CN110176035A - Localization method, device, computer equipment and the storage medium of index point - Google Patents
Localization method, device, computer equipment and the storage medium of index point Download PDFInfo
- Publication number
- CN110176035A CN110176035A CN201910378889.XA CN201910378889A CN110176035A CN 110176035 A CN110176035 A CN 110176035A CN 201910378889 A CN201910378889 A CN 201910378889A CN 110176035 A CN110176035 A CN 110176035A
- Authority
- CN
- China
- Prior art keywords
- initial
- image
- dimensional coordinate
- visual angle
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000004807 localization Effects 0.000 title abstract 3
- 230000000007 visual effect Effects 0.000 claims description 106
- 239000003550 marker Substances 0.000 claims description 70
- 230000006870 function Effects 0.000 claims description 36
- 238000005457 optimization Methods 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 27
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000036544 posture Effects 0.000 description 33
- 238000010586 diagram Methods 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
This application involves a kind of localization method of index point, device, computer equipment and storage mediums.The described method includes: obtaining multiple multi-view images；Selection meets the first multi-view image and the second multi-view image of the first preset condition from each multi-view image；First preset condition is used to limit the baseline range and index point number of first multi-view image and the second multi-view image；According to the first index point of identical code value in first multi-view image and second multi-view image, initial three-dimensional coordinate set is obtained；According to the initial three-dimensional coordinate set, determine the three-dimensional coordinate of the index point of each multi-view image, pass through the localization method of above-mentioned index point, without according to the initial three-dimensional coordinate for pre-setting special sign point (encoded point at cross line), realize the positioning of index point, even for the encoded point of non-Cross ruler annulus shape, the positioning of index point also may be implemented, and with strong applicability.
Description
Technical Field
The present application relates to the field of camera measurement, and in particular, to a method and an apparatus for locating a landmark, a computer device, and a storage medium.
Background
With the rapid development of computers and optical devices, the technology for realizing three-dimensional reconstruction of objects by using the optical devices has also been rapidly developed. Specifically, a digital camera is used as an image sensor, coding points are arranged on the surface of an object to be detected, the coding points are identified and detected, the spatial positions of the coding points are determined, and further the detection of three-dimensional information of certain specific points on the surface of the object to be detected can be realized.
A common method for locating a mark point generally includes setting an initial three-dimensional coordinate of a specific coding point in advance, and then implementing three-dimensional reconstruction of the coding point according to the initial three-dimensional coordinate. For example, the three-dimensional coordinates of the code points on the cross-bar circle are generally known, but when the measuring distance is long, a relatively large cross-bar is generally needed to locate the code points by using the three-dimensional coordinates of the code points on the cross-bar circle.
Therefore, the positioning method of the mark point has the problem of poor applicability.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for locating a mark point with high applicability.
A method of locating a landmark, the method comprising:
acquiring a plurality of view angle images; each of the perspective images includes a plurality of landmark points;
selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
acquiring an initial three-dimensional coordinate set according to first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set.
In one embodiment, the acquiring an initial three-dimensional coordinate set according to a first landmark point with the same code value in the first view image and the second view image includes: acquiring a first relative posture of the first visual angle image and the second visual angle image according to the coordinate of the first mark point; and acquiring the initial three-dimensional coordinate set according to the first relative posture and the coordinates of the first mark point.
In one embodiment, the determining three-dimensional coordinates of a landmark point of each of the perspective images according to the initial three-dimensional coordinate set includes:
step a, acquiring a third visual angle image meeting a second preset condition; the second preset condition is used for limiting the number of the mark points of the third visual angle image; b, acquiring a three-dimensional coordinate of a second mark point in the third visual angle image according to the third visual angle image, the initial three-dimensional coordinate and a preset optimization function; the code value of the second landmark point is not included in the initial decoding set; the initial decoding set is a code value corresponding to the first mark point; step c, adding the three-dimensional coordinates of the second mark point into the initial three-dimensional coordinate set to obtain a new three-dimensional coordinate set; adding the decoded value of the second mark point into the initial decoding set to obtain a new decoding set; and repeating the steps a to c until no visual angle image meeting the second preset condition exists, and determining the three-dimensional coordinate set obtained by the ending time as the three-dimensional coordinate set of the mark point of each visual angle image.
In one embodiment, the acquiring the three-dimensional coordinate of the second marker point in the third perspective image according to the third perspective image, the initial three-dimensional coordinate and a preset optimization function includes: optimizing the initial three-dimensional coordinate set by adopting a preset optimization function to obtain an optimized initial three-dimensional coordinate; and obtaining the three-dimensional coordinate of the second mark point in the third visual angle image according to the third visual angle image and the optimized initial three-dimensional coordinate.
In one embodiment, the obtaining the three-dimensional coordinate of the second marker point in the third perspective image according to the third perspective image and the optimized initial three-dimensional coordinate includes: estimating a second relative pose of the third perspective image according to the initial three-dimensional coordinate set and the third perspective image; optimizing the second relative posture and the initial three-dimensional coordinate set according to the preset optimization function to obtain an optimized second relative posture and an optimized initial three-dimensional coordinate; and acquiring the three-dimensional coordinates of a second mark point in the third visual angle image according to the optimized second relative posture.
In one embodiment, the first preset condition includes: a baseline of the first perspective image and the second perspective image is greater than a first baseline threshold and less than a second baseline threshold; the number of the marker points with the same code value in the first view image and the second view image is larger than or equal to a marker point threshold value.
In one embodiment, the method further comprises: and judging whether the mark points in the visual angle images are abnormal or not by adopting a preset judgment method.
In one embodiment, the method further comprises: acquiring the corresponding relation between the same non-coding mark points in each visual angle image by adopting a preset epipolar constraint method; and determining the three-dimensional coordinates of the non-coding mark points of each view image according to the corresponding relation.
