A method, device and apparatus for obtaining posture

Abstract

The present invention provides a posture acquisition method, device, and equipment, relating to the field of visual posture calculation technology. The posture acquisition method includes: acquiring image information generated by the visual marker; obtaining first projection image information of the first feature pattern and second projection image information of the grating area based on the position information of the first feature pattern in the image information; obtaining coarse-precision posture information of the visual marker based on the position information of the first feature pattern and the first projection image information; obtaining the center pixel position of the second feature pattern generated by the grating area based on the second projection image information; obtaining the sight angle based on the change in the center pixel position of the second feature pattern; and obtaining high-precision posture information of the visual marker based on the sight angle and the coarse-precision posture information of the visual marker. Compared with the existing technology, the present invention can improve the accuracy of posture calculation.

Description

Technical Field

[0001] The present invention relates to the technical field of visual pose calculation, and in particular to a pose acquisition method, device and equipment. Background Art

[0002] Pose estimation, a key component of computer vision, is the process of determining the translation and rotation of a target coordinate system relative to a reference coordinate system. Common pose estimation technologies include GPS, inertial navigation systems, and vision. Vision-based pose estimation, due to its low cost, minimal system complexity, rapid deployment, and high degree of automation, is widely used in areas such as robot control and navigation, simultaneous localization and mapping, and weapon guidance and initial alignment.

[0003] The most commonly used visual pose estimation technology is pose estimation based on feature points. This method uses perspective projection to determine the coordinates of n feature points in the target coordinate system and the pixel coordinates of the corresponding points in the image pixel coordinate system, given the parameters within the camera. The coordinates of the feature points in the camera coordinate system are obtained using the perspective projection relationship, and then the relative pose relationship is solved. This method mainly uses visual markers such as black and white checkerboards and circular patterns. Its feature extraction is simple, has few restrictions, and is easy to operate, making it suitable for most measurement scenarios. However, the feature extraction accuracy of this method directly determines the accuracy of the final pose result. When the position changes during the estimation process, the position of the feature points in the image changes significantly, resulting in high detection accuracy. However, when the posture changes, especially when the camera is observing the marker directly, the pixel position of the feature points caused by angular rotation changes less, and the measurement error of the feature information is large, which leads to unsatisfactory pose estimation results. Summary of the Invention

[0004] The problem solved by the present invention is that the existing method for estimating the pose of a visual marker has insufficient estimation accuracy when a small pose change occurs.

[0005] To solve the above technical problems, the present invention provides a posture acquisition method, which is based on a posture acquisition device. The posture acquisition device includes a visual marker based on an out-of-plane grating, the visual marker includes a grating area and a plurality of first characteristic patterns arranged around the grating area, and the grating area is used to generate a second characteristic pattern. The posture acquisition method includes:

[0006] Acquiring image information generated by the visual marker;

[0007] obtaining first projection image information of the first characteristic pattern and second projection image information of the grating area according to position information of the first characteristic pattern in the image information;

[0008] Obtaining coarse-precision position information of the visual marker according to the position information of the first characteristic pattern and the first projection image information;

[0009] Obtaining a central pixel position of a second characteristic pattern generated in the grating area according to the second projection image information;

[0010] obtaining a sight angle according to a change in a central pixel position of the second characteristic pattern;

[0011] High-precision pose information of the visual marker is obtained according to the sight angle and the coarse-precision pose information of the visual marker.

[0012] Optionally, obtaining the image information generated by the visual marker includes:

[0013] Calibrate the image collector;

[0014] The image information generated by the visual marker is acquired using a calibrated image collector.

[0015] Optionally, obtaining first projection image information of the first characteristic pattern and second projection image information of the grating area according to position information of the first characteristic pattern in the image information includes:

[0016] Preprocessing the acquired image information to obtain image information with a specified color;

[0017] performing image extraction on the image information having the specified color to obtain position information of the plurality of first characteristic patterns;

[0018] According to the position information of the plurality of first characteristic patterns, first projection image information of the first characteristic patterns and second projection image information of the grating area are obtained by using homography transformation.

[0019] Optionally, the acquired image information is color image information.

