CN116030145A - Stereo matching method and system for binocular lenses with different focal lengths - Google Patents
Stereo matching method and system for binocular lenses with different focal lengths Download PDFInfo
- Publication number
- CN116030145A CN116030145A CN202310289274.6A CN202310289274A CN116030145A CN 116030145 A CN116030145 A CN 116030145A CN 202310289274 A CN202310289274 A CN 202310289274A CN 116030145 A CN116030145 A CN 116030145A
- Authority
- CN
- China
- Prior art keywords
- binocular
- monocular
- parameter calibration
- normalized
- camera
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003384 imaging method Methods 0.000 claims abstract description 87
- 238000003702 image correction Methods 0.000 claims abstract description 19
- 238000013507 mapping Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a stereo matching method and a system for binocular lenses with different focal lengths, wherein the method comprises the following steps: monocular calibration is respectively carried out on a left camera and a right camera of the binocular system by utilizing a monocular camera model which is created in advance, monocular internal parameters are obtained, so that binocular internal parameter calibration is completed, and the monocular internal parameters comprise a left camera parameter calibration result and a right camera parameter calibration result; shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration; performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter; and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens. The method and the system realize the stereo matching of the binocular lenses with different focal lengths.
Description
Technical Field
The invention relates to the technical field of auxiliary driving, in particular to a stereo matching method and system for binocular lenses with different focal lengths.
Background
With the increasing demand of people for safer and more convenient trips, intelligent driving technology is in the vigorous development period, and the ability to perceive and understand the environment is the basis and premise of an automobile intelligent system. The intelligent vehicle collects the view through the binocular camera, analyzes the view after sensing the surrounding environment, and detects the running condition by providing information to the control system.
When depth estimation is performed on stereo images acquired by a binocular camera, stereo matching is required, and the purpose of the stereo matching is to estimate the correspondence of all pixel points between two corrected images. In an intelligent driving scene, if lenses with different focal lengths are adopted to form a binocular camera, more accurate road surface image conditions can be obtained, but the existing stereo matching algorithm is provided based on two binocular lenses with the same focal length, and the stereo matching requirements of the binocular lenses with different focal lengths cannot be met.
Disclosure of Invention
Therefore, the embodiment of the invention provides a stereo matching method and a system for binocular lenses with different focal lengths, so as to realize the stereo matching of the binocular lenses with different focal lengths.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
the invention provides a stereo matching method for binocular lenses with different focal lengths, which comprises the following steps:
monocular calibration is respectively carried out on a left camera and a right camera of the binocular system by utilizing a monocular camera model which is created in advance, monocular internal parameters are obtained, so that binocular internal parameter calibration is completed, and the monocular internal parameters comprise a left camera parameter calibration result and a right camera parameter calibration result;
shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration;
performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter;
and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens.
In some embodiments, monocular calibration is performed on the left and right cameras of the binocular system by using a monocular camera model created in advance, so as to obtain monocular internal parameters, and then the method further includes:
and carrying out distortion correction on the monocular imaging by using the left-eye camera parameter calibration result and the right-eye camera parameter calibration result so as to obtain a binocular system based on the two distortion corrected images.
In some embodiments, the imaging plane is normalized for the two raw image projection values using a first preset formula;
the first preset formula is:
where (u, v) is the coordinates of the pixel on the imaging plane,
is the coordinates of the pixel on the normalized imaging plane,
is the principal point coordinate on the imaging plane, and f is the lens focal length.
In some embodiments, for points on the normalized imaging plane, the epipolar constraint is satisfied as:
where P (u, v) is the planar coordinates of the point,
and->
Representing the coordinates of points on the normalized imaging plane of the left and right cameras of the binocular system, respectively.
In some embodiments, performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter specifically includes:
on the normalized imaging plane, carrying out coordinate projection mapping on normalized coordinate points of the two monocular cameras;
coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes.
In some embodiments, coordinate projection mapping is performed on the normalized coordinate points of the two monocular cameras using a second preset formula;
the second preset formula is:
wherein,,
is one half of the cross matrix of the translation vector T,/->
Is one-half of the rotation vector and,
is the normalized planar coordinates after epipolar alignment projection.
In some embodiments, coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes using a third preset formula;
the third preset formula is:
wherein,,
is the polar line alignment stateThe normalized plane point coordinates below, (u, v) are the coordinates of the pixel on the imaging plane, +.>
Is the principal point coordinate on the imaging plane, and f is the lens focal length.