A device for locating a landmark, the device comprising:
the first acquisition module is used for acquiring a plurality of view angle images; each of the perspective images includes a plurality of landmark points;
the selection module is used for selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
the second acquisition module is used for acquiring an initial three-dimensional coordinate set according to the first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and the determining module is used for determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the method for locating a landmark point according to any of the embodiments described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for locating a landmark point according to any one of the embodiments described above.
According to the method, the device, the computer equipment and the storage medium for positioning the mark points, the first visual angle image and the second visual angle image which meet the first preset condition are selected from the visual angle images by acquiring the plurality of visual angle images, then the initial three-dimensional coordinate set is acquired according to the first mark points with the same code values in the first visual angle image and the second visual angle image, the three-dimensional coordinates of the mark points of the visual angle images are determined according to the initial three-dimensional coordinate set, the mark points are positioned without setting the initial three-dimensional coordinates of specific mark points (encoding points at the cross connecting line), even for the encoding points in the shape of a non-cross ruler ring, the mark points can be positioned, and the applicability is strong.
Drawings
FIG. 1 is a diagram illustrating an internal structure of a computer device according to an embodiment;
FIG. 2 is a schematic flow chart diagram illustrating a method for locating landmark points in one embodiment;
FIG. 3 is a schematic flowchart of an implementation manner of S203 in the embodiment of FIG. 2;
FIG. 4 is a schematic flow chart illustrating an implementation manner of S204 in the embodiment of FIG. 2;
FIG. 5 is a flowchart illustrating an implementation manner of S402 in the embodiment of FIG. 4;
FIG. 6 is a flowchart illustrating an implementation manner of S502 in the embodiment of FIG. 5;
FIG. 7 is a flowchart illustrating a method for locating a landmark point according to another embodiment;
FIG. 8 is a block diagram showing the structure of a marker point locating device according to an embodiment;
FIG. 9 is a block diagram showing the structure of a marker point locating device in another embodiment;
FIG. 10 is a block diagram showing the structure of a marker point locating device in another embodiment;
FIG. 11 is a block diagram showing the structure of a marker point locating device in another embodiment;
fig. 12 is a block diagram showing a structure of a marker point locating device in another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method for locating a landmark point provided in the embodiment of the present application may be applied to a computer device, where the computer device may be a terminal, and an internal structure diagram of the computer device may be as shown in fig. 1. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of locating a landmark. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
In one embodiment, as shown in fig. 2, a method for locating a landmark is provided, where an execution subject of the method is a computer device shown in fig. 1, and the application relates to a specific implementation process of locating a landmark, including the following steps:
s201, acquiring a plurality of view angle images; each of the perspective images includes a plurality of marker points.
Each view image may include coded mark points and non-coded mark points, or may include only coded mark points. Specifically, a plurality of perspective images can be acquired through the image acquisition device connected with the computer device, for example, the camera can be used for photographing objects to be detected at different perspectives to acquire a plurality of perspective images of the objects to be detected at different perspectives, and then the image acquisition device sends the plurality of perspective images of the objects to be detected to the computer device, and the computer device acquires the plurality of perspective images.
It should be noted that, because the object to be measured is an object with the mark points attached, when the images of each viewing angle are acquired, it needs to be satisfied that at least two images of each viewing angle include the same mark point.
S202, selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first perspective image and the second perspective image.
The base line is the distance between the optical centers of two cameras in the stereoscopic vision system and is used for describing the viewpoint position relationship for shooting two visual angle images, and when the base line is larger, the position difference between the cameras is large, or the change of the rotation or the focal length of the cameras is larger; the first preset condition is used for limiting the number of the mark points of the first view picture and the second view picture of the view picture, where the number of the mark points refers to the number of the coding mark points of the first view picture and the second view picture having the same code value.
Note that, if each view image includes only the coding flag point. Specifically, the coding mark points of each view image can be decoded by a preset decoding algorithm, a code value set corresponding to all the coding mark points of each view image is obtained, and then a first view image and a second view image which meet a first preset condition are selected from the multiple view images according to the code value set to serve as initial view images.
S203, acquiring an initial three-dimensional coordinate set according to first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point.
Wherein, the first marker point refers to a pixel point having the same code value in the first view image and the second view image, for example, the coding marker point { P1, P2, P3, P4, P5, P6, P7, P8} in the first view image has the same code value with the coding marker point { Q1, Q2, Q3, Q4, Q5, Q6, Q7, Q8} in the second view image, the first marker point is { P1, P2, P3, P4, P5, P6, P7, P8} and { Q1, Q2, Q3, Q4, Q5, Q6, Q7, Q8}, and the coordinate of the pixel point corresponding to the coordinate { P1, P2, P3, P4, Q4, P4: { R1, R2, R3, R4, R5, R6, R7, R8}, and mixing Xs: { R1, R2, R3, R4, R5, R6, R7, R8} as an initial set of three-dimensional coordinates.
And S204, determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set.
Specifically, the three-dimensional coordinates of the coding mark points of each view image can be calculated according to the initial three-dimensional coordinate set, and then the three-dimensional coordinates of the non-coding mark points of each view image are calculated on the basis of reconstructing the three-dimensional coordinates of the coding mark points, so as to determine the three-dimensional coordinates of the mark points of each view image.
In the above method for positioning a marker point in the embodiment, because a plurality of view images are acquired, a first view image and a second view image which meet a first preset condition are selected from the view images, then an initial three-dimensional coordinate set is acquired according to the first marker point with the same code value in the first view image and the second view image, and further according to the initial three-dimensional coordinate set, the three-dimensional coordinates of the marker point of each view image are determined, the marker point is positioned without setting the initial three-dimensional coordinates of a specific marker point (a coding point at a cross connecting line) in advance, even for a coding point in a non-cross ruler circular ring shape, the marker point can be positioned, and the applicability is strong.