[0020] The preprocessing of the acquired image information to obtain image information with a specified color includes:

[0021] Converting the acquired color image information into grayscale image information;

[0022] Comparing the grayscale value of each pixel in the grayscale image information with a preset threshold;

[0023] The color of each image point is set according to the comparison result to obtain image information with a specified color, wherein the image information with the specified color includes foreground image information and background image information distinguished by color.

[0024] Optionally, performing image extraction on the image information having the specified color to obtain position information of the plurality of first characteristic patterns includes:

[0025] extracting contour information of a plurality of the first characteristic patterns in the foreground image information;

[0026] According to the contour information of the plurality of first characteristic patterns, a centroid extraction method is used to obtain the center position information of each first characteristic pattern, and the center position information is used as the position information of the corresponding first characteristic pattern.

[0027] Optionally, obtaining the sight angle according to a change in the position of a central pixel of the second characteristic pattern includes:

[0028] Obtaining an initial position and a current position of a central pixel of the second characteristic pattern;

[0029] obtaining an observation angle of the visual marker and a moving distance of the second characteristic pattern;

[0030] Obtaining a preset value according to the observation angle and the moving distance of the second characteristic pattern;

[0031] A sight angle is obtained according to an initial position, a current position and the preset value of a central pixel of the second characteristic pattern.

[0032] Optionally, obtaining high-precision pose information of the visual marker according to the sight angle and the coarse-precision pose information of the visual marker includes:

[0033] Obtaining a rotation axis vector and a rotation angle of the image collector according to the sight angle;

[0034] High-precision pose information of the visual marker is obtained according to the rotation axis vector, the rotation angle and the coarse-precision pose information of the visual marker.

[0035] The advantages of the posture acquisition method of the present invention over the prior art are:

[0036] The posture acquisition method of the present invention, on the one hand, utilizes the second characteristic pattern generated by the grating area in the visual marker, such as Moiré fringes, to produce significant fringe position movement according to tiny posture changes, thereby overcoming the low posture sensitivity of current posture estimation markers and methods under the condition of direct view, and effectively improving the posture calculation accuracy; on the other hand, the present invention can obtain high-precision posture information of the visual marker based on the line of sight angle and the coarse-precision posture information of the visual marker, and the computational complexity of the posture solution is small, including only a conventional posture estimation (coarse-precision posture estimation) and a posture correction based on the viewpoint position, thereby ensuring real-time requirements; in addition, the present invention uses the conventional posture estimation result as the coarse-precision calculation result, which can suppress interference from complex environments and effectively improve the anti-interference ability of the posture acquisition device.

[0037] To solve the above technical problems, the present invention further provides a posture acquisition device, which is provided on a posture acquisition device. The posture acquisition device includes a visual marker based on an out-of-plane grating, the visual marker includes a grating area and a plurality of first characteristic patterns arranged around the grating area, and the grating area is used to generate a second characteristic pattern. The posture acquisition device includes:

[0038] an acquisition unit, the acquisition unit being configured to acquire image information generated by the visual marker;

[0039] an information processing unit, configured to obtain first projection image information of the first characteristic pattern and second projection image information of the grating area according to position information of the first characteristic pattern in the image information;

[0040] The information processing unit is further configured to obtain rough position information of the visual marker based on the position information of the first characteristic pattern and the first projection image information.

[0041] The information processing unit is further configured to obtain the central pixel position of the second characteristic pattern generated by the grating area according to the second projection image information,

[0042] The information processing unit is further configured to obtain a sight angle according to a change in a central pixel position of the second characteristic pattern;

[0043] A calculation unit is used to obtain high-precision pose information of the visual marker according to the sight angle and the coarse-precision pose information of the visual marker.

[0044] The advantages of the posture acquisition device described in the present invention and the posture acquisition method described in the present invention over the prior art are the same and will not be repeated here.

[0045] In order to solve the above technical problems, the present invention also provides a posture acquisition device, including a memory, a processor and a computer program stored in the memory and runnable on the processor, and the processor implements the steps of the posture acquisition method when executing the computer program.

[0046] Optionally, the posture acquisition device further includes:

[0047] A visual marker based on an out-of-plane grating, the visual marker comprising a grating region and a plurality of first characteristic patterns arranged around the grating region, wherein the grating region is used to generate a second characteristic pattern;

[0048] An image collector, configured to collect image information generated by the visual marker;

[0049] A posture acquisition base, the visual marker and the image collector are both connected to the posture acquisition base, and the visual marker is suitable for translation or rotation on the posture acquisition base;

[0050] The above-mentioned posture acquirer is used to receive the image information acquired by the image collector, and obtain high-precision posture information of the visual marker after processing the image information.