The invention also provides a stereo matching system for binocular lenses with different focal lengths, which comprises:
the internal parameter calibration unit is used for respectively carrying out monocular calibration on the left camera and the right camera of the binocular system by utilizing a monocular camera model which is created in advance to obtain monocular internal parameters so as to finish the monocular internal parameter calibration, wherein the monocular internal parameters comprise a left-eye camera parameter calibration result and a right-eye camera parameter calibration result;
the external parameter calibration unit is used for shooting the same target surface by utilizing the binocular system to obtain two original images, normalizing the imaging surfaces of the projection values of the two original images, and extracting limit alignment parameters on the normalized imaging surfaces to finish binocular external parameter calibration;
an image correction unit configured to perform image correction on the original image according to the limit alignment parameter and the monocular internal parameter;
and the result output unit is used for carrying out three-dimensional matching on the binocular system and determining the structural parameters of the binocular lens based on the binocular internal parameter calibration and the binocular external parameter calibration.
The invention also provides an intelligent terminal, which comprises: the device comprises a data acquisition device, a processor and a memory;
the data acquisition device is used for acquiring data; the memory is used for storing one or more program instructions; the processor is configured to execute one or more program instructions to perform the method as described above.
The present invention also provides a computer readable storage medium having embodied therein one or more program instructions for performing the method as described above.
According to the stereo matching method for the binocular lenses with different focal lengths, monocular calibration is respectively carried out on the left camera and the right camera of the binocular system by utilizing the monocular camera model which is created in advance, monocular internal parameters are obtained, so that binocular internal parameter calibration is completed, and the monocular internal parameters comprise a left-eye camera parameter calibration result and a right-eye camera parameter calibration result; shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration; performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter; and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens. Therefore, the invention overcomes the requirement of the traditional stereo matching technology on hardware consistency and provides data support for realizing the stereo matching of the binocular lenses with different focal lengths.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
Fig. 1 is a schematic flow chart of a stereo matching method for binocular lenses with different focal lengths;
FIG. 2 is an equivalent imaging schematic of a binocular camera;
FIG. 3 is a schematic diagram of a comparison of two binocular systems;
FIG. 4 is a schematic illustration of calibration of a different focus binocular camera system;
fig. 5 is a block diagram of a stereo matching system for binocular lenses with different focal lengths.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flow chart of a stereo matching method for binocular lenses with different focal lengths according to the present invention.
In one embodiment, the invention provides a stereo matching method for binocular lenses with different focal lengths, comprising the following steps:
s110: monocular calibration is respectively carried out on a left camera and a right camera of the binocular system by utilizing a monocular camera model which is created in advance, monocular internal parameters are obtained, so that binocular internal parameter calibration is completed, and the monocular internal parameters comprise a left camera parameter calibration result and a right camera parameter calibration result;
s120: shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration;
s130: performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter;
s140: and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens.
Specifically, when based on a stereo matching scheme of binocular systems with different focal lengths of equivalent imaging planes, for binocular images obtained by the binocular systems with different focal lengths, each pixel coordinate of a long-focus lens image is projected onto the equivalent imaging plane with the same focal length as a short-focus lens, as shown in fig. 2, an image of one point in space in an A camera imaged by the long-focus lens is R, an image in a B camera imaged by the short-focus lens is L, then the A camera of the long-focus lens is projected onto the equivalent imaging plane, and an image in the equivalent imaging plane corresponding to the image R is N. The difference between the column pixel coordinates of N in the a-camera equivalent imaging plane and L in the B-camera imaging plane is defined based on the parallax value of the binocular system.
The camera A with a long lens is mapped from an imaging surface to an equivalent imaging surface by adopting a common interpolation method. The stereo matching scheme can adopt a radical creating scheme, namely, firstly extracting local features of pixels, then constructing a cost function based on feature consistency evaluation indexes, searching a path with the globally minimum matching cost in a cost space of feature matching, and changing indexes of corresponding costs on the path to obtain parallax values. It should be understood that the manner adopted in this step is the same as that in the prior art, and will not be described in detail.
When the structural parameters of the binocular cameras with different focal lengths are determined, the parallax space constructed in the previous cycle is based on the matching result obtained based on the related parameters of the short-focus camera. The corresponding binocular system related parameters include:
a baseline (baseline) equal to the baseline parameters of the different focal length binocular system;
focal length (focalingth), equal to the focal length parameter of a short focal length camera;
pel size (pixelsize), equal to the pel size parameter of a short focal length camera;
a principal point (principal point) equal to a principal point coordinate parameter of the short-focal camera;
based on the related parameters, three-dimensional coordinate calculation of the parallax point cloud can be performed by combining the parallax space.