Fig. 3 provides a specific implementation manner of acquiring an initial three-dimensional coordinate set according to first marker points with the same code value in a first perspective image and a second perspective image, as shown in fig. 3, as an optional implementation manner, S203 "acquiring an initial three-dimensional coordinate set according to first marker points with the same code value in the first perspective image and the second perspective image" includes:
s301, acquiring a first relative posture of the first visual angle image and the second visual angle image according to the coordinate of the first mark point.
Illustratively, if the encoded marker point { P1, P2, P3, P4, P5, P6, P7, P8} in the first perspective image has the same code value as the encoded marker point { Q1, Q2, Q3, Q4, Q5, Q6, Q7, Q8} in the second perspective image, the first marker point is { P1, P2, P3, P4, P5, P6, P7, P8} and { Q1, Q2, Q3, Q4, Q5, Q6, Q7, Q8}, and the first relative posture E is determined from the pixel coordinates of the first marker point; specifically, the first relative attitude E may be calculated by the following equation:
p'TEp＝0
wherein P' and P are any pair of matching points of the first perspective image and the second perspective image, and since { P1, P2, P3, P4, P5, P6, P7, P8} and { Q1, Q2, Q3, Q4, Q5, Q6, Q7, Q8} of the first marker point correspond to each other, the first relative posture E can be obtained through an 8-point algorithm.
S302, acquiring the initial three-dimensional coordinate set according to the first relative posture and the coordinates of the first mark point.
Specifically, the initial set of three-dimensional coordinates may be obtained according to the following formula:
wherein KK is an internal reference matrix, Motion, of the cameraiAnd MotionjThe poses of the first landmark points relative to the world coordinate system, which may be an identity matrix and a first relative pose, respectively;which is used to represent the three-dimensional coordinates of the first marker point,andsetting corresponding pixels with the same encoding point in the first view image and the second view imageAnd solving the formula to obtain the three-dimensional coordinate of the first mark point, namely the initial three-dimensional coordinate.
In the above embodiment, the first relative postures of the first view image and the second view image are obtained according to the coordinates of the first marker point, then the initial three-dimensional coordinate set is obtained according to the first relative postures and the coordinates of the first marker point, and further the three-dimensional coordinates of the marker points of each view image can be determined according to the initial three-dimensional coordinate set, and the positioning of the marker points is realized without setting the initial three-dimensional coordinates of specific marker points in advance, so that the positioning of the marker points can be realized even for non-cross ruler ring-shaped coded marker points, and the method has better applicability.
In one embodiment, as an optional implementation manner, as shown in fig. 4, the step S204 "determining three-dimensional coordinates of a landmark point of each of the perspective images according to the initial three-dimensional coordinate set" includes:
s401, acquiring a third view angle image meeting a second preset condition; the second preset condition is used for limiting the number of the mark points of the third perspective image.
One or more third-view images can be selected; the second preset condition is used to limit the number of the mark points of the third perspective image, where the number of the mark points of the third perspective image refers to the number of the mark points of the third perspective image having the same code value as the first mark point, and alternatively, the second preset condition may be that the mark points have 5 or more than 5 code values as the first mark points. Specifically, a third perspective image meeting a second preset condition is acquired from each perspective image according to the second preset condition. Note that the third perspective image is a perspective image with an estimated pose not being estimated.
S402, acquiring a three-dimensional coordinate of a second mark point in the third visual angle image according to the third visual angle image, the initial three-dimensional coordinate and a preset optimization function; the code value of the second landmark point is not included in the initial decoding set; and the initial decoding set is a code value corresponding to the first mark point.
The preset optimization function is a target optimization function taking the initial three-dimensional coordinate set as a variable, illustratively, the third view images are multiple, for example, the view images 1,2 and 3 are respectively view images, and then the three-dimensional coordinates of the second mark point are obtained according to the view images 1,2, 3, the initial three-dimensional coordinates and the preset optimization function. On the basis of the foregoing embodiment, as an optional implementation manner, in S402, "obtaining a three-dimensional coordinate of a second marker point in a third perspective image according to the third perspective image, the initial three-dimensional coordinate, and a preset optimization function", includes:
s501, optimizing the initial three-dimensional coordinate set by adopting a preset optimization function to obtain an optimized initial three-dimensional coordinate.
Specifically, since the preset optimization function is an objective optimization function using the initial three-dimensional coordinate set, the internal reference matrix, and the like as variables, the optimized initial three-dimensional coordinate can be obtained by optimizing the objective optimization function.
And S502, obtaining the three-dimensional coordinate of the second mark point in the third visual angle image according to the third visual angle image and the optimized initial three-dimensional coordinate.
Optionally, the second relative pose of the third perspective image is estimated according to the initial three-dimensional coordinate set and the third perspective image, the second relative pose is optimized according to a preset optimization function, the optimized second relative pose is obtained, and the three-dimensional coordinate of the second marker point in the third perspective image is obtained according to the optimized second relative pose.
In the above embodiment, the initial three-dimensional coordinate set is optimized by using the preset optimization function to obtain the optimized initial three-dimensional coordinate, and then the three-dimensional coordinate of the second mark point in the third view image is obtained according to the third view image and the optimized initial three-dimensional coordinate.
S403, adding the three-dimensional coordinates of the second mark point into the initial three-dimensional coordinate set to obtain a new three-dimensional coordinate set; and adding the decoded value of the second mark point into the initial decoding set to obtain a new decoding set.
Repeating S401-S403 until no perspective image meeting the second preset condition exists, and determining the three-dimensional coordinate set obtained by the ending time as the three-dimensional coordinate set of the mark point of each perspective image.