[0051] The advantages of the posture acquisition device described in the present invention and the posture acquisition method described in the present invention are the same as those of the prior art, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 Flowchart of a method for acquiring posture in an embodiment of the present invention;

[0053] Figure 2 This is a structural diagram of a posture acquisition device in an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of the structure of a posture acquisition device in an embodiment of the present invention;

[0055] Figure 4 Schematic diagram of the overall structure of the visual marker in an embodiment of the present invention;

[0056] Figure 5 Schematic diagram of the structure of the grating region in an embodiment of the present invention;

[0057] Figure 6 Schematic diagram of determining a precise camera viewpoint based on a sight angle in an embodiment of the present invention;

[0058] Figure 7 Schematic diagram of posture correction from a rough viewpoint to a precise viewpoint in an embodiment of the present invention.

[0059] Description of reference numerals:

[0060] 1. Image collector, 2. Posture calculation platform, 3. Visual marker, 4. Posture acquirer, 5. First feature pattern, 6. Grating area, 7. Grid grating, 8. Transparent medium plate. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be described clearly and in detail below with reference to the accompanying drawings.

[0062] In the description of the embodiments of this application, the term "some embodiments" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same implementation or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in any one or more embodiments or examples.

[0063] Combine Figure 1 As shown, an embodiment of the present invention provides a posture acquisition method, which is based on a posture acquisition device. The posture acquisition device includes a visual marker 3 based on an out-of-plane grating, and the visual marker 3 includes a grating area 6 and a plurality of first characteristic patterns 5 arranged around the grating area 6. The grating area 6 is used to generate a second characteristic pattern. The posture acquisition method includes:

[0064] Step S1, obtaining image information generated by the visual marker 3;

[0065] Step S2, obtaining first projection image information of the first characteristic pattern 5 and second projection image information of the grating area 6 according to the position information of the first characteristic pattern 5 in the image information;

[0066] Step S3, obtaining rough position information of the visual marker 3 according to the position information of the first characteristic pattern 5 and the first projection image information;

[0067] Step S4, obtaining the central pixel position of the second characteristic pattern generated by the grating area 6 according to the second projection image information;

[0068] Step S5, obtaining the sight angle according to the change of the central pixel position of the second characteristic pattern;

[0069] Step S6 , obtaining high-precision pose information of the visual marker 3 according to the sight angle and the coarse-precision pose information of the visual marker 3 .

[0070] It should be noted that in this embodiment, the visual marker 3 is capable of one-dimensional translation and two-dimensional rotation, and the multiple first characteristic patterns 5 of the visual marker 3 are four circular patterns of the same diameter, the second characteristic pattern is a moiré fringes, the grating area 6 is a first rectangular area, and the four centers of the four circular patterns are all on the diagonals of the first rectangular area, and the centers of the four circular patterns are connected in sequence to form a second rectangular area. Therefore, the posture acquisition method of this embodiment, using the moiré fringes generated by the grating area 6 in the visual marker 3, can produce significant fringing position movement according to the slight posture change of the visual marker 3 during movement, overcoming the low posture sensitivity of the current posture estimation markers and methods in the face-on situation, and effectively improving the accuracy of posture calculation.

[0071] In some embodiments, in step S1, obtaining the image information generated by the visual marker 3 includes:

[0072] Step S11, calibrating the image collector 1;

[0073] Step S12: using the calibrated image collector 1 to acquire the image information generated by the visual marker 3.

[0074] Preferably, in step S11, the image collector 1 is an industrial camera, and the following steps are used to calibrate the industrial camera:

[0075] Step S111, analyzing the camera imaging process and establishing a pinhole imaging model of the camera to obtain the intrinsic parameter matrix and extrinsic parameter matrix of the industrial camera;

[0076] In this step, a certain spatial point P is assumed to undergo a rigid body transformation from the world coordinate system to the camera coordinate system, as well as a similarity transformation and a translation transformation of the camera coordinate system, and is finally converted into an image point p in the pixel coordinate system. According to the above relationship, the pinhole imaging model of the camera can be obtained.

[0077]

[0078] Among them, [u,v,1] and [X W ,Y W ,Z W ,1] are the homogeneous coordinates of the image point p of the spatial point P in the pixel coordinate system and the homogeneous coordinates of the spatial point P in the world coordinate system respectively.

[0079] make

[0080]

[0081]

[0082] Among them, M1 and M2 are the intrinsic parameter matrix and extrinsic parameter matrix of the industrial camera respectively, dx and dy are the lengths of 1 pixel in the x and y directions, f is the focal length, a x and a y are the scale factors of the camera in the X and Y axis directions, u0 and v0 are the horizontal and vertical coordinates of the origin of the image plane coordinate system in the pixel coordinate system, R is the rotation matrix, which represents the posture, and T is the translation vector, which represents the position.

[0083] Use Zhang Zhengyou's chessboard calibration method to solve the internal parameter matrix M1:

[0084] First, use a calibration plate composed of two-dimensional squares and use a camera to take pictures of the calibration plate in different poses. Then, input the number of corner points, corner point spacing, and pictures of different poses of the calibration plate into the camera calibration toolbox of Matlab to calculate the camera intrinsic parameter matrix M1.

[0085] Among them, in step S12, the image information generated by the visual marker 3 is obtained by using the calibrated image collector 1, including: using the calibrated image collector 1 to obtain the image information generated by the visual marker 3 during one-dimensional translation and two-dimensional rotation, and using the slight posture change of the visual marker 3 during the movement to produce significant stripe position movement, thereby improving the calculation accuracy.

[0086] In some embodiments, in step S2, obtaining first projection image information of the first characteristic pattern 5 and second projection image information of the grating area 6 according to the position information of the first characteristic pattern 5 in the image information includes:

[0087] Step S21, pre-processing the acquired image information to obtain image information with a specified color;

[0088] Step S22, performing image extraction on the image information having the specified color to obtain position information of the plurality of first characteristic patterns 5;

[0089] Step S23 : obtaining first projection image information of the first characteristic patterns 5 and second projection image information of the grating area 6 by using homography transformation according to the position information of the plurality of first characteristic patterns 5 .

[0090] Wherein, the image information obtained is color image information,

[0091] In step S21, the obtained image information is preprocessed to obtain image information with a specified color, including:

[0092] Step S211, converting the acquired color image information into grayscale image information;

[0093] Step S212, comparing the grayscale value of each pixel in the grayscale image information with a preset threshold;

[0094] Step S213 , setting the color of each image point according to the comparison result, and obtaining image information with a specified color, wherein the image information with the specified color includes foreground image information and background image information distinguished by color.

[0095] The grayscale value of each pixel in the grayscale image information is obtained by weighting the brightness of the three RGB color channels on each pixel in the color image information.

[0096] In some preferred embodiments, the foreground image information and the background image information are usually distinguished by white or black, and the color difference is obvious, which is easy to distinguish.

[0097] In some specific embodiments, in step S22, performing image extraction on the image information having the specified color to obtain position information of the plurality of first characteristic patterns 5 includes:

[0098] Step S221, extracting contour information of a plurality of the first characteristic patterns 5 in the foreground image information;

[0099] Step S222 : According to the contour information of the plurality of first characteristic patterns 5 , a centroid extraction method is used to obtain the center position information of each first characteristic pattern 5 , and the center position information is used as the position information of the corresponding first characteristic pattern 5 .

[0100] Specifically, the region growing method is adopted, starting from a set of seed points, and the neighboring pixels similar to the seed points are added to the current seeds to form a growth region. After the contour information of the first feature pattern 5 is successfully extracted, the first feature pattern 5 is distinguished from the image based on the connected domain formed by the growth.

[0101] Specifically, in step S23, the homography transformation formula is as follows:

[0102]

[0103] Among them, after determining the pixel positions of the four first characteristic patterns 5, namely the circular patterns, the transformed four-point coordinates are set to conform to the actual size ratio, and the homography matrix can be solved to obtain the first projection image information of the four circular patterns, and the grating area 6 surrounded by the four circular patterns is converted into a square image to obtain the second projection image information of the grating area 6, which is convenient for the subsequent acquisition of the true position of the center pixel position of the second characteristic pattern relative to the marker.

[0104] In some preferred embodiments, in step S4, obtaining the central pixel position of the second characteristic pattern generated by the grating area 6 according to the second projection image information includes:

[0105] Step S41, preprocessing the acquired second projection image information to obtain projection image information with a specified color;

[0106] Step S42, performing image extraction on the projection image information having the specified color to obtain contour information of the second characteristic pattern;

[0107] Step S43: Obtain the central pixel position of the second characteristic pattern using the zero-order moment and the first-order moment of the image.

[0108] In step S42, since the second projection image information also includes the 1 / 4 circular patterns at the four corners, the mask is used to further extract the image to obtain the contour information including only the second characteristic pattern, ie, the moiré fringes.

[0109] Among them, in step S43,

[0110] The zero-order moment of an image (the pixel weighting of each point in the image) is calculated using the following formula:

[0111]

[0112] The first-order moment of an image (the pixel weights of each point in the image in the x and y directions) is calculated using the following formula:

[0113]

[0114]

[0115] The centroid of the binary image, that is, the central pixel position of the second characteristic pattern, can be obtained through the above formula:

[0116]

[0117] x c is the x-coordinate of the center pixel of the second characteristic pattern, y c is the y-coordinate of the center pixel of the second characteristic pattern.

[0118] In a preferred embodiment, step S5, obtaining the sight angle according to the change in the position of the central pixel of the second characteristic pattern, includes:

[0119] Step S51, obtaining the initial position and current position of the central pixel of the second characteristic pattern;

[0120] Step S52, obtaining the observation angle of the visual marker 3 and the moving distance of the second characteristic pattern;

[0121] Step S53, obtaining a preset value according to the observation angle and the moving distance of the second characteristic pattern;

[0122] Step S54 , obtaining a sight angle according to the initial position, current position and the preset value of the central pixel of the second characteristic pattern.

[0123] It should be noted that, in this embodiment, the viewpoint is set to the position of the industrial camera, the line of sight is the straight line connecting the viewpoint of the industrial camera and the center of the cross moiré fringe, the line of sight angle is the angle between the line of sight and the perpendicular line of the plane of the visual marker 3, and the initial position of the cross moiré fringe is the relative position of the center of the cross moiré fringe when the line of sight angle from the industrial camera to the cross moiré fringe is 0.

[0124] When the visual marker 3 moves, the cross moiré fringes will move relative to each other. At this time, the viewing angle and the relative movement distance of the fringes are in a linear relationship:

[0125]

[0126] The sight angle θ can be calculated using the above formula. Here, x and y represent the current position of the center pixel of the second characteristic pattern, x0 and y0 represent the initial position of the center pixel of the second characteristic pattern, and the slope k can be calculated using a high-precision turntable based on the observation angle and the travel distance of the second characteristic pattern.

[0127] In a preferred embodiment, in step S6, obtaining high-precision pose information of the visual marker 3 based on the sight angle and the coarse-precision pose information of the visual marker 3 includes:

[0128] Step S61, obtaining the rotation axis vector and rotation angle of the image collector 1 according to the sight angle;

[0129] Step S62 : obtaining high-precision pose information of the visual marker 3 according to the rotation axis vector, the rotation angle, and the coarse-precision pose information of the visual marker 3 .

[0130] In this embodiment, the coarse precision viewpoint of the industrial camera can be rotated to a high precision position with the center of the visual marker as the center. Figure 7 shown.

[0131] Specifically, the rotation axis vector is obtained by the following calculation formula:

[0132]

[0133] Among them, P and Pc are the coarse and high-precision position coordinates of the industrial camera, respectively, O is the center coordinate of the marker, OP and OPc are the vectors from the center of the visual marker 3 to the coarse and high-precision positions of the industrial camera, respectively, a is the rotation axis vector, and the modulus of the axial quantity is the rotation angle ρ.

[0134] It should be noted that, in this embodiment, the coarse-precision position coordinates of the industrial camera can be obtained through the coarse-precision pose information of the visual marker 3 .

[0135] In addition, in this embodiment, since the distance d from the industrial camera to the center of the visual marker 3 is known, a triangle of the industrial camera, the center of the visual marker 3 and the center of the current stripe can be constructed, as shown in FIG. Figure 6 As shown, the high-precision position coordinates P of the industrial camera can be obtained. C .

[0136] Specifically, in step S62, obtaining high-precision pose information of the visual marker 3 according to the rotation axis vector, the rotation angle, and the coarse-precision pose information of the visual marker 3 includes:

[0137] Step S621, obtaining a homogeneous transformation matrix H of the rotation process according to the rotation axis vector and the rotation angle;

[0138] Step S622 : obtaining high-precision pose information of the visual marker 3 according to the homogeneous transformation matrix H and the coarse-precision pose information of the visual marker 3 .

[0139] In step S621, the calculation formula of the homogeneous transformation matrix H is as follows:

[0140]

[0141] Where ρ is the rotation angle,

[0142] cosρ=c, sinρ=s, (1-cosρ)=C.

[0143] In step S622, high-precision pose information H is obtained according to the following calculation formula: C :

[0144] H C =H W H,

[0145] Among them, H W is the coarse-precision pose information of the visual marker 3, and according to the high-precision pose information H C The external parameter matrix of the industrial camera can be obtained.

[0146] Therefore, the posture acquisition method of this embodiment, on the one hand, utilizes the second characteristic pattern generated by the grating area 6 in the visual marker 3, such as Moiré fringes, to produce significant fringe position movement according to tiny posture changes, thereby overcoming the low posture sensitivity of current posture estimation markers and methods under the straight-on condition, and effectively improving the posture calculation accuracy; on the other hand, the present invention can obtain high-precision posture information of the visual marker 3 based on the line of sight angle and the coarse-precision posture information of the visual marker 3, and the computational complexity of the posture solution is small, and only includes a conventional posture estimation (coarse-precision posture estimation) and a posture correction based on the viewpoint position, thereby ensuring real-time requirements; in addition, the present invention uses the conventional posture estimation result as the coarse-precision calculation result, which can suppress interference from complex environments and effectively improve the anti-interference ability of the posture acquisition device.

[0147] Combine Figure 2 As shown, another embodiment of the present invention further provides a posture acquisition device, which is provided on the posture acquisition device, wherein the posture acquisition device includes a visual marker 3 based on an out-of-plane grating, wherein the visual marker 3 includes a grating area 6 and a plurality of first characteristic patterns 5 arranged around the grating area 6, and the grating area 6 is used to generate a second characteristic pattern. The posture acquisition device includes:

[0148] An acquisition unit 210, the acquisition unit 210 is used to acquire image information generated by the visual marker 3;

[0149] an information processing unit 220, configured to obtain first projection image information of the first characteristic pattern 5 and second projection image information of the grating area 6 according to position information of the first characteristic pattern 5 in the image information;

[0150] The information processing unit 220 is further configured to obtain rough position information of the visual marker 3 based on the position information of the first characteristic pattern 5 and the first projection image information.

[0151] The information processing unit 220 is further configured to obtain the central pixel position of the second characteristic pattern generated by the grating area 6 according to the second projection image information.

[0152] The information processing unit 220 is further configured to obtain a sight angle according to a change in the position of a central pixel of the second characteristic pattern;

[0153] The calculation unit 230 is used to obtain high-precision pose information of the visual marker 3 according to the sight angle and the coarse-precision pose information of the visual marker 3.

[0154] Specifically, the acquisition unit 210 is used to acquire the image information generated by the visual marker 3, including:

[0155] Calibrate the image collector 1;

[0156] The image information generated by the visual marker 3 is acquired using the calibrated image collector 1 .

[0157] Specifically, the information processing unit 220 is configured to obtain first projection image information of the first characteristic pattern 5 and second projection image information of the grating area 6 according to the position information of the first characteristic pattern 5 in the image information, including:

[0158] Preprocessing the acquired image information to obtain image information with a specified color;

[0159] Performing image extraction on the image information having the specified color to obtain position information of the plurality of first characteristic patterns 5;

[0160] According to the position information of the plurality of first characteristic patterns 5 , the first projection image information of the first characteristic patterns 5 and the second projection image information of the grating area 6 are obtained by using homography transformation.

[0161] Specifically, the information processing unit 220 is further configured to obtain the sight angle according to the change in the central pixel position of the second characteristic pattern, including:

[0162] Obtaining an initial position and a current position of a central pixel of the second characteristic pattern;

[0163] Obtaining the observation angle of the visual marker 3 and the moving distance of the second characteristic pattern;

[0164] Obtaining a preset value according to the observation angle and the moving distance of the second characteristic pattern;

[0165] A sight angle is obtained according to an initial position, a current position and the preset value of a central pixel of the second characteristic pattern.

[0166] Specifically, the calculation unit 230 is configured to obtain high-precision pose information of the visual marker 3 according to the sight angle and the coarse-precision pose information of the visual marker 3, including:

[0167] The calculation unit 230 is used to obtain the rotation axis vector and rotation angle of the image collector 1 according to the sight angle;

[0168] The calculation unit 230 is configured to obtain high-precision pose information of the visual marker 3 according to the rotation axis vector, the rotation angle, and the coarse-precision pose information of the visual marker 3 .

[0169] The advantages of the posture acquisition device described in the present invention and the posture acquisition method described in the present invention over the prior art are the same and will not be repeated here.

[0170] Another embodiment of the present invention also provides a posture acquisition device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the posture acquisition method when executing the computer program.

[0171] Combine Figure 3-5 As shown, in this embodiment, the posture acquisition device further includes:

[0172] A visual marker 3 based on an out-of-plane grating, the visual marker 3 comprising a grating region 6 and a plurality of first characteristic patterns 5 arranged around the grating region 6, wherein the grating region 6 is configured to generate a second characteristic pattern;

[0173] An image collector 1, the image collector 1 is used to collect image information generated by the visual marker 3;

[0174] A posture acquisition base, wherein the visual marker 3 and the image collector 1 are both connected to the posture acquisition base, and the visual marker 3 is suitable for translation or rotation on the posture acquisition base;

[0175] The posture acquirer 4 is used to receive the image information acquired by the image collector 1 and obtain high-precision posture information of the visual marker 3 after processing the image information.

[0176] In a preferred embodiment, the image collector 1 is an industrial camera with low cost.

[0177] In some embodiments, the visual marker 3 is capable of one-dimensional translation and two-dimensional rotation, and includes a substrate having a grating region 6 and a plurality of first characteristic patterns 5 disposed around the grating region 6. The plurality of first characteristic patterns 5 are four circular patterns of the same diameter. The grating region 6 is a first rectangular region, and the four centers of the four circular patterns are all on the diagonal of the first rectangular region. The centers of the four circular patterns are sequentially connected to form a second rectangular region. The structure is simple.

[0178] Preferably, the substrate is made of organic glass, which is low in cost and readily available.

[0179] In some embodiments, the structure of the grating region 6 includes two layers of grid grating 7 and a transparent dielectric plate 8 disposed between the two layers of grid grating 7. This can produce moiré fringes that are much larger than the grid size, appearing as large, dark cross-shaped fringes, and can undergo significant relative motion with slight changes in position.

[0180] The advantages of the posture acquisition device described in the present invention and the posture acquisition apparatus described in the present invention over the prior art are the same and will not be repeated here.

[0181] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements that are inherent to such process, method, article or device. In the absence of further limitations, the elements defined by the sentence "comprises..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0182] Although the present disclosure is disclosed as above, the protection scope of the present disclosure is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present disclosure, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A posture acquisition method, characterized in that: The method is based on a posture acquisition device, wherein the posture acquisition device comprises a visual marker (3) based on an out-of-plane grating, wherein the visual marker (3) comprises a grating region (6) and a plurality of first characteristic patterns (5) arranged around the grating region (6), and the grating region (6) is used to generate a second characteristic pattern. The method comprises: Acquiring image information generated by the visual marker (3); Obtaining first projection image information of the first characteristic pattern (5) and second projection image information of the grating area (6) based on position information of the first characteristic pattern (5) in the image information; Obtaining coarse-precision position information of the visual marker (3) based on the position information of the first characteristic pattern (5) and the first projection image information; Obtaining the central pixel position of the second characteristic pattern generated by the grating area (6) according to the second projection image information; obtaining a sight angle according to a change in a central pixel position of the second characteristic pattern; High-precision position information of the visual marker (3) is obtained based on the sight angle and the coarse-precision position information of the visual marker (3).

2. The posture acquisition method according to claim 1, characterized in that The step of obtaining the image information generated by the visual marker (3) comprises: Calibrate the image collector (1); The image information generated by the visual marker (3) is acquired using a calibrated image collector (1).

3. The posture acquisition method according to claim 1, characterized in that The step of obtaining first projection image information of the first characteristic pattern (5) and second projection image information of the grating area (6) based on the position information of the first characteristic pattern (5) in the image information comprises: Preprocessing the acquired image information to obtain image information with a specified color; Performing image extraction on the image information having the specified color to obtain position information of a plurality of the first characteristic patterns (5); According to the position information of the plurality of first characteristic patterns (5), first projection image information of the first characteristic patterns (5) and second projection image information of the grating area (6) are obtained by using homography transformation.

4. The posture acquisition method according to claim 3, characterized in that: The image information obtained is color image information, The preprocessing of the acquired image information to obtain image information with a specified color includes: Converting the acquired color image information into grayscale image information; Comparing the grayscale value of each pixel in the grayscale image information with a preset threshold; The color of each image point is set according to the comparison result to obtain image information with a specified color, wherein the image information with the specified color includes foreground image information and background image information distinguished by color.

5. The posture acquisition method according to claim 4, characterized in that: The step of extracting the image information having the specified color to obtain position information of the plurality of first characteristic patterns (5) includes: Extracting contour information of a plurality of the first characteristic patterns (5) in the foreground image information; According to the contour information of the plurality of first characteristic patterns (5), a centroid extraction method is used to obtain the center position information of each first characteristic pattern (5), and the center position information is used as the position information of the corresponding first characteristic pattern (5).

6. The posture acquisition method according to claim 1, characterized in that: The obtaining of the sight angle according to the change of the central pixel position of the second characteristic pattern includes: Obtaining an initial position and a current position of a central pixel of the second characteristic pattern; Obtaining the observation angle of the visual marker (3) and the moving distance of the second characteristic pattern; Obtaining a preset value according to the observation angle and the moving distance of the second characteristic pattern; A sight angle is obtained according to an initial position, a current position and the preset value of a central pixel of the second characteristic pattern.

7. The posture acquisition method according to claim 2, characterized in that: The method of obtaining high-precision pose information of the visual marker (3) based on the sight angle and the coarse-precision pose information of the visual marker (3) comprises: Obtaining a rotation axis vector and a rotation angle of the image collector (1) according to the sight angle; High-precision position information of the visual marker (3) is obtained based on the rotation axis vector, the rotation angle and the coarse-precision position information of the visual marker (3).

8. A posture acquisition device, characterized in that: The device is provided on a posture acquisition device, wherein the posture acquisition device includes a visual marker (3) based on an out-of-plane grating, the visual marker (3) includes a grating region (6) and a plurality of first characteristic patterns (5) arranged around the grating region (6), and the grating region (6) is used to generate a second characteristic pattern. The posture acquisition device includes: an acquisition unit, the acquisition unit being used to acquire image information generated by the visual marker (3); an information processing unit, the information processing unit being configured to obtain first projection image information of the first characteristic pattern (5) and second projection image information of the grating area (6) based on position information of the first characteristic pattern (5) in the image information; The information processing unit is further configured to obtain rough position information of the visual marker (3) based on the position information of the first characteristic pattern (5) and the first projection image information. The information processing unit is further configured to obtain the central pixel position of the second characteristic pattern generated by the grating area (6) according to the second projection image information, The information processing unit is further configured to obtain a sight angle according to a change in a central pixel position of the second characteristic pattern; A calculation unit is provided, wherein the calculation unit is used to obtain high-precision posture information of the visual marker (3) based on the sight angle and the coarse-precision posture information of the visual marker (3).

9. A posture acquisition device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the posture acquisition method according to any one of claims 1 to 7 are implemented.

10. The posture acquisition device according to claim 9, characterized in that: Also includes: A visual marker (3) based on an out-of-plane grating, the visual marker (3) comprising a grating region (6) and a plurality of first characteristic patterns (5) arranged around the grating region (6), and the grating region (6) is used to generate a second characteristic pattern; An image collector (1), the image collector (1) being used to collect image information generated by the visual marker (3); A posture acquisition base, the visual marker (3) and the image collector (1) are both connected to the posture acquisition base, and the visual marker (3) is suitable for performing translation or rotation on the posture acquisition base; A posture acquirer (4) is used to receive the image information acquired by the image collector (1), and obtain high-precision posture information of the visual marker (3) after processing the image information.

Images