In step S110, monocular calibration is performed on the left and right cameras of the binocular system by using the monocular camera model created in advance, so as to obtain monocular internal parameters, and then the method further includes:
and carrying out distortion correction on the monocular imaging by using the left-eye camera parameter calibration result and the right-eye camera parameter calibration result so as to obtain a binocular system based on the two distortion corrected images.
In a specific use scenario, when the structure of the binocular camera with different focal lengths is designed, conventionally, the binocular system formed by two monocular cameras with the same focal length is generally arranged in a left-right (or up-down) manner, and the epipolar constraint of the binocular camera system occurs in the image row direction (or column direction). In this embodiment, a left-right arrangement is taken as an example, and scheme discussion is performed; however, the same method is also applicable to the case of up-and-down arrangement.
As shown in fig. 3, the right side is a conventional same focal length binocular system, and the left side is a different focal length binocular system to which the present solution belongs. They are identical in structural composition of the binocular camera system, all being arranged side-to-side, and the geometric optical centers of the camera lenses being located on the same horizontal plane.
In step S120, the two original image projection values are normalized to an imaging plane by using a first preset formula;
the first preset formula is:
where (u, v) is the coordinates of the pixel on the imaging plane,
is the coordinates of the pixel on the normalized imaging plane,
is the principal point coordinate on the imaging plane, and f is the lens focal length.
Further, for points on the normalized imaging plane, the epipolar constraint conditions satisfied are:
where P (u, v) is the planar coordinates of the point,
and->
Representing the coordinates of points on the normalized imaging plane of the left and right cameras of the binocular system, respectively.
Specifically, as shown in fig. 4, when the calibration of the binocular cameras with different focal lengths is performed, the same monocular camera model is used for monocular calibration of the left and right cameras, respectively, and the process mainly calibrates focal lengths, principal point coordinates and distortion parameters of the monocular cameras and performs distortion correction on monocular imaging by using the parameters. The binocular system based on the two distortion correction images shoots the same target surface, and images and projects the two cameras with different focuses to a normalized imaging surface respectively, wherein the projection mode is shown in formula 1:
Where (u, v) is the coordinates of the pixel on the imaging plane,
is the coordinates of the pixel on the normalized imaging plane,
is the principal point coordinate on the imaging plane, f is the focal length of the lens, and these two parameters have been calculated in the monocular calibration process. For different focus binocular systems, when the scheme of formula 1 is called to perform normalized coordinate calculation, the principal point coordinates and the lens focal length parameters are also different. Calculating parameters R and T of epipolar constraint based on the normalized plane pixel coordinate values; where R is a rotation vector and T is a translation vector.
For points on the normalized plane, the condition for satisfying epipolar constraint is shown in equation 2:
Where P (u, v) is the planar coordinates of the point,
and->
Representing the coordinates of points on the normalized imaging surface of the left and right cameras of the binocular system, respectively, the left and right cameras being independent of the distribution of the long and short focal length monocular lenses.
In step S130, performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter, specifically including:
on the normalized imaging plane, carrying out coordinate projection mapping on normalized coordinate points of the two monocular cameras;
coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes.
In some embodiments, coordinate projection mapping is performed on the normalized coordinate points of the two monocular cameras using a second preset formula;
the second preset formula is:
wherein,,
is one half of the cross matrix of the translation vector T,/->
Is one-half of the rotation vector and,
is the normalized planar coordinates after epipolar alignment projection.
In some embodiments, coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes using a third preset formula;
the third preset formula is:
wherein,,
is the normalized plane point coordinates in the polar alignment state, (u, v) is the coordinates of the pixel on the imaging plane, +.>
Is the principal point coordinate on the imaging plane, and f is the lens focal length.
Specifically, in the image correction scheme for the binocular camera with different focal lengths, the image correction is performed for the binocular camera with different focal lengths based on the polar alignment parameters R and T obtained in the above formula 2 and the monocular reference obtained in step S110. Firstly, on a normalized imaging plane, coordinate projection mapping is carried out on normalized coordinate points of two monocular cameras, as shown in a formula 3:
Wherein,,
is one half of the cross matrix of the translation vector T,/->
Is one-half of the rotation vector and,
is the normalized planar coordinates after epipolar alignment projection. And then, using a formula 4, mapping coordinates meeting the epipolar constraint of the normalized plane back to the respective imaging planes.
