺 彭麟雅 王学 于 2019-09-02 设计创作，主要内容包括：本发明公开了一种双目立体视觉三维测量方法及系统、服务器及存储介质,其通过投影3种特定频率竖直正弦条纹至物体表面,采用相位测量轮廓术进行条纹分析后,再利用三频率相位展开技术获取绝对相位,通过绝对相位引导双目立体匹配,获得精确的三维测量结果。通过投影结构光的方式,为待测物体增加主动特征,解决被动式立体视觉方法匹配速度慢,在低纹理区域匹配精度低的问题。此外,通过基于频率选择的三频率相位展开技术对变形条纹图像进行相位展开,具有较强的抗噪声性能,能够非常准确的确定变形条纹的绝对相位。(The invention discloses a binocular stereo vision three-dimensional measurement method and system, a server and a storage medium, wherein 3 vertical sinusoidal stripes with specific frequencies are projected on the surface of an object, a phase measurement profilometry is adopted to analyze the stripes, then a three-frequency phase expansion technology is utilized to obtain an absolute phase, and binocular stereo matching is guided through the absolute phase, so that an accurate three-dimensional measurement result is obtained. By means of projecting structured light, active features are added to an object to be measured, and the problems that a passive stereoscopic vision method is low in matching speed and low in matching precision in a low-texture area are solved. In addition, the phase unwrapping is carried out on the deformed fringe image through a three-frequency phase unwrapping technology based on frequency selection, so that the method has strong anti-noise performance and can accurately determine the absolute phase of the deformed fringe.)

1. The binocular stereoscopic vision three-dimensional measurement method is characterized by comprising the following steps:

Respectively projecting three vertical sine stripes with specific frequency to the surface of an object to be measured, projecting three frames of phase shift images at each frequency, and shooting stripe images projected to the surface of the object to be measured to be deformed by a left camera and a right camera;

Performing fringe analysis on the three-frequency fringe image through a phase measurement profilometry to obtain a wrapping phase of a point and generate a three-frequency wrapping phase diagram;

phase unwrapping is carried out on the obtained three-frequency wrapped phase diagram through a three-frequency phase unwrapping technology, and absolute phases of the points are obtained;

Taking the absolute phase difference of corresponding points on the left image and the right image as matching cost, and performing binocular stereo matching to obtain a matching disparity map;

and recovering the three-dimensional appearance information of the object from the disparity map according to the disparity principle.

2. The binocular stereoscopic three-dimensional measurement method according to claim 1, wherein a greatest common factor of the three specific frequencies is 1.

3. The binocular stereo vision three-dimensional measurement method according to claim 2, wherein each group is composed of a plurality of groupsand a unique set n₁(x,y),n₂(x,y),n₃(x, y) corresponds to, n₁(x,y),n₂(x,y),n₃(x, y) is the order of the fringe periods, i.e., the order of the fringes, at different frequencies for the same corresponding point.

4. The binocular stereoscopic three-dimensional measurement method according to claim 1, wherein the three phase-shifted images of each frequency projection are sequentially shifted by 2 pi/3 of phase.

5. The binocular stereoscopic vision three-dimensional measurement method according to claim 1, wherein the three-frequency fringe image is subjected to fringe analysis through phase measurement profilometry to obtain wrapping phases of points, and a three-frequency wrapping phase diagram is generated; the method comprises the following specific steps:

a) Acquiring a deformation stripe image gray value, and expressing as:

wherein f is the spatial frequency of the fundamental frequency component of the projection fringe, phi is the wrapping phase, and M is the phase shift frame number; k denotes the current order of the harmonics, i.e. the kth harmonic, b_kis the amplitude of the kth harmonic component relative to f₀The change is slow, and can be regarded as constant processing, M represents the frame sequence of the image, namely the M-th frame image, and M is 3, M is 1,2 and 3 for the three-frame phase-shift profile technology.

b) calculating intermediate variable D of left and right images_A,D_B：

c) Calculating the wrapping phase:

6. The binocular stereoscopic vision three-dimensional measurement method according to claim 1, wherein the obtained three-frequency wrapped phase diagram is subjected to phase unwrapping by a three-frequency phase unwrapping technique to obtain absolute phases of points; the method comprises the following specific steps:

a) EstablishingAnd n₁,n₂,n₃The mapping relationship between the two;

b) after the mapping relation table is obtained, the intermediate variable of the point (x, y) is calculated Finding the stripe order n corresponding to the point in the mapping relation table according to the intermediate variable value of the point obtained by calculation₁(x,y),n₂(x,y),n₃(x,y)；

c) Calculating the absolute phase phi of the corresponding point by₁,Φ₂,Φ₃：

d) the absolute phase phi of the left image and the right image under 3 frequencies can be calculated by repeating the step c_1L,Φ_1R,Φ_2L,Φ_2R,Φ_3L,Φ_3R。

7. The binocular stereoscopic vision three-dimensional measurement method according to claim 1, wherein the absolute phase difference of corresponding points on the left and right images is used as a matching cost to perform binocular stereoscopic matching to obtain a matching disparity map; the method comprises the following specific steps:

a) Taking the right graph as a reference graph, traversing points on the right graph, and establishing the following constraint for one point (x, y) on the right graph:

min D, max D is the parallax range of left and right image matching, N_R(x,y),N_L(x, y) is the fringe order obtained by phase unwrapping; traversing the points which meet the constraint condition in the left graph one by one;

b) Calculating the absolute phase difference of the points to be matched as the matching cost:

C(x,y,d)＝|Φ_R(x,y)-Φ_L(x+d,y)|

Selecting a matching point with the minimum matching cost in the constraint condition as a parallax matching result;

c) Performing sub-pixel estimation on the parallax matching result to respectively obtain the matching cost C of the optimal matching point₂And the matching cost C of its left and right neighbors₁,C₃Calculating the sub-pixel position d of the best matching point_s：

d_s＝d-(C₃-C₁)/2*(C₁-2*C₂+C₃)

where d is the disparity value of the best matching point.

8. The binocular stereoscopic vision three-dimensional measurement system is characterized by comprising the following functional modules:

The image projection module is used for projecting three vertical sinusoidal stripes with specific frequency to the surface of an object to be measured respectively, projecting three frames of phase shift images at each frequency, and shooting stripe images projected to the surface of the object to be measured to be deformed by a left camera and a right camera;

the fringe analysis module is used for carrying out fringe analysis on the three-frequency fringe image through phase measurement profilometry to obtain the wrapping phase of the point and generate a three-frequency wrapping phase diagram;

The phase unwrapping module is used for unwrapping the phase of the obtained three-frequency wrapped phase diagram through a three-frequency phase unwrapping technology to obtain the absolute phase of the point;

The stereo matching module is used for performing binocular stereo matching by taking the absolute phase difference of corresponding points on the left image and the right image as matching cost to obtain a matching disparity map;

and the parallax recovery module is used for recovering the three-dimensional appearance information of the object from the parallax map according to the parallax principle.

9. a server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the binocular stereo three-dimensional measurement method according to any one of claims 1 to 7.

10. a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the binocular stereo vision three-dimensional measurement method according to any one of claims 1 to 7.

Technical Field

The invention relates to the technical field of three-dimensional measurement, in particular to a binocular stereoscopic vision three-dimensional measurement method and system, a server and a storage medium.