Illustratively, from images of each view angle, an image in which there are 5 marker points having the same code values as those of the first marker point and no pose is estimated is acquired, and as a third view angle, for example, the initial code set corresponding to the first marker point is code: {1, 2, 3, 4, 5, 6, 7, 8, 9}, where the three-dimensional coordinates corresponding to the first landmark point, i.e., the initial set of three-dimensional coordinates, is Xs: { R1, R2, R3, R4, R5, R6, R7, R8, R9}, an image with a code value of {1, 2, 3, 4, 5, 10,11,12} corresponding to the image landmark point and an image with a code value of {1, 2, 3, 5, 6, 10,11,12} corresponding to the image landmark point can be used as a third view image, and it should be noted that, because the obtained views of the encoded landmark point are overlapped, further, there are generally encoded points and their corresponding points in the third view image, which have no reconstructed three-dimensional coordinates.
On the basis of the above example, the second marker point is a marker point with a code value of {10,11}, and the three-dimensional coordinate of the second marker point in the third perspective image is obtained according to the third perspective image, the initial three-dimensional coordinate Xs and the preset optimization function, that is, the three-dimensional coordinate corresponding to the marker point with the code value of {10,11} is obtained, and the corresponding three-dimensional coordinate set is { R10, R11 }; adding { R10, R11} in Xs: { R1, R2, R3, R4, R5, R6, R7, R8, R9}, a new three-dimensional coordinate set Xs: { R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11 }; add {10,11} to code: {1, 2, 3, 4, 5, 6, 7, 8, 9}, a new decoding set code: {1, 2, 3, 4, 5, 6, 7, 8, 9, 10,11}, repeating the above steps until no view angle image satisfying the second preset condition exists, and determining the three-dimensional coordinate set obtained at the time of the cutoff as the three-dimensional coordinate set of the mark point of each view angle image.
On the basis of the foregoing embodiment, as an optional implementation manner, in S502, "obtaining a three-dimensional coordinate of a second marker point in a third perspective image according to the third perspective image and the optimized initial three-dimensional coordinate" includes:
s601, estimating a second relative posture of the third perspective image according to the initial three-dimensional coordinate set and the third perspective image.
Illustratively, if the third perspective image includes perspective image 1, perspective image 2, and perspective image 3, then a second relative pose Motion1 of perspective image 1 with respect to the world coordinate system is estimated based on the initial set of three-dimensional coordinates and perspective image 1; estimating 2 a second relative pose of the perspective image 2 with respect to the world coordinate system based on the initial set of three-dimensional coordinates and the perspective image 2; from the initial set of three-dimensional coordinates and the perspective image 3, a second relative pose Motion3 of the perspective image 3 with respect to the world coordinate system is estimated.
Specifically, the three-dimensional point coordinates in space under the world coordinate system may be expressed as: p is a radical ofi wI ═ 1,2, …, n; the three-dimensional point coordinates in space under the camera coordinate system can be expressed as: p is a radical ofi c,i＝1,2,…,n
Defining coordinates of the reference points under four world coordinate systems, wherein linear combination of the coordinates is used for describing three-dimensional point coordinates in space: c. Cj cJ is 1,2, …, n; defining coordinates of the reference points under four camera coordinate systems, and linear combination of the coordinates is used for describing three-dimensional point coordinates in space: c. Cj w,j＝1,2,…,n
Under the world coordinate system, three-dimensional point coordinates in space can be represented by a linear combination of four reference points:
wherein:
the projected relationship of the three-dimensional point coordinates in space to the two-dimensional point coordinates on the image can then be expressed as:
the above expansion can be written as:
in the above formula exceptIn addition, other coefficients constitute a coefficient matrix M, and the above equation can be written as:
x is MTThe linear combination of the null-space feature vectors of M can be expressed as:
β can be estimated by the relative static relationship of the position and the attitude of the reference pointsi；
And getToThen, the spatial three-dimensional point coordinates in the camera coordinate system can be expressed as:wherein,
finally, we pass pi wAnd pi cA second relative pose of the camera may be estimated: p is a radical ofi c＝Motionspi w。
And S602, optimizing the second relative posture and the initial three-dimensional coordinate set according to the preset optimization function, and acquiring the optimized second relative posture and the optimized initial three-dimensional coordinate.
Alternatively, the preset optimization function may be the following objective optimization function:
wherein norm2 represents a two-norm, Oi represents a residual error of a three-dimensional coordinate of a coding mark point in the ith view image projected onto an image plane; KK is an internal reference matrix, Motion, of a single lens reflexiAnd k is the second relative posture of the ith visual angle image, kc is the distortion of the camera lens, and Xj is the three-dimensional coordinate of the ith visual angle image in the world coordinate system corresponding to the jth coding mark point.
S603, acquiring the three-dimensional coordinates of the second mark point in the third visual angle image according to the optimized second relative posture.
Specifically, the three-dimensional coordinates of the second marker point may also be obtained according to the following formula:
in the above embodiment, the initial three-dimensional coordinate set and the second relative character bar are optimized through the preset optimization function, so that the three-dimensional coordinate of the second mark point in the third view image obtained according to the optimized second relative posture is more accurate.
In one embodiment, the first preset condition includes: a baseline of the first perspective image and the second perspective image is greater than a first baseline threshold and less than a second baseline threshold; the number of the marker points with the same code value in the first view image and the second view image is larger than or equal to a marker point threshold value. Illustratively, the first preset condition is that the baseline of the first perspective image and the second perspective image is large, and the first perspective image and the second perspective image have more than 8 marker points with the same code value.
On the basis of the above embodiment, if the mark point is blocked or has low resolution, it may cause a part of the measured object to have a measurement error, and therefore, the mark point needs to be determined. In one embodiment, the method further comprises: and judging whether the mark points in the visual angle images are abnormal or not by adopting a preset judgment method.