Wherein,,
is the normalized plane point coordinates in the polar alignment state, (u, v) is the coordinates of the pixel on the imaging plane, +.>
Is the principal point coordinate on the imaging plane, and f is the lens focal length. The monocular parameters when using equation 4 are also inconsistent for different focal binocular systems.
In the above specific embodiment, the stereo matching method for binocular lenses with different focal lengths provided by the invention performs monocular calibration on the left and right cameras of the binocular system respectively by using the monocular camera model created in advance to obtain monocular internal parameters so as to complete the monocular internal parameter calibration, wherein the monocular internal parameters comprise a left-eye camera parameter calibration result and a right-eye camera parameter calibration result; shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration; performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter; and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens. Therefore, the invention overcomes the requirement of the traditional stereo matching technology on hardware consistency and provides data support for realizing the stereo matching of the binocular lenses with different focal lengths.
In addition to the above method, the present invention also provides a stereo matching system for binocular lenses with different focal lengths, as shown in fig. 5, the system includes:
an internal parameter calibration unit 501, configured to perform monocular calibration on a left camera and a right camera of the binocular system respectively by using a monocular camera model created in advance, so as to obtain monocular internal parameters, where the monocular internal parameters include a left-eye camera parameter calibration result and a right-eye camera parameter calibration result;
the external parameter calibration unit 502 is configured to take a photograph of the same target surface by using the binocular system to obtain two original images, normalize the projection values of the two original images to an imaging surface, and extract a limit alignment parameter on the normalized imaging surface to complete binocular external parameter calibration;
an image correction unit 503 for performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter;
and a result output unit 504, configured to perform stereo matching on the binocular system and determine structural parameters of the binocular lens based on the binocular internal parameter calibration and the binocular external parameter calibration.
In some embodiments, monocular calibration is performed on the left and right cameras of the binocular system by using a monocular camera model created in advance, so as to obtain monocular internal parameters, and then the method further includes:
and carrying out distortion correction on the monocular imaging by using the left-eye camera parameter calibration result and the right-eye camera parameter calibration result so as to obtain a binocular system based on the two distortion corrected images.
In some embodiments, the imaging plane is normalized for the two raw image projection values using a first preset formula;
the first preset formula is:
where (u, v) is the coordinates of the pixel on the imaging plane,
is the coordinates of the pixel on the normalized imaging plane,
is the principal point coordinate on the imaging plane, and f is the lens focal length.
In some embodiments, for points on the normalized imaging plane, the epipolar constraint is satisfied as:
where P (u, v) is the planar coordinates of the point,
and->
Representing the coordinates of points on the normalized imaging plane of the left and right cameras of the binocular system, respectively.
In some embodiments, performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter specifically includes:
on the normalized imaging plane, carrying out coordinate projection mapping on normalized coordinate points of the two monocular cameras;
coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes.
In some embodiments, coordinate projection mapping is performed on the normalized coordinate points of the two monocular cameras using a second preset formula;
the second preset formula is:
wherein,,
is one half of the cross matrix of the translation vector T,/->
Is one-half of the rotation vector and,
is the normalized planar coordinates after epipolar alignment projection.
In some embodiments, coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes using a third preset formula;
the third preset formula is:
wherein,,
is the normalized plane point coordinates in the polar alignment state, (u, v) is the coordinates of the pixel on the imaging plane, +.>
Is the principal point coordinate on the imaging plane, and f is the lens focal length.
In the above specific embodiment, the stereo matching system for binocular lenses with different focal lengths provided by the invention performs monocular calibration on the left and right cameras of the binocular system respectively by using the monocular camera model created in advance to obtain monocular internal parameters so as to complete the monocular internal parameter calibration, wherein the monocular internal parameters comprise a left-eye camera parameter calibration result and a right-eye camera parameter calibration result; shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration; performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter; and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens. Therefore, the invention overcomes the requirement of the traditional stereo matching technology on hardware consistency and provides data support for realizing the stereo matching of the binocular lenses with different focal lengths.
The invention also provides an intelligent terminal, which comprises: the device comprises a data acquisition device, a processor and a memory;
the data acquisition device is used for acquiring data; the memory is used for storing one or more program instructions; the processor is configured to execute one or more program instructions to perform the method as described above.
Corresponding to the above embodiments, the present invention also provides a computer readable storage medium, which contains one or more program instructions. Wherein the one or more program instructions are for performing the method as described above by a binocular camera depth calibration system.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP for short), an application specific integrated circuit (Application SpecificIntegrated Circuit, ASIC for short), a field programmable gate array (FieldProgrammable Gate Array, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable ROM (Electrically EPROM, EEPROM), or a flash Memory.