Background

Three-dimensional measurement refers to a technique for acquiring three-dimensional topography of an object by using a certain method and equipment. The high-precision three-dimensional measurement technology is widely applied to the fields of measurement and processing of precision industrial components, reconstruction of medical images, aviation mapping, reverse reconstruction of model instruments and the like. Emerging technical fields such as unmanned driving, intelligent robots, smart cities and the like which rise with the rise of artificial intelligence waves need participation of three-dimensional measurement technology. The binocular stereo vision method and the structured light three-dimensional measurement method are two three-dimensional measurement technologies which are most widely applied at present. The binocular stereo vision method is a passive three-dimensional measurement technology based on the human eye object viewing principle, under the condition of not introducing an active light source, corresponding points of images shot by different cameras are matched according to characteristic information of the images such as color, gradient and gray scale, and then object three-dimensional information is recovered according to the parallax principle. The method is simple to operate and wide in application range, but the method is difficult to find the matching point for the low-texture area, low in matching precision, poor in measurement result and low in processing speed. The structured light three-dimensional measurement technology is an active three-dimensional vision method for recovering scene three-dimensional data according to a modulated and deformed coding template by projecting a coding template image to a scene to be measured. The main problem of the structured light three-dimensional measurement technology is that the structured light three-dimensional measurement method needs to limit an object to be measured on a fixed reference plane and is sensitive to reflected light. The advantages and disadvantages of the stereo vision method and the structured light three-dimensional measurement method are respectively good and bad, and the advantages and disadvantages of the stereo vision method and the structured light three-dimensional measurement method are just complemented under many conditions, so that in recent years, many experts and scholars are studying how to reasonably combine the stereo vision method and the structured light three-dimensional measurement method so as to realize the three-dimensional measurement method with high real-time precision and high robustness

At present, the binocular stereo vision three-dimensional measurement technology based on structured light mainly has the following forms. One is an algorithm for guiding binocular stereo matching by using projection structured light edge characteristics, such as a stereo vision algorithm for projecting structured light signals of grids, binary stripes, color stripes and the like, and the method cannot fully utilize characteristic information in the grids and the stripes and cannot obtain higher measurement accuracy. The other type is a structured light stereo vision method based on sine projection stripe signals, the light intensity of the sine stripe signals changes in a sine rule, relative phase information is obtained through a stripe analysis technology, and after an absolute phase is obtained through a phase unwrapping technology, phase characteristics accurate to a unit pixel can be obtained, high-precision stereo matching is achieved, and therefore the method is widely applied to the field of structured light stereo vision.

In the industrial application of structured light stereo vision, the existing method is still deficient in real-time performance and measurement accuracy, and many structured light stereo vision systems need to improve the measurement accuracy and reduce the matching time by using a way of pasting a physical label on the surface of an object to be measured as a guiding way, which often causes inconvenience or limits the application range of the system in practical application. Therefore, it is necessary to search a real-time structured light stereo vision three-dimensional measurement scheme with higher precision and high reliability.

disclosure of Invention

In view of this, embodiments of the present invention provide a binocular stereoscopic vision three-dimensional measurement method and system, a server, and a storage medium, which have the advantages of strong real-time performance, high accuracy, strong anti-noise performance, and the like, and can solve the problems of poor real-time performance and measurement accuracy, limited application range, and the like in the prior art.

In a first aspect of the embodiments of the present invention, a binocular stereoscopic vision three-dimensional measurement method is provided, where the binocular stereoscopic vision three-dimensional measurement method includes the following steps:

Respectively projecting three vertical sine stripes with specific frequency to the surface of an object to be measured, projecting three frames of phase shift images at each frequency, and shooting stripe images projected to the surface of the object to be measured to be deformed by a left camera and a right camera;

Performing fringe analysis on the three-frequency fringe image through a phase measurement profilometry to obtain a wrapping phase of a point and generate a three-frequency wrapping phase diagram;

Phase unwrapping is carried out on the obtained three-frequency wrapped phase diagram through a three-frequency phase unwrapping technology, and absolute phases of the points are obtained;

taking the absolute phase difference of corresponding points on the left image and the right image as matching cost, and performing binocular stereo matching to obtain a matching disparity map;

and recovering the three-dimensional appearance information of the object from the disparity map according to the disparity principle.

in a second aspect of the embodiments of the present invention, there is provided a binocular stereoscopic vision three-dimensional measurement system, including the following functional modules:

The image projection module is used for projecting three vertical sinusoidal stripes with specific frequency to the surface of an object to be measured respectively, projecting three frames of phase shift images at each frequency, and shooting stripe images projected to the surface of the object to be measured to be deformed by a left camera and a right camera;

the fringe analysis module is used for carrying out fringe analysis on the three-frequency fringe image through phase measurement profilometry to obtain the wrapping phase of the point and generate a three-frequency wrapping phase diagram;

the phase unwrapping module is used for unwrapping the phase of the obtained three-frequency wrapped phase diagram through a three-frequency phase unwrapping technology to obtain the absolute phase of the point;

The stereo matching module is used for performing binocular stereo matching by taking the absolute phase difference of corresponding points on the left image and the right image as matching cost to obtain a matching disparity map;

and the parallax recovery module is used for recovering the three-dimensional appearance information of the object from the parallax map according to the parallax principle.

in a third aspect of the embodiments of the present invention, there is provided a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the binocular stereoscopic three-dimensional measurement method as described above when executing the computer program.