Specifically, whether coding mark points in each view image are abnormal or not is judged through a preset judgment method, and if the coding mark points of the view images are abnormal, the view images are removed and are left for subsequent processing; and if the coding mark point of the view image is abnormal, taking the view image as a first view image and a second view image which can be selected and meet a first preset condition.
By adopting a preset judgment method, whether the mark points in each visual angle image are abnormal or not is judged, the visual angle images with lower resolution of the coded mark points, shielding and the like can be processed, the problem of subsequent decoding is avoided, the positioning precision of the whole mark point is influenced, and the precision of the positioning method of the mark points is ensured to a certain extent.
In one embodiment, as shown in fig. 7, the method further includes:
s701, acquiring the corresponding relation between the same non-coding mark points in each view image by adopting a preset epipolar constraint method.
The preset epipolar constraint method may be a three-view epipolar constraint algorithm, and illustratively, if each view image further includes a non-coding mark point, and each view image includes a view image 1, a view image 2, a view image 3, and a view image 4, the non-coding mark points of the view images 1 to 4 may be identified by the three-view epipolar constraint method, so as to obtain a corresponding relationship between the same non-coding mark points in each view image.
S702, determining the three-dimensional coordinates of the non-coding mark points of each view angle image according to the corresponding relation.
And reconstructing the three-dimensional coordinates of the non-coding mark points through the corresponding relation between the second relative posture motion-i of the view image i, the second relative posture motion-j of the view image j and the non-coding mark points of the view image i and the view image j.
By adopting a preset epipolar constraint method, the corresponding relation between the same non-coding mark points in each view image is obtained, and then the three-dimensional coordinates of the non-coding mark points of each view image are determined according to the corresponding relation, so that the positioning of the non-coding mark points can be realized, and the applicability of the positioning method of the mark points provided by the application is wider.
It should be understood that although the various steps in the flow charts of fig. 2-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, there is provided a device for locating a landmark point, including a first obtaining module 11, a selecting module 12, a second obtaining module 13, and a determining module 14, wherein:
a first acquiring module 11, configured to acquire a plurality of perspective images; each of the perspective images includes a plurality of landmark points;
a selecting module 12, configured to select a first perspective image and a second perspective image that satisfy a first preset condition from each of the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
a second obtaining module 13, configured to obtain an initial three-dimensional coordinate set according to a first landmark point with a same code value in the first view image and the second view image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and a determining module 14, configured to determine three-dimensional coordinates of the mark point of each view image according to the initial three-dimensional coordinate set.
On the basis of fig. 8, as shown in fig. 9, in one embodiment, the second obtaining module 13 includes:
a first obtaining unit 130, configured to obtain a first relative posture of the first perspective image and the second perspective image according to the coordinate of the first marker point;
a second obtaining unit 131, configured to obtain the initial three-dimensional coordinate set according to the first relative pose and the coordinate of the first mark point.
On the basis of fig. 8, as shown in fig. 10, in one embodiment, the determining module 14 includes:
a first function unit 140, configured to acquire a third perspective image that satisfies a second preset condition; the second preset condition is used for limiting the number of the mark points of the third visual angle image;
a second function unit 141, configured to obtain a three-dimensional coordinate of a second marker point in a third perspective image according to the third perspective image, the initial three-dimensional coordinate, and a preset optimization function; the code value of the second landmark point is not included in the initial decoding set; the initial decoding set is a code value corresponding to the first mark point;
a third function unit 142, configured to add the three-dimensional coordinate of the second marker point to the initial three-dimensional coordinate set, so as to obtain a new three-dimensional coordinate set; adding the decoded value of the second mark point into the initial decoding set to obtain a new decoding set;
and repeating the first functional unit and the third functional unit until no visual angle image meeting the second preset condition exists, and determining a three-dimensional coordinate set obtained by the ending time as a three-dimensional coordinate set of the mark point of each visual angle image.
In one embodiment, the first functional unit 140 is specifically configured to optimize the initial three-dimensional coordinate set by using a preset optimization function, so as to obtain an optimized initial three-dimensional coordinate; and obtaining the three-dimensional coordinate of the second mark point in the third visual angle image according to the third visual angle image and the optimized initial three-dimensional coordinate.
In one embodiment, the first functional unit 140 is specifically configured to estimate a second relative pose of the third perspective image according to the initial three-dimensional coordinate set and the third perspective image; optimizing the second relative posture and the initial three-dimensional coordinate set according to the preset optimization function to obtain an optimized second relative posture and an optimized initial three-dimensional coordinate; and acquiring the three-dimensional coordinates of a second mark point in the third visual angle image according to the optimized second relative posture.
In one embodiment, the first preset condition includes: a baseline of the first perspective image and the second perspective image is greater than a first baseline threshold and less than a second baseline threshold; the number of the marker points with the same code value in the first view image and the second view image is larger than or equal to a marker point threshold value.
In one embodiment, as shown in fig. 11, the apparatus further includes a decision 15 based on the fig. 8, wherein:
the judging module 15 is configured to judge whether the mark point in each of the view images is abnormal by using a preset judging method.
In one embodiment, as shown in fig. 12, on the basis of fig. 8, the apparatus further includes a third obtaining module 16 and a second determining module 17, wherein:
a third obtaining module 16, configured to obtain, by using a preset epipolar constraint method, a corresponding relationship between identical non-coding mark points in each of the view images;
and a second determining module 17, configured to determine, according to the corresponding relationship, a three-dimensional coordinate of the non-coding mark point of each view image.