The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data RateSDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (directracram, DRRAM).
The storage media described in embodiments of the present invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the present invention may be implemented in a combination of hardware and software. When the software is applied, the corresponding functions may be stored in a computer-readable medium or transmitted as one or more instructions or code on the computer-readable medium. Computer-readable media includes both computer-readable storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the foregoing is by way of illustration and description only, and is not intended to limit the scope of the invention.
Claims (10)
1. A stereo matching method for binocular lenses of different focal lengths, the method comprising:
monocular calibration is respectively carried out on a left camera and a right camera of the binocular system by utilizing a monocular camera model which is created in advance, monocular internal parameters are obtained, so that binocular internal parameter calibration is completed, and the monocular internal parameters comprise a left camera parameter calibration result and a right camera parameter calibration result;
shooting the same target surface by using the binocular system to obtain two original images, normalizing the two original image projection values to form an imaging surface, and extracting limit alignment parameters on the normalized imaging surface to finish binocular external parameter calibration;
performing image correction on the original image according to the limit alignment parameter and the monocular internal parameter;
and based on the binocular internal parameter calibration and the binocular external parameter calibration, carrying out three-dimensional matching on a binocular system and determining structural parameters of the binocular lens.
2. The stereo matching method for binocular lenses of different focal lengths according to claim 1, wherein monocular calibration is performed on the left and right cameras of the binocular system respectively by using a monocular camera model created in advance to obtain monocular internal parameters, and further comprising:
and carrying out distortion correction on the monocular imaging by using the left-eye camera parameter calibration result and the right-eye camera parameter calibration result so as to obtain a binocular system based on the two distortion corrected images.
3. The stereoscopic matching method for different focal length binocular lenses of claim 2, wherein the two original image projection values are normalized to the imaging plane using a first preset formula;
the first preset formula is:
where (u, v) is the coordinates of the pixel on the imaging plane,
is the normalized image on the imaging planeThe coordinates of the element(s),
is the principal point coordinate on the imaging plane, and f is the lens focal length.
4. A stereo matching method for different focal length binocular lenses according to claim 3, wherein for points on the normalized imaging plane, the epipolar constraint condition is satisfied:
5. The stereo matching method for different focal length binocular lenses according to claim 1, wherein the image correction of the original image is performed according to the limit alignment parameter and the monocular internal parameter, specifically comprising:
on the normalized imaging plane, carrying out coordinate projection mapping on normalized coordinate points of the two monocular cameras;
coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes.
6. The stereoscopic matching method for binocular lenses of different focal lengths according to claim 5, wherein the normalized coordinate points of the two monocular cameras are mapped by coordinate projection using a second preset formula;
the second preset formula is:
7. The stereoscopic matching method for different focal length binocular lenses of claim 5, wherein coordinates satisfying the normalized planar epipolar constraint are mapped back to the respective imaging planes using a third preset formula;
the third preset formula is:
8. A stereo matching system for different focal length binocular lenses, the system comprising:
the internal parameter calibration unit is used for respectively carrying out monocular calibration on the left camera and the right camera of the binocular system by utilizing a monocular camera model which is created in advance to obtain monocular internal parameters so as to finish the monocular internal parameter calibration, wherein the monocular internal parameters comprise a left-eye camera parameter calibration result and a right-eye camera parameter calibration result;
the external parameter calibration unit is used for shooting the same target surface by utilizing the binocular system to obtain two original images, normalizing the imaging surfaces of the projection values of the two original images, and extracting limit alignment parameters on the normalized imaging surfaces to finish binocular external parameter calibration;
an image correction unit configured to perform image correction on the original image according to the limit alignment parameter and the monocular internal parameter;
and the result output unit is used for carrying out three-dimensional matching on the binocular system and determining the structural parameters of the binocular lens based on the binocular internal parameter calibration and the binocular external parameter calibration.
9. An intelligent terminal, characterized in that, the intelligent terminal includes: the device comprises a data acquisition device, a processor and a memory;
the data acquisition device is used for acquiring data; the memory is used for storing one or more program instructions; the processor being configured to execute one or more program instructions for performing the method of any of claims 1-7.