In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the binocular stereoscopic vision three-dimensional measurement method as described above.

According to the binocular stereoscopic vision three-dimensional measurement method and system, the server and the storage medium, active characteristics are added to the object to be measured in a projection structured light mode, and the problems that a passive stereoscopic vision method is low in matching speed and low in matching accuracy in a low-texture area are solved. In addition, the phase unwrapping is carried out on the deformed fringe image through a three-frequency phase unwrapping technology based on frequency selection, so that the method has strong anti-noise performance and can accurately determine the absolute phase of the deformed fringe.

drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a flow chart of a binocular stereoscopic vision three-dimensional measurement method provided by an embodiment of the invention;

Fig. 2 is an experimental system diagram of a binocular stereoscopic vision three-dimensional measurement system provided by an embodiment of the invention;

FIG. 3 shows a sinusoidal fringe image (a) f photographed at different frequencies by using the binocular stereo vision three-dimensional measurement method provided by the embodiment of the invention₁＝18(b)f₂＝25(c)f₃＝30；

Fig. 4 is a functional block diagram of a binocular stereoscopic vision three-dimensional measurement system according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

As shown in fig. 1, the binocular stereo vision three-dimensional measurement method provided by the embodiment of the invention includes the following steps:

and S1, projecting three vertical sinusoidal stripes with specific frequency to the surface of the object to be measured respectively, projecting three frames of phase shift images at each frequency, and shooting the stripe images projected to the surface of the object to be measured to be deformed by the left camera and the right camera.

Specifically, fig. 2 shows an experimental system diagram of the binocular stereoscopic vision three-dimensional measurement system provided by the embodiment of the invention. Selecting three frequencies f with a maximum common factor of 1₁,f₂,f₃the vertical sinusoidal stripes of each frequency respectively project three frames of phase shift images to the surface of an object to be measured, the three frames of phase shift images projected by each frequency sequentially shift 2 pi/3 of phase, and the left camera and the right camera shoot the surface of the object to be measured at different frequencies and different phase shift images to obtain a plurality of frames of left deformation stripe images and right deformation stripe images, as shown in fig. 3.

the intensity I of the fringe image can be expressed as:

I＝A*cos(2πfy+φ(x,y))+B

In the formula, a is the fringe amplitude, and B is the standard light intensity, because the light intensity range of projecting apparatus is (0, 255), so a, B value should satisfy:

x is the abscissa of the corresponding point, y is the ordinate of the corresponding point, when the vertical sine stripe is projected, the light intensity of the image in the vertical direction is equal, and the light intensity in the horizontal direction changes in a sine relationship.

S2, carrying out fringe analysis on the three-frequency fringe image through phase measurement profilometry to obtain the wrapping phase phi of the point_1L,φ_1R,φ_2L,φ_2R,φ_3L,φ_3Rgenerating a three-frequency wrapped phase diagram;

the specific operation is as follows:

S21, acquiring the gray value of the deformed stripe image, and expressing as:

Wherein f is the spatial frequency of the fundamental frequency component of the projection fringe, phi is the wrapping phase, and M is the phase shift frame number; k denotes the current order of the harmonics, i.e. the kth harmonic, b_kis the amplitude of the kth harmonic component relative to f₀The change is slow, and can be regarded as constant processing, M represents the frame sequence of the image, namely the M-th frame image, and M is 3, M is 1,2 and 3 for the three-frame phase-shift profile technology.

s22, calculating the intermediate variable D of the left and right images_A,D_B：

s23, calculating wrapping phase:

s3, performing phase unwrapping on the obtained three-frequency wrapped phase diagram through a three-frequency phase unwrapping technology to obtain absolute phases phi of the points under 3 fringe frequencies of the left camera and the right camera_1L,Φ_1R,Φ_2L,Φ_2R,Φ_3L,Φ_3RThe method comprises the following specific operations:

S31, current fringe frequency f₁,f₂,f₃without a common factor greater than 1, each group must be associated with a unique set n₁(x,y),n₂(x,y),n₃(x, y) corresponds to, n₁(x,y),n₂(x,y),n₃(x, y) is the order of fringe periods, i.e. the order of fringes, at different frequencies for the same corresponding point, and thus can be establishedAnd n₁,n₂,n₃the mapping relationship between the two images, for example, the stripe order mapping table established for the stripe images with the selected frequencies of 18, 25 and 30 in table 1;

Table 1: f. of₁＝18,f₂＝25,f₃when equal to 30And n₁(x,y),n₂(x,y),n₃(x, y) mapping relation table:

S32, after obtaining the mapping relation table, calculating the intermediate variable of the point (x, y) Finding the stripe order n corresponding to the point in the mapping relation table according to the intermediate variable value of the point obtained by calculation₁(x,y),n₂(x,y),n₃(x,y)；

s33, calculating the absolute phase phi of the corresponding point by the following formula₁,Φ₂,Φ₃：

S34, repeating the step c to calculate the absolute phase phi of the left and right images under 3 frequencies_1L,Φ_1R,Φ_2L,Φ_2R,Φ_3L,Φ_3R。

s4, theoretically, absolute phase values of a point on an object calculated on the left image and the right image are equal, the absolute phase difference of the left image and the right image is used as matching cost, a binocular stereo matching technology is used for obtaining matching disparity maps of the left image and the right image, and the method comprises the following specific steps:

S41, taking the right graph as a reference graph, traversing the points on the right graph, and establishing the following constraint for one point (x, y) on the right graph:

minX, maxX is the parallax range of the horizontal coordinate of the point in the left and right image matching, N_R(x,y),N_L(x, y) is the fringe order obtained by phase unwrapping; and traversing the points meeting the constraint condition in the left graph one by one.

S42, calculating the absolute phase difference of the points to be matched as the matching cost:

C(x,y,d)＝|Φ_R(x,y)-Φ_L(x+d,y)|

Selecting a matching point with the minimum matching cost in the constraint condition as a parallax matching result, calculating 3 groups of absolute phases obtained in the step 3 to obtain parallax, wherein the high-frequency fringe absolute phase has a larger noise tolerance range, and a more accurate matching result can be obtained.

therefore, in the stereo matching process, the error tolerance range for the absolute phase can be approximated as:

S43, performing sub-pixel estimation on the parallax matching result to respectively obtain the matching cost C of the best matching point₂and the matching cost C of its left and right neighbors₁,C₃calculating the sub-pixel position d of the best matching point_s：

d_s＝d-(C₃-C₁)/2*(C₁-2*C₂+C₃)

where d is the disparity value of the best matching point.

S5, finally, recovering the three-dimensional shape information of the object according to the parallax result, measuring the distance B (Baseline) between the optical axes of the left camera and the right camera, wherein the focal length of the left camera and the right camera is f, and determining the sub-pixel position of a point P (x, y) on the image as d through the step S4_sthe depth Z of the point from the camera system, namely the three-dimensional space Z-axis coordinate of the point P in the camera coordinate system, can be determined:

z＝B*f/d_s。

by adopting the binocular stereoscopic vision three-dimensional measurement method, the active characteristic is added to the object to be measured in a mode of projecting structured light, and the problems of low matching speed and low matching precision in a low-texture area of a passive stereoscopic vision method are solved. In addition, the phase unwrapping is carried out on the deformed fringe image through a three-frequency phase unwrapping technology based on frequency selection, so that the method has strong anti-noise performance and can accurately determine the absolute phase of the deformed fringe.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

The above mainly describes a binocular stereoscopic three-dimensional measurement method, and a binocular stereoscopic three-dimensional measurement system will be described in detail below.

As shown in fig. 4, the binocular stereo vision three-dimensional measurement system includes the following functional modules:

The image projection module 10 is used for projecting three vertical sinusoidal stripes with specific frequency to the surface of an object to be measured respectively, projecting three frames of phase shift images at each frequency, and shooting stripe images projected to the surface of the object to be measured to be deformed by a left camera and a right camera;

The fringe analysis module 20 is configured to perform fringe analysis on the three-frequency fringe image through a phase measurement profilometry, obtain a wrapped phase of a point, and generate a three-frequency wrapped phase map;

The phase unwrapping module 30 is configured to perform phase unwrapping on the obtained three-frequency wrapped phase diagram by using a three-frequency phase unwrapping technique to obtain an absolute phase of a point;

The stereo matching module 40 is used for performing binocular stereo matching by using the absolute phase difference of corresponding points on the left and right images as matching cost to obtain a matching disparity map;

And the parallax recovery module 50 is used for recovering the three-dimensional appearance information of the object from the parallax map according to the parallax principle.

fig. 5 is a schematic diagram of a server structure for binocular stereo vision three-dimensional measurement according to an embodiment of the present invention. The server, which is a device providing computing services, generally refers to a computer with high computing power, and is provided to a plurality of users via a network. As shown in fig. 5, the server 6 of this embodiment includes: a memory 61, a processor 62, and a system bus 63, the memory 61 including an executable program 611 stored thereon, it being understood by those skilled in the art that the terminal device configuration shown in fig. 5 does not constitute a limitation of the terminal device, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.

the following specifically describes each constituent component of the terminal device with reference to fig. 5:

the memory 61 may be used to store software programs and modules, and the processor 62 executes various functional applications and data processing of the terminal by operating the software programs and modules stored in the memory 61. The memory 61 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal, etc. Further, the memory 61 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

the executable program 611 of the binocular stereoscopic three-dimensional measurement method is contained in the memory 61, the executable program 611 may be divided into one or more modules/units, the one or more modules/units are stored in the memory 61 and executed by the processor 62 to complete the transmission of the notification and obtain the notification implementation process, and the one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used for describing the execution process of the computer program 611 in the server 6. For example, the computer program 611 may be divided into an acquisition module, a comparison module, a concatenation module, and a sending module.

The processor 62 is a control center of the server, connects various parts of the entire terminal device using various interfaces and lines, and performs various functions of the terminal and processes data by running or executing software programs and/or modules stored in the memory 61 and calling data stored in the memory 61, thereby performing overall monitoring of the terminal. Alternatively, processor 62 may include one or more processing units; preferably, the processor 62 may integrate an application processor, which primarily handles operating systems, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 62.

The system bus 63 is used to connect functional units inside the computer, and can transmit data information, address information, and control information, and may be, for example, a PCI bus, an ISA bus, a VESA bus, or the like. The instructions of the processor 62 are transmitted to the memory 61 through the bus, the memory 61 feeds data back to the processor 62, and the system bus 63 is responsible for data and instruction interaction between the processor 62 and the memory 61. Of course, the system bus 63 may also access other devices such as network interfaces, display devices, etc.

The server at least includes a CPU, a chipset, a memory, a disk system, and the like, and other components are not described herein again.

in the embodiment of the present invention, the executable program executed by the processor 62 included in the terminal specifically includes: a binocular stereo vision three-dimensional measurement method comprises the following steps:

Respectively projecting three vertical sine stripes with specific frequency to the surface of an object to be measured, projecting three frames of phase shift images at each frequency, and shooting stripe images projected to the surface of the object to be measured to be deformed by a left camera and a right camera;

Performing fringe analysis on the three-frequency fringe image through a phase measurement profilometry to obtain a wrapping phase of a point and generate a three-frequency wrapping phase diagram;

phase unwrapping is carried out on the obtained three-frequency wrapped phase diagram through a three-frequency phase unwrapping technology, and absolute phases of the points are obtained;

Taking the absolute phase difference of corresponding points on the left image and the right image as matching cost, and performing binocular stereo matching to obtain a matching disparity map;

And recovering the three-dimensional appearance information of the object from the disparity map according to the disparity principle.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

in the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art would appreciate that the modules, elements, and/or method steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

the above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.