For the specific definition of the positioning device of the mark point, reference may be made to the above definition of the positioning method of the mark point, and details are not described herein again. The various modules in the above-described location of the landmark points may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a plurality of view angle images; each of the perspective images includes a plurality of landmark points;
selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
acquiring an initial three-dimensional coordinate set according to first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a first relative posture of the first visual angle image and the second visual angle image according to the coordinate of the first mark point; and acquiring the initial three-dimensional coordinate set according to the first relative posture and the coordinates of the first mark point.
In one embodiment, the processor, when executing the computer program, further performs the steps of: step a, acquiring a third visual angle image meeting a second preset condition; the second preset condition is used for limiting the number of the mark points of the third visual angle image; b, acquiring a three-dimensional coordinate of a second mark point in the third visual angle image according to the third visual angle image, the initial three-dimensional coordinate and a preset optimization function; the code value of the second landmark point is not included in the initial decoding set; the initial decoding set is a code value corresponding to the first mark point; step c, adding the three-dimensional coordinates of the second mark point into the initial three-dimensional coordinate set to obtain a new three-dimensional coordinate set; adding the decoded value of the second mark point into the initial decoding set to obtain a new decoding set; and repeating the steps a to c until no visual angle image meeting the second preset condition exists, and determining the three-dimensional coordinate set obtained by the ending time as the three-dimensional coordinate set of the mark point of each visual angle image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: optimizing the initial three-dimensional coordinate set by adopting a preset optimization function to obtain an optimized initial three-dimensional coordinate; and obtaining the three-dimensional coordinate of the second mark point in the third visual angle image according to the third visual angle image and the optimized initial three-dimensional coordinate.
In one embodiment, the processor, when executing the computer program, further performs the steps of: estimating a second relative pose of the third perspective image according to the initial three-dimensional coordinate set and the third perspective image; optimizing the second relative posture and the initial three-dimensional coordinate set according to the preset optimization function to obtain an optimized second relative posture and an optimized initial three-dimensional coordinate; and acquiring the three-dimensional coordinates of a second mark point in the third visual angle image according to the optimized second relative posture.
In one embodiment, the processor, when executing the computer program, further implements: the first preset condition includes: a baseline of the first perspective image and the second perspective image is greater than a first baseline threshold and less than a second baseline threshold; the number of the marker points with the same code value in the first view image and the second view image is larger than or equal to a marker point threshold value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and judging whether the mark points in the visual angle images are abnormal or not by adopting a preset judgment method.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring the corresponding relation between the same non-coding mark points in each visual angle image by adopting a preset epipolar constraint method; and determining the three-dimensional coordinates of the non-coding mark points of each view image according to the corresponding relation.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a plurality of view angle images; each of the perspective images includes a plurality of landmark points;
selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
acquiring an initial three-dimensional coordinate set according to first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set. In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a first relative posture of the first visual angle image and the second visual angle image according to the coordinate of the first mark point; and acquiring the initial three-dimensional coordinate set according to the first relative posture and the coordinates of the first mark point.
In one embodiment, the computer program when executed by the processor further performs the steps of: step a, acquiring a third visual angle image meeting a second preset condition; the second preset condition is used for limiting the number of the mark points of the third visual angle image; b, acquiring a three-dimensional coordinate of a second mark point in the third visual angle image according to the third visual angle image, the initial three-dimensional coordinate and a preset optimization function; the code value of the second landmark point is not included in the initial decoding set; the initial decoding set is a code value corresponding to the first mark point; step c, adding the three-dimensional coordinates of the second mark point into the initial three-dimensional coordinate set to obtain a new three-dimensional coordinate set; adding the decoded value of the second mark point into the initial decoding set to obtain a new decoding set; and repeating the steps a to c until no visual angle image meeting the second preset condition exists, and determining the three-dimensional coordinate set obtained by the ending time as the three-dimensional coordinate set of the mark point of each visual angle image.
In one embodiment, the computer program when executed by the processor further performs the steps of: optimizing the initial three-dimensional coordinate set by adopting a preset optimization function to obtain an optimized initial three-dimensional coordinate; and obtaining the three-dimensional coordinate of the second mark point in the third visual angle image according to the third visual angle image and the optimized initial three-dimensional coordinate.
In one embodiment, the computer program when executed by the processor further performs the steps of: estimating a second relative pose of the third perspective image according to the initial three-dimensional coordinate set and the third perspective image; optimizing the second relative posture and the initial three-dimensional coordinate set according to the preset optimization function to obtain an optimized second relative posture and an optimized initial three-dimensional coordinate; and acquiring the three-dimensional coordinates of a second mark point in the third visual angle image according to the optimized second relative posture.
In one embodiment, the computer program when executed by the processor further performs the steps of: a baseline of the first perspective image and the second perspective image is greater than a first baseline threshold and less than a second baseline threshold; the number of the marker points with the same code value in the first view image and the second view image is larger than or equal to a marker point threshold value.
In one embodiment, the computer program when executed by the processor further performs the steps of: and judging whether the mark points in the visual angle images are abnormal or not by adopting a preset judgment method.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring the corresponding relation between the same non-coding mark points in each visual angle image by adopting a preset epipolar constraint method; and determining the three-dimensional coordinates of the non-coding mark points of each view image according to the corresponding relation.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. A method for locating a landmark, the method comprising:
acquiring a plurality of view angle images; each of the perspective images includes a plurality of landmark points;
selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
acquiring an initial three-dimensional coordinate set according to first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set.
2. The method of claim 1, wherein obtaining an initial set of three-dimensional coordinates from a first landmark point of a same code value in the first view image and the second view image comprises:
acquiring a first relative posture of the first visual angle image and the second visual angle image according to the coordinate of the first mark point;
and acquiring the initial three-dimensional coordinate set according to the first relative posture and the coordinates of the first mark point.