10. A computer readable storage medium having one or more program instructions embodied therein for performing the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310289274.6A CN116030145A (en) | 2023-03-23 | 2023-03-23 | Stereo matching method and system for binocular lenses with different focal lengths |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310289274.6A CN116030145A (en) | 2023-03-23 | 2023-03-23 | Stereo matching method and system for binocular lenses with different focal lengths |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116030145A true CN116030145A (en) | 2023-04-28 |
Family
ID=86089461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310289274.6A Pending CN116030145A (en) | 2023-03-23 | 2023-03-23 | Stereo matching method and system for binocular lenses with different focal lengths |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116030145A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578450A (en) * | 2017-09-14 | 2018-01-12 | 长沙全度影像科技有限公司 | A kind of method and system for the demarcation of panorama camera rigging error |
| CN110009690A (en) * | 2019-03-23 | 2019-07-12 | 西安电子科技大学 | Binocular stereo vision image measuring method based on polar curve correction |
| CN112070845A (en) * | 2020-08-31 | 2020-12-11 | 上海爱观视觉科技有限公司 | Calibration method and device of binocular camera and terminal equipment |
| CN113808220A (en) * | 2021-09-24 | 2021-12-17 | 上海闻泰电子科技有限公司 | Calibration method and system of binocular camera, electronic equipment and storage medium |
| JPWO2020188799A1 (en) * | 2019-03-20 | 2021-12-23 | 日本電気株式会社 | Camera calibration device, camera calibration method, and program |
-
2023
- 2023-03-23 CN CN202310289274.6A patent/CN116030145A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578450A (en) * | 2017-09-14 | 2018-01-12 | 长沙全度影像科技有限公司 | A kind of method and system for the demarcation of panorama camera rigging error |
| JPWO2020188799A1 (en) * | 2019-03-20 | 2021-12-23 | 日本電気株式会社 | Camera calibration device, camera calibration method, and program |
| CN110009690A (en) * | 2019-03-23 | 2019-07-12 | 西安电子科技大学 | Binocular stereo vision image measuring method based on polar curve correction |
| CN112070845A (en) * | 2020-08-31 | 2020-12-11 | 上海爱观视觉科技有限公司 | Calibration method and device of binocular camera and terminal equipment |
| CN113808220A (en) * | 2021-09-24 | 2021-12-17 | 上海闻泰电子科技有限公司 | Calibration method and system of binocular camera, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110689581B (en) | Structured light module calibration method, electronic device and computer readable storage medium | |
| CN112906449B (en) | Road surface pothole detection method, system and equipment based on dense disparity map | |
| TWI567693B (en) | Method and system for generating depth information | |
| CN113343745B (en) | Remote target detection method and system based on binocular camera and intelligent terminal | |
| CN111160232B (en) | Front face reconstruction method, device and system | |
| CN107545586B (en) | Depth obtaining method and system based on light field polar line plane image local part | |
| CN110969666B (en) | Binocular camera depth calibration method, device, system and storage medium | |
| CN109963080B (en) | Image acquisition method and device, electronic equipment and computer storage medium | |
| CN110602474B (en) | Method, device and equipment for determining image parallax | |
| CN111882655B (en) | Method, device, system, computer equipment and storage medium for three-dimensional reconstruction | |
| CN113965742B (en) | Dense disparity map extraction method and system based on multi-sensor fusion and intelligent terminal | |
| CN114926521A (en) | Stereo matching method and system based on binocular camera | |
| CN111225201A (en) | Parallax correction method and device, and storage medium | |
| CN115100621A (en) | Ground scene detection method and system based on deep learning network | |
| CN114495043A (en) | Method and system for detecting up-and-down slope road conditions based on binocular vision system and intelligent terminal | |
| CN113240631B (en) | Road surface detection method and system based on RGB-D fusion information and intelligent terminal | |
| JP2023021087A (en) | Binocular image matching method, apparatus, device, and storage medium | |
| CN113763303B (en) | Real-time ground fusion method and system based on binocular stereo vision and intelligent terminal | |
| CN116030145A (en) | Stereo matching method and system for binocular lenses with different focal lengths | |
| CN110148086B (en) | Depth filling method and device for sparse depth map and three-dimensional reconstruction method and device | |
| CN111383255B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN114998412B (en) | Shadow region parallax calculation method and system based on depth network and binocular vision | |
| CN111553850B (en) | Three-dimensional information acquisition method and device based on binocular stereoscopic vision | |
| CN113676719A (en) | Method and system for calculating focusing parameters of binocular stereo camera and intelligent terminal | |
| CN113706622B (en) | Road surface fitting method and system based on binocular stereo vision and intelligent terminal |
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 |
Application publication date: 20230428 |
|
| RJ01 | Rejection of invention patent application after publication |