3. The method according to claim 1 or 2, wherein said determining three-dimensional coordinates of a landmark point of each of said perspective images from said initial set of three-dimensional coordinates comprises:
step a, acquiring a third visual angle image meeting a second preset condition; the second preset condition is used for limiting the number of the mark points of the third visual angle image;
b, acquiring a three-dimensional coordinate of a second mark point in the third visual angle image according to the third visual angle image, the initial three-dimensional coordinate and a preset optimization function; the code value of the second landmark point is not included in the initial decoding set; the initial decoding set is a code value corresponding to the first mark point;
step c, adding the three-dimensional coordinates of the second mark point into the initial three-dimensional coordinate set to obtain a new three-dimensional coordinate set; adding the decoded value of the second mark point into the initial decoding set to obtain a new decoding set;
and repeating the steps a to c until no visual angle image meeting the second preset condition exists, and determining the three-dimensional coordinate set obtained by the ending time as the three-dimensional coordinate set of the mark point of each visual angle image.
4. The method according to claim 3, wherein the obtaining the three-dimensional coordinates of the second marker point in the third perspective image according to the third perspective image, the initial three-dimensional coordinates and a preset optimization function comprises:
optimizing the initial three-dimensional coordinate set by adopting a preset optimization function to obtain an optimized initial three-dimensional coordinate;
and obtaining the three-dimensional coordinate of the second mark point in the third visual angle image according to the third visual angle image and the optimized initial three-dimensional coordinate.
5. The method according to claim 4, wherein obtaining the three-dimensional coordinates of the second marker point in the third perspective image according to the third perspective image and the optimized initial three-dimensional coordinates comprises:
estimating a second relative pose of the third perspective image according to the initial three-dimensional coordinate set and the third perspective image;
optimizing the second relative posture and the initial three-dimensional coordinate set according to the preset optimization function to obtain an optimized second relative posture and an optimized initial three-dimensional coordinate;
and acquiring the three-dimensional coordinates of a second mark point in the third visual angle image according to the optimized second relative posture.
6. The method according to claim 1 or 2, wherein the first preset condition comprises:
a baseline of the first perspective image and the second perspective image is greater than a first baseline threshold and less than a second baseline threshold;
the number of the marker points with the same code value in the first view image and the second view image is larger than or equal to a marker point threshold value.
7. The method according to claim 1 or 2, characterized in that the method further comprises:
and judging whether the mark points in the visual angle images are abnormal or not by adopting a preset judgment method.
8. The method according to claim 1 or 2, characterized in that the method further comprises:
acquiring the corresponding relation between the same non-coding mark points in each visual angle image by adopting a preset epipolar constraint method;
and determining the three-dimensional coordinates of the non-coding mark points of each view image according to the corresponding relation.
9. A device for locating a landmark, the device comprising:
the first acquisition module is used for acquiring a plurality of view angle images; each of the perspective images includes a plurality of landmark points;
the selection module is used for selecting a first perspective image and a second perspective image which meet a first preset condition from all the perspective images; the first preset condition is used for limiting the baseline range and the number of the mark points of the first visual angle image and the second visual angle image;
the second acquisition module is used for acquiring an initial three-dimensional coordinate set according to the first mark points with the same code value in the first visual angle image and the second visual angle image; the initial set of three-dimensional coordinates includes three-dimensional coordinates of the first marker point;
and the determining module is used for determining the three-dimensional coordinates of the mark points of the view angle images according to the initial three-dimensional coordinate set.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 8 when executing the computer program.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910378889.XA CN110176035B (en) | 2019-05-08 | 2019-05-08 | Method and device for positioning mark point, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910378889.XA CN110176035B (en) | 2019-05-08 | 2019-05-08 | Method and device for positioning mark point, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110176035A true CN110176035A (en) | 2019-08-27 |
| CN110176035B CN110176035B (en) | 2021-09-28 |
Family
ID=67690591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910378889.XA Active CN110176035B (en) | 2019-05-08 | 2019-05-08 | Method and device for positioning mark point, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110176035B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11587252B2 (en) | 2020-12-31 | 2023-02-21 | Zg Technology Co., Ltd. | Positioning method and system combining mark point positioning and intelligent reverse positioning |
| WO2024067033A1 (en) * | 2022-09-30 | 2024-04-04 | 先临三维科技股份有限公司 | Mark point recognition method and apparatus, and device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101975552A (en) * | 2010-08-30 | 2011-02-16 | 天津工业大学 | Method for measuring key point of car frame based on coding points and computer vision |
| CN102034238A (en) * | 2010-12-13 | 2011-04-27 | 西安交通大学 | Multi-camera system calibrating method based on optical imaging test head and visual graph structure |
| CN102376089A (en) * | 2010-12-09 | 2012-03-14 | 深圳大学 | Target correction method and system |
| CN104299261A (en) * | 2014-09-10 | 2015-01-21 | 深圳大学 | Three-dimensional imaging method and system for human body |
| CN104406538A (en) * | 2014-12-01 | 2015-03-11 | 南京航空航天大学 | Three-dimensional mark point matching method for point cloud registration and three-dimensional scanning method |
| CN106096207A (en) * | 2016-06-29 | 2016-11-09 | 武汉中观自动化科技有限公司 | A kind of rotor wing unmanned aerial vehicle wind resistance appraisal procedure based on multi-vision visual and system |
| CN106780587A (en) * | 2016-12-07 | 2017-05-31 | 西安蒜泥电子科技有限责任公司 | A kind of characteristics of human body's labeling method based on colour recognition |
| CN107230233A (en) * | 2017-05-04 | 2017-10-03 | 深圳大学 | The scaling method and device of telecentric lens 3-D imaging system based on bundle adjustment |
| WO2018002697A1 (en) * | 2016-06-29 | 2018-01-04 | Uab "Go-Bi" | Method for the enhancement of digital image resolution by applying a unique processing of partially overlapping low-resolution images |
| CN108844524A (en) * | 2018-07-05 | 2018-11-20 | 空气动力学国家重点实验室 | One kind is based on the modified helicopter rotor blade movement parameter measurement method of vibration |
| CN109118545A (en) * | 2018-07-26 | 2019-01-01 | 深圳市易尚展示股份有限公司 | 3-D imaging system scaling method and system based on rotary shaft and binocular camera |
| CN110360991A (en) * | 2019-06-18 | 2019-10-22 | 武汉中观自动化科技有限公司 | A kind of photogrammetric survey method, device and storage medium |
-
2019
- 2019-05-08 CN CN201910378889.XA patent/CN110176035B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101975552A (en) * | 2010-08-30 | 2011-02-16 | 天津工业大学 | Method for measuring key point of car frame based on coding points and computer vision |
| CN102376089A (en) * | 2010-12-09 | 2012-03-14 | 深圳大学 | Target correction method and system |
| CN102034238A (en) * | 2010-12-13 | 2011-04-27 | 西安交通大学 | Multi-camera system calibrating method based on optical imaging test head and visual graph structure |
| CN104299261A (en) * | 2014-09-10 | 2015-01-21 | 深圳大学 | Three-dimensional imaging method and system for human body |
| US20160300383A1 (en) * | 2014-09-10 | 2016-10-13 | Shenzhen University | Human body three-dimensional imaging method and system |
| CN104406538A (en) * | 2014-12-01 | 2015-03-11 | 南京航空航天大学 | Three-dimensional mark point matching method for point cloud registration and three-dimensional scanning method |
| CN106096207A (en) * | 2016-06-29 | 2016-11-09 | 武汉中观自动化科技有限公司 | A kind of rotor wing unmanned aerial vehicle wind resistance appraisal procedure based on multi-vision visual and system |
| WO2018002697A1 (en) * | 2016-06-29 | 2018-01-04 | Uab "Go-Bi" | Method for the enhancement of digital image resolution by applying a unique processing of partially overlapping low-resolution images |
| CN106780587A (en) * | 2016-12-07 | 2017-05-31 | 西安蒜泥电子科技有限责任公司 | A kind of characteristics of human body's labeling method based on colour recognition |
| CN107230233A (en) * | 2017-05-04 | 2017-10-03 | 深圳大学 | The scaling method and device of telecentric lens 3-D imaging system based on bundle adjustment |
| CN108844524A (en) * | 2018-07-05 | 2018-11-20 | 空气动力学国家重点实验室 | One kind is based on the modified helicopter rotor blade movement parameter measurement method of vibration |
| CN109118545A (en) * | 2018-07-26 | 2019-01-01 | 深圳市易尚展示股份有限公司 | 3-D imaging system scaling method and system based on rotary shaft and binocular camera |
| CN110360991A (en) * | 2019-06-18 | 2019-10-22 | 武汉中观自动化科技有限公司 | A kind of photogrammetric survey method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 康喜若 等: "基于双目视觉的相对物体的姿态测量", 《导弹与航天运载技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11587252B2 (en) | 2020-12-31 | 2023-02-21 | Zg Technology Co., Ltd. | Positioning method and system combining mark point positioning and intelligent reverse positioning |
| WO2024067033A1 (en) * | 2022-09-30 | 2024-04-04 | 先临三维科技股份有限公司 | Mark point recognition method and apparatus, and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110176035B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Łuczyński et al. | The pinax-model for accurate and efficient refraction correction of underwater cameras in flat-pane housings | |
| CN111598993B (en) | Three-dimensional data reconstruction method and device based on multi-view imaging technology | |
| CN107230225B (en) | Method and apparatus for three-dimensional reconstruction | |
| JP6338021B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| US20200334842A1 (en) | Methods, devices and computer program products for global bundle adjustment of 3d images | |
| JP6503906B2 (en) | Image processing apparatus, image processing method and image processing program | |
| JP6079333B2 (en) | Calibration apparatus, method and program | |
| CN113330486A (en) | Depth estimation | |
| JP6547754B2 (en) | Triangulation apparatus, triangulation method and program thereof | |
| CN106815869B (en) | Optical center determining method and device of fisheye camera | |
| CN112686877B (en) | Binocular camera-based three-dimensional house damage model construction and measurement method and system | |
| JP7116262B2 (en) | Image depth estimation method and apparatus, electronic device, and storage medium | |
| CN109740659B (en) | Image matching method and device, electronic equipment and storage medium | |
| da Silveira et al. | Dense 3d scene reconstruction from multiple spherical images for 3-dof+ vr applications | |
| CN110176035B (en) | Method and device for positioning mark point, computer equipment and storage medium | |
| CN108444452B (en) | Method and device for detecting longitude and latitude of target and three-dimensional space attitude of shooting device | |
| CN112243518A (en) | Method and device for acquiring depth map and computer storage medium | |
| JP2016126673A (en) | Information processing device, control method therefor, and video camera | |
| TW201913575A (en) | Three dimensional reconstruction method, apparatus and non-transitory computer readable storage medium | |
| JP5235842B2 (en) | Optical system parameter calibration apparatus, optical system parameter calibration method, program, and recording medium | |
| US20210118160A1 (en) | Methods, devices and computer program products for 3d mapping and pose estimation of 3d images | |
| CN113436269B (en) | Image dense stereo matching method, device and computer equipment | |
| Rousso et al. | Robust recovery of camera rotation from three frames | |
| Pollok et al. | A visual SLAM-based approach for calibration of distributed camera networks | |
| JP2006195790A (en) | Lens distortion estimation apparatus, lens distortion estimation method, and lens distortion estimation program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |