WO2017128603A1 - 一种教育玩具套件及其反光镜位置检测方法 - Google Patents

一种教育玩具套件及其反光镜位置检测方法 Download PDF

Info

Publication number
WO2017128603A1
WO2017128603A1 PCT/CN2016/086800 CN2016086800W WO2017128603A1 WO 2017128603 A1 WO2017128603 A1 WO 2017128603A1 CN 2016086800 W CN2016086800 W CN 2016086800W WO 2017128603 A1 WO2017128603 A1 WO 2017128603A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
area
groove
positioning hole
mirror
Prior art date
Application number
PCT/CN2016/086800
Other languages
English (en)
French (fr)
Inventor
范旭
孙贤军
Original Assignee
上海葡萄纬度科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海葡萄纬度科技有限公司 filed Critical 上海葡萄纬度科技有限公司
Publication of WO2017128603A1 publication Critical patent/WO2017128603A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
    • A63H33/00—Other toys
    • A63H33/04—Building blocks, strips, or similar building parts
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
    • A63H33/00—Other toys
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Definitions

  • the invention relates to the technical field of computer vision detection and processing, in particular to an educational toy kit and a mirror position detecting method thereof.
  • an educational toy kit has been successfully developed in the field of application of computer vision recognition processing technology, including: a bracket, a helmet detector and a bottom plate, and the bracket is mounted on the bottom plate, and the helmet detector is mounted on the bracket; There is a first groove; the bottom of the bracket has a protrusion, the protrusion is installed in the first groove, the top has a second groove and a third groove, the second groove is used for placing the tablet; the helmet detector is installed on the first Inside the three grooves.
  • a positioning hole is provided on the educational toy kit, and a targeted image processing technology can be applied to detect whether the position of the preset positioning hole on the component is centered, and whether the slot line is located. Symmetrical positioning above the locating holes enables calibration of the mirror mount.
  • the present invention provides an educational toy kit and a mirror position detecting method thereof, and the technical solutions are as follows:
  • An educational toy kit comprising a bracket, a helmet detector and a bottom plate, wherein the bracket is mounted on the bottom plate, the helmet detector is mounted on the bracket, and a first groove is arranged above the bottom plate; the bottom of the bracket has a protrusion, and the protrusion is installed at the bottom a recess having a second recess for positioning a tablet computer; a helmet detector mounted in the third recess; and a positioning hole disposed in the third recess On the longitudinal center axis of the side wall;
  • the helmet detector further includes: a body, a fourth groove, two segments and a mirror, and the fourth groove is located in the body for holding different types of tablets, and holding the tablet screen in the fourth groove a mirror is provided at the end point, The other end of the mirror is mounted on the edge of the helmet detector. The angle between the mirror and the horizontal plane is acute.
  • the fourth groove holds the end of the tablet screen higher than the camera position of the tablet.
  • the two sectors are located in the mirror 2 On the edge, it is used to fix the mirror and hold the tablet.
  • a fixed fulcrum is provided at the back casing of the fourth groove holding tablet for clamping the tablet.
  • a method for detecting a position of a mirror of an educational toy kit comprising the following steps:
  • Step one first installing the bottom end of the tablet in the second recess, and then mounting the helmet detector on the top of the tablet through the fourth recess;
  • Step 2 After the installation is fixed, the image is acquired by the front camera of the tablet computer;
  • Step 3 extracting a position image of the positioning hole in the image acquired by the front camera
  • Step 4 Determine the position of the positioning hole by using the position image extracted in the third step, and determine whether the tablet computer is accurately installed by the position of the positioning hole. If the steps 1 to 4 are not performed accurately, re-install until the measurement is accurate. If the installation is accurate, perform step five;
  • the positioning hole In the correct image obtained by the front camera, the positioning hole should be located at the center point of the image; a deviation threshold is preset, as long as the deviation of the positioning hole is less than or equal to the deviation threshold, the installation is considered accurate; if a positioning hole appears in the image, but the positioning If the hole exceeds the deviation threshold, it means that the tablet is not properly installed; if the positioning hole does not appear in the image, it means that the tablet or helmet detector is not properly installed;
  • Step 5 extracting a position image containing only the groove line in the image, and measuring an absolute value of the angle between the long axis of the groove line and the X axis;
  • step 6 it is determined whether the mirror is accurately installed by the absolute value of the angle between the long axis of the slot line and the X axis.
  • step two are:
  • I xy f(x, y);
  • f(x, y) (R xy , G xy , B xy );
  • R xy represents the color value of the image pixel in the red channel
  • G xy represents the color value of the image pixel in the green channel
  • B xy represents the color value of the image pixel in the blue channel.
  • step three are:
  • the color image acquired in step 2 is converted into a grayscale image.
  • the specific formula is:
  • Gray(x, y) 0.2989 ⁇ R xy +0.5870 ⁇ G xy +0.1140 ⁇ B xy ;
  • Gray(x, y) represents a grayscale image
  • a template matrix is defined to extract the positioning holes, the template matrix size is (n+2) ⁇ (n+2), and the template matrix is a square matrix with an n ⁇ n zero matrix in the middle and a boundary of 1, the template matrix Specifically:
  • mask (n+2) ⁇ (n+2) represents a template matrix
  • grayscale image is convoluted together with the template matrix
  • the positioning hole Since the positioning hole is disposed on the bottom side of the side wall of the third groove, the positioning hole should be located in the upper half of the grayscale image, and only the upper half of the grayscale image is processed together with the template matrix during the convolution operation. Yes;
  • M r represents the height of the image
  • M c represents the width of the image
  • C (s, t) represents the convolved image
  • the specific value of n is determined by the diameter of the positioning hole in the image
  • the convolution image is subtracted from the gray image to obtain a difference image, and then the pixel value of the difference image is calculated, and the difference image is binarized.
  • the specific formula is:
  • B(x, y) represents a binarized image of the difference image, and ⁇ represents an empirical threshold in the binarization process of the locating hole;
  • the morphological prior knowledge is used to filter out the locating hole area, and a position image containing only the locating hole is obtained.
  • step 3 the morphological prior knowledge is used to filter the positioning hole area, and the specific steps of obtaining the position image containing only the positioning hole are:
  • 8 neighborhood connectivity refers to the point that the pixel value of one pixel is non-zero, and the other pixel points have non-zero pixel values in the upper, lower, left, right, upper left, upper right, lower left, and lower right directions.
  • the two pixels are connected in 8 neighborhoods, so different connected areas can be distinguished one by one;
  • step b) separately calculating the area of the connected area marked in step a), and setting the area threshold;
  • step c) separately calculating the eccentricity of the connected region marked in step a), and setting the eccentricity threshold;
  • the positioning area can be filtered out, and the positioning hole position image is obtained;
  • the remaining connected area of the filtering area is the positioning hole position image.
  • step five are:
  • the color image acquired in step 2 is converted into a grayscale image.
  • the specific formula is:
  • Gray(x, y) 0.2989 ⁇ R xy +0.5870 ⁇ G xy +0.1140 ⁇ B xy ;
  • Gray(x, y) represents a grayscale image
  • a template matrix is defined to extract slot lines, the template matrix size is (n+2) ⁇ (n+2), and the template matrix is a square matrix with an n ⁇ n zero matrix in the middle and a boundary of 1, template matrix Specifically:
  • mask (n+2) ⁇ (n+2) represents a template matrix
  • grayscale image is convoluted together with the template matrix
  • the positioning hole Since the positioning hole is disposed on the bottom side of the side wall of the third groove, the positioning hole should be located in the upper half of the grayscale image, and only the upper half of the grayscale image is processed together with the template matrix during the convolution operation. Yes;
  • M r represents the height of the image
  • M c represents the width of the image
  • C (s, t) represents the convolved image
  • the specific value of h is determined by the width of the groove line in the image
  • the convolution image is subtracted from the gray image to obtain a difference image, and then the pixel value of the difference image is calculated, and the difference image is binarized.
  • the specific formula is:
  • B(x, y) represents a binarized image of the difference image, and ⁇ represents a preset empirical threshold in the slot line binarization process;
  • the morphological prior knowledge is used to filter out the groove line area, resulting in an image containing only the groove lines.
  • step 5 the morphological prior knowledge is used to filter out the slot line area, and the specific steps of obtaining the image containing only the slot line are:
  • 8 neighborhood connectivity refers to the point that the pixel value of one pixel is non-zero, and the other pixel points have non-zero pixel values in the upper, lower, left, right, upper left, upper right, lower left, and lower right directions.
  • the two pixels are connected in 8 neighborhoods, so different connected areas can be distinguished one by one;
  • step 2) Calculate the length of the major axis and the minor axis of the connected region marked in step 1), respectively, and calculate the ratio of the major axis to the minor axis, and set the threshold value of the long and short axis ratio;
  • step 1) separately calculating the area of the connected area marked in step 1), and setting the area threshold;
  • the number of pixels included in each of the 8 neighborhood connected components is calculated, and the number of pixels is the area of the connected region;
  • the area in the connected area that exceeds the area threshold or the long-short axis ratio threshold is a non-slot line area, which is filtered out;
  • the correct positional relationship between the positioning hole and the groove line should be that the positioning hole is located in the middle, and the groove line is located around the positioning hole; if the correct positional relationship between the positioning hole and the groove line is not satisfied, it is a non-slot line area, and is filtered out , to get an image that only contains slot lines.
  • step 6 the absolute value of the angle between the long axis and the X axis of the slot line determines whether the mirror is accurately mounted.
  • the mirror If the absolute value of the angle between the long axis of the slot line and the X axis is greater than the preset deviation angle threshold, the mirror is considered to be rotated and the installation is incorrect, otherwise the installation is accurate.
  • the hardware design is ingenious.
  • the invention only has a positioning hole on the base of the tablet computer.
  • the structure is simple and the cost is low.
  • the size and position of the positioning hole are verified by a large number of experiments, which is more scientific and convenient for the camera to collect images and can be quickly Check if the installation was successful.
  • the detection performance is stable, the installation of different lighting, different tablet computers can be quickly tested, the applicability is stronger.
  • the invention provides a positioning hole on the educational toy kit, and can apply a targeted image processing technology to detect whether the position of the preset positioning hole on the component is centered, and whether the groove line is located symmetrically above the positioning hole to realize the mirror Calibration of the installation.
  • FIG. 1 is a schematic structural view of an educational toy kit of the present invention.
  • FIG. 2 is a rear elevational view of the bracket of the educational toy kit of the present invention.
  • FIG. 3 is a perspective view of a bracket of an educational toy kit of the present invention.
  • FIG. 4 is a schematic structural view of a bottom plate of an educational toy kit of the present invention.
  • FIG. 5 is a schematic structural view of a helmet detector of the grape exploration number educational toy kit of the present invention.
  • Fig. 6 is a schematic view showing the application of the grape exploration number educational toy kit of the present invention.
  • FIG. 7 is a flow chart of a method of detecting a position of a mirror of an educational toy kit.
  • Bracket 1 protrusion 101, second groove 102, third groove 103, dish-shaped chassis 104, circular top frame 105, open handle 106, helmet detector 2, body 201, fourth groove 202 2 sectors 203, mirror 204, fixed fulcrum 205, bottom plate 3, first groove 301.
  • Figure 7 is a flow chart of an educational toy kit and its mirror position detecting method.
  • an educational toy kit and a mirror position detecting method thereof include the following steps:
  • Step one first installing the bottom end of the tablet in the second recess, and then mounting the helmet detector on the top of the tablet through the fourth recess;
  • Step 2 After the installation is fixed, the image is acquired by the front camera of the tablet computer;
  • I xy f(x, y);
  • f(x, y) (R xy , G xy , B xy );
  • R xy represents the color value of the image pixel in the red channel
  • G xy represents the color value of the image pixel in the green channel
  • B xy represents the color value of the image pixel in the blue channel
  • Step 3 extracting a position image of the positioning hole in the image acquired by the front camera
  • the color image acquired in step 2 is converted into a grayscale image.
  • the specific formula is:
  • Gray(x, y) 0.2989 ⁇ R xy +0.5870 ⁇ G xy +0.1140 ⁇ B xy ;
  • Gray(x, y) represents a grayscale image
  • a template matrix is defined to extract the positioning holes, the template matrix size is (n+2) ⁇ (n+2), and the template matrix is a square matrix with an n ⁇ n zero matrix in the middle and a boundary of 1, the template matrix Specifically:
  • mask (n+2) ⁇ (n+2) represents a template matrix
  • grayscale image is convoluted together with the template matrix
  • the positioning hole Since the positioning hole is disposed on the bottom side of the side wall of the third groove, the positioning hole should be located in the upper half of the grayscale image, and only the upper half of the grayscale image is processed together with the template matrix during the convolution operation. Yes;
  • M r represents the height of the image
  • M c represents the width of the image
  • C (s, t) represents the convolved image
  • the specific value of n is determined by the diameter of the positioning hole in the image
  • the convolution image is subtracted from the gray image to obtain a difference image, and then the pixel value of the difference image is calculated, and the difference image is binarized.
  • the specific formula is:
  • B(x, y) represents a binarized image of the difference image
  • the morphological prior knowledge is used to filter the locating hole area, and the specific steps for obtaining the locating hole position image are:
  • 8 neighborhood connectivity refers to the point that the pixel value of one pixel is non-zero, and the other pixel points have non-zero pixel values in the upper, lower, left, right, upper left, upper right, lower left, and lower right directions.
  • the two pixels are connected in 8 neighborhoods, so different connected areas can be distinguished one by one;
  • step b) separately calculating the area of the connected area marked in step a), and setting the area threshold;
  • step c) separately calculating the eccentricity of the connected region marked in step a), and setting the eccentricity threshold;
  • the positioning area can be filtered out, and the positioning hole image is obtained;
  • Step 4 Determine the position of the positioning hole by using the position image extracted in the third step, and determine whether the tablet computer is accurately installed by the position of the positioning hole. If the steps 1 to 4 are not performed accurately, re-install until the measurement is accurate. If the installation is accurate, perform step five;
  • the positioning hole In the correct image obtained by the front camera, the positioning hole should be located at the center point of the image; a deviation threshold is preset, as long as the deviation of the positioning hole is less than or equal to the deviation threshold, the installation is considered accurate; if a positioning hole appears in the image, but the positioning If the hole exceeds the deviation threshold, it means that the tablet is not properly installed; if the positioning hole does not appear in the image, it means that the tablet or helmet detector is not properly installed;
  • Step 5 extracting a position image containing only the groove line in the image, and measuring an absolute value of the angle between the long axis of the groove line and the X axis;
  • the color image acquired in step 2 is converted into a grayscale image.
  • the specific formula is:
  • Gray(x, y) 0.2989 ⁇ R xy +0.5870 ⁇ G xy +0.1140 ⁇ B xy ;
  • Gray(x, y) represents a grayscale image
  • a template matrix is defined to extract slot lines, the template matrix size is (n+2) ⁇ (n+2), and the template matrix is a square matrix with an n ⁇ n zero matrix in the middle and a boundary of 1, template matrix Specifically:
  • mask (n+2) ⁇ (n+2) represents a template matrix
  • grayscale image is convoluted together with the template matrix
  • the positioning hole Since the positioning hole is disposed on the bottom side of the side wall of the third groove, the positioning hole should be located in the upper half of the grayscale image, and only the upper half of the grayscale image is processed together with the template matrix during the convolution operation. Yes;
  • M r represents the height of the image
  • M c represents the width of the image
  • C (s, t) represents the convolved image
  • the specific value of h is determined by the width of the groove line in the image
  • the convolution image is subtracted from the gray image to obtain a difference image, and then the pixel value of the difference image is calculated, and the difference image is binarized.
  • the specific formula is:
  • B(x, y) represents a binarized image of the difference image, and ⁇ represents a preset empirical threshold in the slot line binarization process;
  • the morphological prior knowledge is used to filter the area of the slot line to obtain an image containing only the slot line.
  • the specific steps are as follows:
  • 8 neighborhood connectivity refers to the point that the pixel value of one pixel is non-zero, and the other pixel points have non-zero pixel values in the upper, lower, left, right, upper left, upper right, lower left, and lower right directions.
  • the two pixels are connected in 8 neighborhoods, so different connected areas can be distinguished one by one;
  • step 2) Calculate the length of the major axis and the minor axis of the connected region marked in step 1), respectively, and calculate the ratio of the major axis to the minor axis, and set the threshold value of the long and short axis ratio;
  • step 1) separately calculating the area of the connected area marked in step 1), and setting the area threshold;
  • the number of pixels included in each of the 8 neighborhood connected components is calculated, and the number of pixels is the area of the connected region;
  • the area in the connected area that exceeds the area threshold or the long-short axis ratio threshold is a non-slot line area, which is filtered out;
  • the correct positional relationship between the positioning hole and the groove line should be that the positioning hole is located in the middle, and the groove line is located around the positioning hole; if the correct positional relationship between the positioning hole and the groove line is not satisfied, it is a non-slot line area, and is filtered out , resulting in an image containing only slot lines;
  • Step 6 determining whether the mirror is accurately installed by the absolute value of the angle between the long axis of the slot line and the X axis;
  • the mirror If the absolute value of the angle between the long axis of the slot line and the X axis is greater than the preset deviation angle threshold, the mirror is considered to be rotated and the installation is incorrect, otherwise the installation is accurate.
  • FIG. 1 is a schematic structural view of an educational toy kit of the present invention.
  • FIG. 2 is a rear elevational view of the bracket of the educational toy kit of the present invention.
  • FIG. 3 is a perspective view of a bracket of an educational toy kit of the present invention.
  • FIG. 4 is a schematic structural view of a bottom plate of an educational toy kit of the present invention.
  • FIG. 5 is a schematic structural view of a helmet detector of the grape exploration number educational toy kit of the present invention.
  • Fig. 6 is a schematic view showing the application of the grape exploration number educational toy kit of the present invention.
  • an educational toy kit includes a bracket 1, a helmet detector 2 and a bottom plate 3, and the bracket 1 is mounted on the bottom plate 3, and the helmet detector 2 is mounted on the bracket 1; the bottom plate 3 is disposed above There is a first groove 301; a bracket 1 having a protrusion 101 at the bottom, the protrusion 101 is mounted in the first groove 301, the top has a second groove 102 and a third groove 103, and the second groove 102 is used for placing
  • the helmet detector 2 is mounted in the third recess 103; and further includes: a positioning hole 104 disposed on a longitudinal central axis of the sidewall of the third recess 103; the helmet detector 2 further includes: a body 201, Four grooves 202, two sector blocks 203 and mirrors 204, and a fourth groove 202 is located in the body 201 for clamping different types of tablets, at the end of the fourth groove 202 holding the tablet screen
  • a mirror 204 is disposed, and the other end of the mirror 204
  • a fixed fulcrum 205 is provided at the back casing of the tablet in which the fourth groove 202 is clamped for clamping the tablet computer.
  • FIG. 7 is a flow chart of a method of detecting a position of a mirror of an educational toy kit.
  • a method for detecting a position of a mirror of an educational toy kit includes the following steps:
  • Step one first installing the bottom end of the tablet in the second recess, and then mounting the helmet detector on the top of the tablet through the fourth recess;
  • Step 2 After the installation is fixed, the image is acquired by the front camera of the tablet computer;
  • Step 3 extracting a position image of the positioning hole in the image acquired by the front camera
  • Step 4 Determine the position of the positioning hole by using the position image extracted in the third step, and determine whether the tablet computer is accurately installed by the position of the positioning hole. If the steps 1 to 4 are not performed accurately, re-install until the measurement is accurate. If the installation is accurate, perform step five;
  • the positioning hole In the correct image obtained by the front camera, the positioning hole should be located at the center point of the image; a deviation threshold is preset, as long as the deviation of the positioning hole is less than or equal to the deviation threshold, the installation is considered accurate; if a positioning hole appears in the image, but the positioning If the hole exceeds the deviation threshold, it means that the tablet is not properly installed; if the positioning hole does not appear in the image, it means that the tablet or helmet detector is not properly installed;
  • Step 5 extracting a position image containing only the groove line in the image, and measuring an absolute value of the angle between the long axis of the groove line and the X axis;
  • step 6 it is determined whether the mirror is accurately installed by the absolute value of the angle between the long axis of the slot line and the X axis.
  • Figure 7 is a flow chart of an educational toy kit and its mirror position detecting method.
  • an educational toy kit and a mirror position detecting method thereof include the following steps:
  • Step one first installing the bottom end of the tablet in the second recess, and then mounting the helmet detector on the top of the tablet through the fourth recess;
  • Step 2 After the installation is fixed, the image is acquired by the front camera of the tablet computer;
  • I xy f(x, y);
  • f(x, y) (R xy , G xy , B xy );
  • R xy represents the color value of the image pixel in the red channel
  • G xy represents the color value of the image pixel in the green channel
  • B xy represents the color value of the image pixel in the blue channel
  • Step 3 extracting a position image of the positioning hole in the image acquired by the front camera
  • the color image acquired in step 2 is converted into a grayscale image.
  • the specific formula is:
  • Gray(x, y) 0.2989 ⁇ R xy +0.5870 ⁇ G xy +0.1140 ⁇ B xy ;
  • Gray(x, y) represents a grayscale image
  • a template matrix is defined to extract the positioning holes, the template matrix size is (n+2) ⁇ (n+2), and the template matrix is a square matrix with an n ⁇ n zero matrix in the middle and a boundary of 1, the template matrix Specifically:
  • mask (n+2) ⁇ (n+2) represents a template matrix
  • grayscale image is convoluted together with the template matrix
  • the positioning hole Since the positioning hole is disposed on the bottom side of the side wall of the third groove, the positioning hole should be located in the upper half of the grayscale image, and only the upper half of the grayscale image is processed together with the template matrix during the convolution operation. Yes;
  • M r represents the height of the image
  • M c represents the width of the image
  • C (s, t) represents the convolved image
  • the specific value of n is determined by the diameter of the positioning hole in the image
  • the convolution image is subtracted from the gray image to obtain a difference image, and then the pixel value of the difference image is calculated, and the difference image is binarized.
  • the specific formula is:
  • B(x, y) represents a binarized image of the difference image
  • the morphological prior knowledge is used to filter the locating hole area, and the specific steps for obtaining the locating hole position image are:
  • 8 neighborhood connectivity refers to the point that the pixel value of one pixel is non-zero, and the other pixel points have non-zero pixel values in the upper, lower, left, right, upper left, upper right, lower left, and lower right directions.
  • the two pixels are connected in 8 neighborhoods, so different connected areas can be distinguished one by one;
  • step b) separately calculating the area of the connected area marked in step a), and setting the area threshold;
  • step c) separately calculating the eccentricity of the connected region marked in step a), and setting the eccentricity threshold;
  • the positioning area can be filtered out, and the positioning hole image is obtained;
  • Step 4 Determine the position of the positioning hole by using the position image extracted in the third step, and determine whether the tablet computer is accurately installed by the position of the positioning hole. If the steps 1 to 4 are not performed accurately, re-install until the measurement is accurate. If the installation is accurate, perform step five;
  • the positioning hole In the correct image obtained by the front camera, the positioning hole should be located at the center point of the image; a deviation threshold is preset, as long as the deviation of the positioning hole is less than or equal to the deviation threshold, the installation is considered accurate; if a positioning hole appears in the image, but the positioning If the hole exceeds the deviation threshold, it means that the tablet is not properly installed; if the positioning hole does not appear in the image, it means that the tablet or helmet detector is not properly installed;
  • Step 5 extracting a position image containing only the groove line in the image, and measuring an absolute value of the angle between the long axis of the groove line and the X axis;
  • the color image acquired in step 2 is converted into a grayscale image.
  • the specific formula is:
  • Gray(x, y) 0.2989 ⁇ R xy +0.5870 ⁇ G xy +0.1140 ⁇ B xy ;
  • Gray(x, y) represents a grayscale image
  • a template matrix is defined to extract slot lines, the template matrix size is (n+2) ⁇ (n+2), and the template matrix is a square matrix with an n ⁇ n zero matrix in the middle and a boundary of 1, template matrix Specifically:
  • mask (n+2) ⁇ (n+2) represents a template matrix
  • grayscale image is convoluted together with the template matrix
  • the positioning hole Since the positioning hole is disposed on the bottom side of the side wall of the third groove, the positioning hole should be located in the upper half of the grayscale image, and only the upper half of the grayscale image is processed together with the template matrix during the convolution operation. Yes;
  • M r represents the height of the image
  • M c represents the width of the image
  • C (s, t) represents the convolved image
  • the specific value of h is determined by the width of the groove line in the image
  • the convolution image is subtracted from the gray image to obtain a difference image, and then the pixel value of the difference image is calculated, and the difference image is binarized.
  • the specific formula is:
  • B(x, y) represents a binarized image of the difference image, and ⁇ represents a preset empirical threshold in the slot line binarization process;
  • the morphological prior knowledge is used to filter the area of the slot line to obtain an image containing only the slot line.
  • the specific steps are as follows:
  • 8 neighborhood connectivity refers to the point that the pixel value of one pixel is non-zero, and the other pixel points have non-zero pixel values in the upper, lower, left, right, upper left, upper right, lower left, and lower right directions.
  • the two pixels are connected in 8 neighborhoods, so different connected areas can be distinguished one by one;
  • step 2) Calculate the length of the major axis and the minor axis of the connected region marked in step 1), respectively, and calculate the ratio of the major axis to the minor axis, and set the threshold value of the long and short axis ratio;
  • step 1) separately calculating the area of the connected area marked in step 1), and setting the area threshold;
  • the number of pixels included in each of the 8 neighborhood connected components is calculated, and the number of pixels is the area of the connected region;
  • the area in the connected area that exceeds the area threshold or the long-short axis ratio threshold is a non-slot line area, which is filtered out;
  • the correct positional relationship between the positioning hole and the groove line should be that the positioning hole is located in the middle, and the groove line is located around the positioning hole; if the correct positional relationship between the positioning hole and the groove line is not satisfied, it is a non-slot line area, and is filtered out , resulting in an image containing only slot lines;
  • Step 6 determining whether the mirror is accurately installed by the absolute value of the angle between the long axis of the slot line and the X axis;
  • the mirror If the absolute value of the angle between the long axis of the slot line and the X axis is greater than the preset deviation angle threshold, the mirror is considered to be rotated and the installation is incorrect, otherwise the installation is accurate.
  • the hardware of the invention is ingeniously designed, and only one positioning hole is placed on the base of the tablet computer, the structure is simple and the cost is low, but the size and position of the positioning hole are verified by a large number of experiments, which is more scientific, convenient for the camera to collect images, and can quickly detect and install. whether succeed.
  • the calculation speed of the invention is fast, and the time of each positioning detection is about 50 ms.
  • the detection performance of the invention is stable, and the installation of different illuminations and different tablet computers can be quickly tested, and the applicability is stronger.
  • the invention provides a positioning hole on the educational toy set, and can apply a targeted image processing technology to detect whether the position of the preset positioning hole on the component is centered, and whether the groove line is located symmetrically above the positioning hole, thereby realizing the installation of the mirror. calibration.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • Image Processing (AREA)

Abstract

一种教育玩具套件及其反光镜位置检测方法，教育玩具套件包括支架（1）、头盔探测器（2）和底板（3），支架（1）安装于底板（3）上，头盔探测器（2）安装于支架（1）上，底板（3）上方设置有第一凹槽（301）；支架（1）底部具有凸起（101），凸起（101）安装在第一凹槽（301）内，顶部具有第二凹槽（102）和第三凹槽（103），第二凹槽（102）用于放置平板电脑；头盔探测器（2）安装于第三凹槽（103）内；还包括：定位孔（104），设置于第三凹槽（103）的侧壁底侧，并且位于侧壁的纵向中心轴上；头盔探测器（2）包括：本体（201）、第四凹槽（202）、扇形块（203）和反光镜（204）。反光镜位置检测方法包括：通过前置摄像头采集图像；检测定位孔（104）和槽线的位置；对图像进行处理，由定位孔（104）、槽线与X轴的夹角判定反光镜（204）是否安装准确。

Description

一种教育玩具套件及其反光镜位置检测方法 技术领域
本发明涉及计算机视觉检测处理技术领域，特别涉及一种教育玩具套件及其反光镜位置检测方法。
背景技术
现在平板电脑上有许多有趣的幼教游戏应用程序或者儿童游戏，但往往只是让小朋友在屏幕上指指画画，互动性欠缺，长时间看着屏幕容易对眼睛造成伤害；而当下一些互动性强的传统性游戏玩具已经脱离了时代的发展，形式上无法满足孩子学习、玩耍的需求，也不便于孩子和家长的互动沟通。
为了解决上述问题，应用计算机视觉识别处理技术领域成功的开发了一种教育玩具套件，包括：支架、头盔探测器和底板，并且支架安装于底板上，头盔探测器安装于支架上；底板上方设置有第一凹槽；支架底部具有凸起，凸起安装在第一凹槽内，顶部具有第二凹槽和第三凹槽，第二凹槽用于放置平板电脑；头盔探测器安装于第三凹槽内。
上述的教育玩具套件虽然解决了平板电脑中游戏的互动性欠缺的问题，但是其关键部件反光镜安装常常出现偏差，会导致安装缓慢，图像采集出错，分析结果不准确等问题的出现。
技术问题
因此，急需一种教育玩具套件及其反光镜位置检测方法，在教育玩具套件上设置定位孔，能够应用针对性的图像处理技术检测部件上预设的定位孔的位置是否居中，槽线是否位于对称的位于定位孔的上方，实现对反光镜安装的校准。
技术解决方案
本发明为了解决上述问题，提供了一种教育玩具套件及其反光镜位置检测方法，技术方案如下：
一种教育玩具套件，包括支架、头盔探测器和底板，并且支架安装于底板上，头盔探测器安装于支架上，底板上方设置有第一凹槽；支架底部具有凸起，凸起安装在第一凹槽内，顶部具有第二凹槽和第三凹槽，第二凹槽用于放置平板电脑；头盔探测器安装于第三凹槽内；还包括：定位孔，设置于第三凹槽侧壁的纵向中心轴上；
头盔探测器还包括：本体、第四凹槽、2个扇形块和反光镜，并且第四凹槽位于本体内，用于夹持不同型号的平板电脑，在第四凹槽夹持平板电脑屏幕的端点处设置有反光镜， 反光镜的另一端安装于头盔探测器边缘上，反光镜与水平面夹角成锐角，第四凹槽夹持平板电脑屏幕的端点高于平板电脑的摄像头位置，2个扇形块位于反光镜的2个边缘上，用于固定反光镜和夹持平板电脑。
优选的，在上述的一种教育玩具套件中，在第四凹槽夹持平板电脑的背部外壳处设置有固定支点，用于夹紧平板电脑。
一种教育玩具套件的反光镜位置检测方法，包括如下步骤：
步骤一，首先将平板电脑的底端安装于第二凹槽内，然后通过第四凹槽将头盔探测器安装于平板电脑的顶端；
步骤二，固定安装好后，通过平板电脑的前置摄像头采集图像；
步骤三，在前置摄像头采集的图像中提取出定位孔的位置图像；
步骤四，通过步骤三中提取出的位置图像，判断出定位孔的位置，由定位孔的位置判定平板电脑是否安装准确如果不准确执行步骤一至四的步骤，重新安装，直至测定安装准确为止，如果安装准确执行步骤五；
前置摄像头获得的正确图像中，定位孔应该位于图像的中心点位置；预先设定一个偏差阈值，只要定位孔的偏差小于等于偏差阈值即认为安装准确；如果图像中出现了定位孔，但是定位孔超过偏差阈值，则表示平板电脑没有正确安装；如果定位孔没有出现在图像中，则表示平板电脑或者头盔探测器没有正确安装；
步骤五，在图像中提取只含有槽线的位置图像，并且测定槽线长轴与X轴的夹角绝对值；
步骤六，由槽线长轴与X轴的夹角绝对值判定反光镜是否安装准确。
优选的，在上述一种教育玩具套件的反光镜位置检测方法中，步骤二的具体步骤为：
将平板电脑前置摄像头所获取图像定义为Ixy，Ixy＝f(x，y)；
其中，(x，y)表示图像像素点的位置坐标，f(x，y)表示图像的在(x，y)上的像素值；
由于摄像头采集的图像为彩色图片，因此f(x，y)＝(Rxy，Gxy，Bxy)；
其中，Rxy表示图像像素点在红色通道的色彩值，Gxy表示图像像素点在绿色通道的色彩值，Bxy表示图像像素点在蓝色通道的色彩值。
优选的，在上述一种教育玩具套件的反光镜位置检测方法中，步骤三的具体步骤为：
首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
其中，Gray(x，y)表示灰度图像；
进一步地，定义一个模板矩阵用以提取定位孔，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
Figure PCTCN2016086800-appb-000001
其中，mask(n+2)×(n+2)表示模板矩阵；
进一步地，把灰度图像与模板矩阵一起做卷积运算；
因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
卷积运算的具体公式为：
Figure PCTCN2016086800-appb-000002
Figure PCTCN2016086800-appb-000003
0≤s≤Mr+n+1；
0≤t≤Mc+n+1；
Figure PCTCN2016086800-appb-000004
其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，n的具体数值由图像中定位孔的直径确定；
进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
Figure PCTCN2016086800-appb-000005
其中，B(x，y)表示差图像的二值化图像，γ表示定位孔二值化处理中的经验阈值；
进一步地，采用形态学先验知识滤除非定位孔区域，得到只含有定位孔的位置图像。
优选的，在上述一种教育玩具套件的定位孔检测定位方法中，步骤三中采用形态学先验知识滤除非定位孔区域，得到只含有定位孔的位置图像的具体步骤为：
a)对差图像的二值化图像做8邻域连通分量标记；
8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
b)分别计算步骤a)标记完成的连通区域的面积，并且设定面积阈值；
计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
c)分别计算步骤a)标记完成的连通区域的离心率，并且设定离心率阈值；
d)根据每个连通区域的面积、面积阈值、离心率以及离心率阈值即可滤除非定位区域，得出定位孔位置图像；
首先，将步骤b)中计算得出的连通区域的面积数值与面积阈值进行比较，当面积数值超出面积阈值范围时表示该连通区域为非定位区域，将其滤除；
然后，将步骤c)中计算得出的连通区域的离心率与离心率阈值相比较，当离心率超出离心率阈值范围时表示该连通区域为非定位区域，将其滤除；
进一步地，滤除非定位区域的剩余连通区域为定位孔位置图像。
优选的，在上述一种教育玩具套件的反光镜位置检测方法中，步骤五的具体步骤为：
首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
其中，Gray(x，y)表示灰度图像；
进一步地，定义一个模板矩阵用以提取槽线，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
Figure PCTCN2016086800-appb-000006
其中，mask(n+2)×(n+2)表示模板矩阵；
进一步地，把灰度图像与模板矩阵一起做卷积运算；
因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
卷积运算的具体公式为：
Figure PCTCN2016086800-appb-000007
Figure PCTCN2016086800-appb-000008
0≤s≤Mr+n+1；
0≤t≤Mc+n+1；
Figure PCTCN2016086800-appb-000009
其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，h的具体数值由图像中槽线的宽度确定；
进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
Figure PCTCN2016086800-appb-000010
其中，B(x，y)表示差图像的二值化图像，β表示槽线二值化处理中预先设定的经验阈值；
进一步地，采用形态学先验知识滤除非槽线区域，得到只含有槽线的图像。
优选的，在上述一种教育玩具套件的反光镜位置检测方法中，步骤五中采用形态学先验知识滤除非槽线区域，得到只含有槽线的图像的具体步骤为：
1)对差图像的二值化图像做8邻域连通分量标记；
8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
2)分别计算步骤1)标记完成的连通区域的长轴和短轴长度，并且计算长轴与短轴的比率，并且设定长短轴比率阈值；
3)分别计算步骤1)标记完成的连通区域的长轴与X轴夹角的绝对值，夹角取值范围为0-90°；
4)分别计算步骤1)标记完成的连通区域的面积，并且设定面积阈值；
首先，计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
5)根据每个连通区域的面积、面积阈值、长短轴比率、长短轴比率阈值即可滤除大部分非槽线区域；
连通区域内超出面积阈值或者长短轴比率阈值的区域为非槽线区域，将其滤除；
6)计算定位孔与槽线的相互关系，滤除所有非槽线区域，得出只含有槽线的图像。
定位孔与槽线的正确位置关系应该是定位孔位于中间，槽线位于定位孔的四周；如果不满足上述定位孔与槽线的正确位置关系，则其为非槽线区域，将其滤除，得出只含有槽线的图像。
优选的，在上述一种教育玩具套件的反光镜位置检测方法中，步骤六中由槽线的长轴与X轴夹角的绝对值判定反光镜是否安装准确的评判标准为：
如果槽线的长轴与X轴夹角的绝对值大于预先设定的偏差角度阈值，则认为反光镜发生旋转，安装错误，否则安装准确。
有益效果
1、硬件设计巧妙，本发明只在平板电脑底座上打上一个定位孔，结构简单，成本低廉，但是定位孔的大小和位置是经过大量的实验验证的，更加科学，便于摄像头采集图像，能够快速检测安装是否成功。
2、计算速度快，每次定位检测耗时在50ms左右。
3、检测性能稳定，对不同光照、不同平板电脑的安装都能够快速的进行测试，适用性更强。
4、本发明在教育玩具套件上设置定位孔，能够应用针对性的图像处理技术检测部件上预设的定位孔的位置是否居中，槽线是否位于对称的位于定位孔的上方，实现对反光镜安装的校准。
附图说明
下面结合附图和具体实施方式来详细说明本发明：
图1是本实用新型一种教育玩具套件的结构示意图。
图2是本实用新型一种教育玩具套件的支架的后视图。
图3是本实用新型一种教育玩具套件的支架的立体图。
图4是本实用新型一种教育玩具套件的底板的结构示意图。
图5是本实用新型葡萄探索号教育玩具套件的头盔探测器的结构示意图。
图6是本实用新型葡萄探索号教育玩具套件的应用示意图。
图7是一种教育玩具套件的反光镜位置检测方法的流程图。
其中，图1-7中的附图标记与部件名称之间的对应关系为：
支架1，凸起101，第二凹槽102，第三凹槽103，碟状底架104，圆形顶架105，露空提手106，头盔探测器2，本体201，第四凹槽202，2个扇形块203，反光镜204，固定支点205，底板3，第一凹槽301。
本发明的最佳实施方式
实施例2：
图7是一种教育玩具套件及其反光镜位置检测方法的流程图。
如图7所示，一种教育玩具套件及其反光镜位置检测方法，包括如下步骤：
步骤一，首先将平板电脑的底端安装于第二凹槽内，然后通过第四凹槽将头盔探测器安装于平板电脑的顶端；
步骤二，固定安装好后，通过平板电脑的前置摄像头采集图像；
将平板电脑前置摄像头所获取图像定义为Ixy，Ixy＝f(x，y)；
其中，(x，y)表示图像像素点的位置坐标，f(x，y)表示图像的在(x，y)上的像素值；
由于摄像头采集的图像为彩色图片，因此f(x，y)＝(Rxy，Gxy，Bxy)；
其中，Rxy表示图像像素点在红色通道的色彩值，Gxy表示图像像素点在绿色通道的色彩值，Bxy表示图像像素点在蓝色通道的色彩值；
步骤三，在前置摄像头采集的图像中提取出定位孔的位置图像；
首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
其中，Gray(x，y)表示灰度图像；
进一步地，定义一个模板矩阵用以提取定位孔，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
Figure PCTCN2016086800-appb-000011
其中，mask(n+2)×(n+2)表示模板矩阵；
进一步地，把灰度图像与模板矩阵一起做卷积运算；
因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
卷积运算的具体公式为：
Figure PCTCN2016086800-appb-000012
Figure PCTCN2016086800-appb-000013
0≤s≤Mr+n+1；
0≤t≤Mc+n+1；
Figure PCTCN2016086800-appb-000014
其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，n的具体数值由图像中定位孔的直径确定；
进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
Figure PCTCN2016086800-appb-000015
其中，B(x，y)表示差图像的二值化图像；
进一步地，采用形态学先验知识滤除非定位孔区域，得出定位孔位置图像的具体步骤为：
a)对差图像的二值化图像做8邻域连通分量标记；
8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
b)分别计算步骤a)标记完成的连通区域的面积，并且设定面积阈值；
计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
c)分别计算步骤a)标记完成的连通区域的离心率，并且设定离心率阈值；
d)根据每个连通区域的面积、面积阈值、离心率以及离心率阈值即可滤除非定位区域，得出定位孔图像；
首先，将步骤b)中计算得出的连通区域的面积数值与面积阈值进行比较，当面积数值超出面积阈值范围时表示该连通区域为非定位区域，将其滤除；
然后，将步骤c)中计算得出的连通区域的离心率与离心率阈值相比较，当离心率超出离心率阈值范围时表示该连通区域为非定位区域，将其滤除；
进一步地，滤除非定位区域的剩余连通区域为定位孔的位置图像；
步骤四，通过步骤三中提取出的位置图像，判断出定位孔的位置，由定位孔的位置判定平板电脑是否安装准确如果不准确执行步骤一至四的步骤，重新安装，直至测定安装准确为止，如果安装准确执行步骤五；
前置摄像头获得的正确图像中，定位孔应该位于图像的中心点位置；预先设定一个偏差阈值，只要定位孔的偏差小于等于偏差阈值即认为安装准确；如果图像中出现了定位孔，但是定位孔超过偏差阈值，则表示平板电脑没有正确安装；如果定位孔没有出现在图像中，则表示平板电脑或者头盔探测器没有正确安装；
步骤五，在图像中提取只含有槽线的位置图像，并且测定槽线长轴与X轴的夹角绝对值；
首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
其中，Gray(x，y)表示灰度图像；
进一步地，定义一个模板矩阵用以提取槽线，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
Figure PCTCN2016086800-appb-000016
其中，mask(n+2)×(n+2)表示模板矩阵；
进一步地，把灰度图像与模板矩阵一起做卷积运算；
因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
卷积运算的具体公式为：
Figure PCTCN2016086800-appb-000017
Figure PCTCN2016086800-appb-000018
0≤s≤Mr+n+1；
0≤t≤Mc+n+1；
Figure PCTCN2016086800-appb-000019
其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，h的具体数值由图像中槽线的宽度确定；
进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
Figure PCTCN2016086800-appb-000020
其中，B(x，y)表示差图像的二值化图像，β表示槽线二值化处理中预先设定的经验阈值；
进一步地，采用形态学先验知识滤除非槽线区域，得到只含有槽线的图像，具体步骤为：
1)对差图像的二值化图像做8邻域连通分量标记；
8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
2)分别计算步骤1)标记完成的连通区域的长轴和短轴长度，并且计算长轴与短轴的比率，并且设定长短轴比率阈值；
3)分别计算步骤1)标记完成的连通区域的长轴与X轴夹角的绝对值，夹角取值范围为0-90°；
4)分别计算步骤1)标记完成的连通区域的面积，并且设定面积阈值；
首先，计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
5)根据每个连通区域的面积、面积阈值、长短轴比率、长短轴比率阈值即可滤除大部分非槽线区域；
连通区域内超出面积阈值或者长短轴比率阈值的区域为非槽线区域，将其滤除；
6)计算定位孔与槽线的相互关系，滤除所有非槽线区域，得出只含有槽线的图像；
定位孔与槽线的正确位置关系应该是定位孔位于中间，槽线位于定位孔的四周；如果不满足上述定位孔与槽线的正确位置关系，则其为非槽线区域，将其滤除，得出只含有槽线的图像；
步骤六，由槽线长轴与X轴的夹角绝对值判定反光镜是否安装准确；
如果槽线的长轴与X轴夹角的绝对值大于预先设定的偏差角度阈值，则认为反光镜发生旋转，安装错误，否则安装准确。
本发明的实施方式
为了使本发明技术实现的措施、创作特征、达成目的与功效易于明白了解，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
实施例1：
图1是本实用新型一种教育玩具套件的结构示意图。
图2是本实用新型一种教育玩具套件的支架的后视图。
图3是本实用新型一种教育玩具套件的支架的立体图。
图4是本实用新型一种教育玩具套件的底板的结构示意图。
图5是本实用新型葡萄探索号教育玩具套件的头盔探测器的结构示意图。
图6是本实用新型葡萄探索号教育玩具套件的应用示意图。
如图1-6所示，一种教育玩具套件，包括支架1、头盔探测器2和底板3，并且支架1安装于底板3上，头盔探测器2安装于支架1上；底板3，上方设置有第一凹槽301；支架1，底部具有凸起101，凸起101安装在第一凹槽301内，顶部具有第二凹槽102和第三凹槽103，第二凹槽102用于放置平板电脑；头盔探测器2，安装于第三凹槽103内；还包括：定位孔104，设置于第三凹槽103侧壁的纵向中心轴上；头盔探测器2还包括：本体201、第四凹槽202、2个扇形块203和反光镜204，并且第四凹槽202位于本体201内，用于夹持不同型号的平板电脑，在第四凹槽202夹持平板电脑屏幕的端点处设置有反光镜204，反光镜204的另一端安装于头盔探测器2边缘上，反光镜204与水平面夹角成锐角， 第四凹槽202夹持平板电脑屏幕的端点高于平板电脑的摄像头位置，2个扇形块203位于反光镜204的2个边缘上，用于固定反光镜204和夹持平板电脑。
本实施例中，在第四凹槽202夹持平板电脑的背部外壳处设置有固定支点205，用于夹紧平板电脑。
图7是一种教育玩具套件的反光镜位置检测方法的流程图。
如图7所示，一种教育玩具套件的反光镜位置检测方法，包括如下步骤：
步骤一，首先将平板电脑的底端安装于第二凹槽内，然后通过第四凹槽将头盔探测器安装于平板电脑的顶端；
步骤二，固定安装好后，通过平板电脑的前置摄像头采集图像；
步骤三，在前置摄像头采集的图像中提取出定位孔的位置图像；
步骤四，通过步骤三中提取出的位置图像，判断出定位孔的位置，由定位孔的位置判定平板电脑是否安装准确如果不准确执行步骤一至四的步骤，重新安装，直至测定安装准确为止，如果安装准确执行步骤五；
前置摄像头获得的正确图像中，定位孔应该位于图像的中心点位置；预先设定一个偏差阈值，只要定位孔的偏差小于等于偏差阈值即认为安装准确；如果图像中出现了定位孔，但是定位孔超过偏差阈值，则表示平板电脑没有正确安装；如果定位孔没有出现在图像中，则表示平板电脑或者头盔探测器没有正确安装；
步骤五，在图像中提取只含有槽线的位置图像，并且测定槽线长轴与X轴的夹角绝对值；
步骤六，由槽线长轴与X轴的夹角绝对值判定反光镜是否安装准确。
实施例2：
图7是一种教育玩具套件及其反光镜位置检测方法的流程图。
如图7所示，一种教育玩具套件及其反光镜位置检测方法，包括如下步骤：
步骤一，首先将平板电脑的底端安装于第二凹槽内，然后通过第四凹槽将头盔探测器安装于平板电脑的顶端；
步骤二，固定安装好后，通过平板电脑的前置摄像头采集图像；
将平板电脑前置摄像头所获取图像定义为Ixy，Ixy＝f(x，y)；
其中，(x，y)表示图像像素点的位置坐标，f(x，y)表示图像的在(x，y)上的像素值；
由于摄像头采集的图像为彩色图片，因此f(x，y)＝(Rxy，Gxy，Bxy)；
其中，Rxy表示图像像素点在红色通道的色彩值，Gxy表示图像像素点在绿色通道的色彩值，Bxy表示图像像素点在蓝色通道的色彩值；
步骤三，在前置摄像头采集的图像中提取出定位孔的位置图像；
首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
其中，Gray(x，y)表示灰度图像；
进一步地，定义一个模板矩阵用以提取定位孔，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
Figure PCTCN2016086800-appb-000021
其中，mask(n+2)×(n+2)表示模板矩阵；
进一步地，把灰度图像与模板矩阵一起做卷积运算；
因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
卷积运算的具体公式为：
Figure PCTCN2016086800-appb-000022
Figure PCTCN2016086800-appb-000023
0≤s≤Mr+n+1；
0≤t≤Mc+n+1；
Figure PCTCN2016086800-appb-000024
其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，n的具体数值由图像中定位孔的直径确定；
进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
Figure PCTCN2016086800-appb-000025
其中，B(x，y)表示差图像的二值化图像；
进一步地，采用形态学先验知识滤除非定位孔区域，得出定位孔位置图像的具体步骤为：
a)对差图像的二值化图像做8邻域连通分量标记；
8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
b)分别计算步骤a)标记完成的连通区域的面积，并且设定面积阈值；
计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
c)分别计算步骤a)标记完成的连通区域的离心率，并且设定离心率阈值；
d)根据每个连通区域的面积、面积阈值、离心率以及离心率阈值即可滤除非定位区域，得出定位孔图像；
首先，将步骤b)中计算得出的连通区域的面积数值与面积阈值进行比较，当面积数值超出面积阈值范围时表示该连通区域为非定位区域，将其滤除；
然后，将步骤c)中计算得出的连通区域的离心率与离心率阈值相比较，当离心率超出离心率阈值范围时表示该连通区域为非定位区域，将其滤除；
进一步地，滤除非定位区域的剩余连通区域为定位孔的位置图像；
步骤四，通过步骤三中提取出的位置图像，判断出定位孔的位置，由定位孔的位置判定平板电脑是否安装准确如果不准确执行步骤一至四的步骤，重新安装，直至测定安装准确为止，如果安装准确执行步骤五；
前置摄像头获得的正确图像中，定位孔应该位于图像的中心点位置；预先设定一个偏差阈值，只要定位孔的偏差小于等于偏差阈值即认为安装准确；如果图像中出现了定位孔，但是定位孔超过偏差阈值，则表示平板电脑没有正确安装；如果定位孔没有出现在图像中，则表示平板电脑或者头盔探测器没有正确安装；
步骤五，在图像中提取只含有槽线的位置图像，并且测定槽线长轴与X轴的夹角绝对值；
首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
其中，Gray(x，y)表示灰度图像；
进一步地，定义一个模板矩阵用以提取槽线，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
Figure PCTCN2016086800-appb-000026
其中，mask(n+2)×(n+2)表示模板矩阵；
进一步地，把灰度图像与模板矩阵一起做卷积运算；
因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
卷积运算的具体公式为：
Figure PCTCN2016086800-appb-000027
Figure PCTCN2016086800-appb-000028
0≤s≤Mr+n+1；
0≤t≤Mc+n+1；
Figure PCTCN2016086800-appb-000029
其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，h的具体数值由图像中槽线的宽度确定；
进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
Figure PCTCN2016086800-appb-000030
其中，B(x，y)表示差图像的二值化图像，β表示槽线二值化处理中预先设定的经验阈值；
进一步地，采用形态学先验知识滤除非槽线区域，得到只含有槽线的图像，具体步骤为：
1)对差图像的二值化图像做8邻域连通分量标记；
8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
2)分别计算步骤1)标记完成的连通区域的长轴和短轴长度，并且计算长轴与短轴的比率，并且设定长短轴比率阈值；
3)分别计算步骤1)标记完成的连通区域的长轴与X轴夹角的绝对值，夹角取值范围为0-90°；
4)分别计算步骤1)标记完成的连通区域的面积，并且设定面积阈值；
首先，计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
5)根据每个连通区域的面积、面积阈值、长短轴比率、长短轴比率阈值即可滤除大部分非槽线区域；
连通区域内超出面积阈值或者长短轴比率阈值的区域为非槽线区域，将其滤除；
6)计算定位孔与槽线的相互关系，滤除所有非槽线区域，得出只含有槽线的图像；
定位孔与槽线的正确位置关系应该是定位孔位于中间，槽线位于定位孔的四周；如果不满足上述定位孔与槽线的正确位置关系，则其为非槽线区域，将其滤除，得出只含有槽线的图像；
步骤六，由槽线长轴与X轴的夹角绝对值判定反光镜是否安装准确；
如果槽线的长轴与X轴夹角的绝对值大于预先设定的偏差角度阈值，则认为反光镜发生旋转，安装错误，否则安装准确。
本发明硬件设计巧妙，只在平板电脑底座上打上一个定位孔，结构简单，成本低廉，但是定位孔的大小和位置是经过大量的实验验证的，更加科学，便于摄像头采集图像，能够快速检测安装是否成功。
本发明计算速度快，每次定位检测耗时在50ms左右。
本发明检测性能稳定，对不同光照、不同平板电脑的安装都能够快速的进行测试，适用性更强。
本发明在教育玩具套件上设置定位孔，能够应用针对性的图像处理技术检测部件上预设的定位孔的位置是否居中，槽线是否位于对称的位于定位孔的上方，实现对反光镜安装的校准。
以上显示和描述了本发明的基本原理、主要特征和本发明的优点。本行业的技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下本发明还会有各种变化和改进，这些变化和改进都落入要求保护的本发明范围内。本发明要求保护范围由所附的权利要求书及其等同物界定。
工业实用性
所属领域技术人员根据上文的记载容易得知，本发明技术方案适合在工业中制造并在生产、生活中使用，因此本发明具备工业实用性。

Claims (9)

  1. 一种教育玩具套件，包括：支架、头盔探测器和底板，并且所述支架安装于底板上，头盔探测器安装于支架上，所述底板上方设置有第一凹槽；所述支架底部具有凸起，所述凸起安装在第一凹槽内，顶部具有第二凹槽和第三凹槽，所述第二凹槽用于放置平板电脑；所述头盔探测器安装于第三凹槽内；其特征在于，还包括：定位孔，设置于所述第三凹槽侧壁的纵向中心轴上；
    所述头盔探测器还包括：本体、第四凹槽、2个扇形块和反光镜，并且所述第四凹槽位于本体内，用于夹持不同型号的平板电脑，在所述第四凹槽夹持平板电脑屏幕的端点处设置有反光镜，所述反光镜的另一端安装于头盔探测器边缘上，所述反光镜与水平面夹角成锐角，所述第四凹槽夹持平板电脑屏幕的端点高于平板电脑的摄像头位置，2个所述扇形块位于反光镜的2个边缘上，用于固定所述反光镜和夹持平板电脑。
  2. 根据权利要求亲1所述的一种教育玩具套件，其特征在于，在所述第四凹槽夹持平板电脑的背部外壳处设置有固定支点，用于夹紧平板电脑。
  3. 一种教育玩具套件的反光镜位置检测方法，其特征在于，包括如下步骤：
    步骤一，首先将平板电脑的底端安装于第二凹槽内，然后通过第四凹槽将头盔探测器安装于平板电脑的顶端；
    步骤二，固定安装好后，通过平板电脑的前置摄像头采集图像；
    步骤三，在前置摄像头采集的图像中提取出定位孔的位置图像；
    步骤四，通过步骤三中提取出的位置图像，判断出定位孔的位置，由定位孔的位置判定平板电脑是否安装准确如果不准确执行所述步骤一至四的步骤，重新安装，直至测定安装准确为止，如果安装准确执行步骤五；
    前置摄像头获得的正确图像中，定位孔应该位于图像的中心点位置；预先设定一个偏差阈值，只要定位孔的偏差小于等于偏差阈值即认为安装准确；如果图像中出现了定位孔，但是定位孔超过偏差阈值，则表示平板电脑没有正确安装；如果定位孔没有出现在图像中，则表示平板电脑或者头盔探测器没有正确安装；
    所述步骤五，在图像中提取只含有槽线的位置图像，并且测定槽线长轴与X轴的夹角绝对值；
    步骤六，由槽线长轴与X轴的夹角绝对值判定反光镜是否安装准确。
  4. 根据权利要求3所述的一种教育玩具套件的反光镜位置检测方法，其特征在于，所述步骤二的具体步骤为：
    将平板电脑前置摄像头获取的图像定义为Ixy，Ixy＝f(x，y)；
    其中，(x，y)表示图像像素点的位置坐标，f(x，y)表示图像的在(x，y)上的像素值；
    由于摄像头采集的图像为彩色图片，因此f(x，y)＝(Rxy，Gxy，Bxy)；
    其中，Rxy表示图像像素点在红色通道的色彩值，Gxy表示图像像素点在绿色通道的色彩值，Bxy表示图像像素点在蓝色通道的色彩值；
  5. 根据权利要求4所述的一种教育玩具套件的反光镜位置检测方法，其特征在于，所述步骤三的具体步骤为：
    首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
    Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
    其中，Gray(x，y)表示灰度图像；
    进一步地，定义一个模板矩阵用以提取定位孔，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
    Figure PCTCN2016086800-appb-100001
    其中，mask(n+2)×(n+2)表示模板矩阵；
    进一步地，把灰度图像与模板矩阵一起做卷积运算；
    因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
    卷积运算的具体公式为：
    Figure PCTCN2016086800-appb-100002
    Figure PCTCN2016086800-appb-100003
    0≤s≤Mr+n+1；
    0≤t≤Mc+n+1；
    Figure PCTCN2016086800-appb-100004
    其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，n的具体数值由图像中定位孔的直径确定；
    进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
    Figure PCTCN2016086800-appb-100005
    其中，B(x，y)表示差图像的二值化图像；
    进一步地，采用形态学先验知识滤除非定位孔区域，得到只含有定位孔的图像。
  6. 根据权利要求5所述的一种教育玩具套件的反光镜位置检测方法，其特征在于，所述步骤三中采用形态学先验知识滤除非定位孔区域，得到只含有定位孔的图像的具体步骤为：
    a)对差图像的二值化图像做8邻域连通分量标记；
    8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
    b)分别计算所述步骤a)标记完成的连通区域的面积，并且设定面积阈值；
    计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
    c)分别计算所述步骤a)标记完成的连通区域的离心率，并且设定离心率阈值；
    d)根据每个连通区域的面积、面积阈值、离心率以及离心率阈值即可滤除非定位区域，得出定位孔位置图像；
    首先，将所述步骤b)中计算得出的连通区域的面积数值与面积阈值进行比较，当面积数值超出面积阈值范围时表示该连通区域为非定位区域，将其滤除；
    然后，将所述步骤c)中计算得出的连通区域的离心率与离心率阈值相比较，当离心率超出离心率阈值范围时表示该连通区域为非定位区域，将其滤除；
    进一步地，滤除非定位区域的剩余连通区域为定位孔位置图像。
  7. 根据权利要求6所述的一种教育玩具套件的反光镜位置检测方法，其特征在于，所述步骤五的具体步骤为：
    首先，把步骤二中采集得到的彩色图像转换为灰度图像，具体公式为：
    Gray(x，y)＝0.2989×Rxy+0.5870×Gxy+0.1140×Bxy；
    其中，Gray(x，y)表示灰度图像；
    进一步地，定义一个模板矩阵用以提取槽线，模板矩阵大小为(n+2)×(n+2)，并且模板矩阵是中间为n×n零矩阵、边界为1的方形矩阵，模板矩阵具体为：
    Figure PCTCN2016086800-appb-100006
    其中，mask(n+2)×(n+2)表示模板矩阵；
    进一步地，把灰度图像与模板矩阵一起做卷积运算；
    因为定位孔设置于第三凹槽的侧壁底侧，所以定位孔应该位于灰度图像的上半部分，在卷积运算的过程中只去灰度图像的上半部分与模板矩阵一起做运算即可；
    卷积运算的具体公式为：
    Figure PCTCN2016086800-appb-100007
    Figure PCTCN2016086800-appb-100008
    0≤s≤Mr+n+1；
    0≤t≤Mc+n+1；
    Figure PCTCN2016086800-appb-100009
    其中，Mr表示图像的高度，Mc表示图像的宽度，C(s，t)表示卷积图像，h的具体数值由图像中槽线的宽度确定；
    进一步地，从灰度图像中减去卷积图像得出差图像，再计算差图像的像素值，并对差图像进行二值化处理，具体公式为：
    Figure PCTCN2016086800-appb-100010
    其中，B(x，y)表示差图像的二值化图像，β表示槽线二值化处理中预先设定的经验阈值；
    进一步地，采用形态学先验知识滤除非槽线区域，得到只含有槽线的图像。
  8. 根据权利要求7所述的一种教育玩具套件的反光镜位置检测方法，其特征在于，所述步骤五中采用形态学先验知识滤除非槽线区域，得到只含有槽线的图像的具体步骤为：
    1)对差图像的二值化图像做8邻域连通分量标记；
    8邻域连通是指将一个像素的像素值非零，另一个像素点的上、下、左、右、左上、右上、左下、右下8个方向也存在非零像素值的点，则认为这2个像素点是8邻域连通的，因此不同的连通区域即可被一一区分出来；
    2)分别计算所述步骤1)标记完成的连通区域的长轴和短轴长度，并且计算长轴与短轴的比率，并且设定长短轴比率阈值；
    3)分别计算所述步骤1)标记完成的连通区域的长轴与X轴夹角的绝对值，夹角取值范围为0-90°；
    4)分别计算所述步骤1)标记完成的连通区域的面积，并且设定面积阈值；
    首先，计算每个8邻域连通分量中含有的像素个数，像素个数即为连通区域的面积；
    5)根据每个连通区域的面积、面积阈值、长短轴比率、长短轴比率阈值即可滤除大部分非槽线区域；
    连通区域内超出面积阈值或者长短轴比率阈值的区域为非槽线区域，将其滤除；
    6)计算定位孔与槽线的相互关系，滤除所有非槽线区域，得出只含有槽线的图像；
    定位孔与槽线的正确位置关系应该是定位孔位于中间，槽线位于定位孔的四周；如果不满足上述定位孔与槽线的正确位置关系，则其为非槽线区域，将其滤除，得出只含有槽线的图像。
  9. 根据权利要求8所述的一种教育玩具套件的反光镜位置检测方法，其特征在于，所述步骤六中由槽线的长轴与X轴夹角的绝对值判定反光镜是否安装准确的评判标准为：
    如果槽线的长轴与X轴夹角的绝对值大于预先设定的偏差角度阈值，则认为反光镜发生旋转，安装错误，否则安装准确。
PCT/CN2016/086800 2016-01-26 2016-06-22 一种教育玩具套件及其反光镜位置检测方法 WO2017128603A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610053440.2 2016-01-26
CN201610053440.2A CN105709434B (zh) 2016-01-26 2016-01-26 一种教育玩具套件及其反光镜位置检测方法

Publications (1)

Publication Number Publication Date
WO2017128603A1 true WO2017128603A1 (zh) 2017-08-03

Family

ID=56154051

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/086800 WO2017128603A1 (zh) 2016-01-26 2016-06-22 一种教育玩具套件及其反光镜位置检测方法

Country Status (2)

Country Link
CN (1) CN105709434B (zh)
WO (1) WO2017128603A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111724444A (zh) * 2020-06-16 2020-09-29 中国联合网络通信集团有限公司 目标物的抓取点的确定方法、装置及抓取系统

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105719318B (zh) * 2016-01-26 2018-07-10 上海葡萄纬度科技有限公司 一种教育玩具套件中基于hsv的魔方颜色识别方法
CN105719307A (zh) * 2016-01-26 2016-06-29 上海葡萄纬度科技有限公司 一种教育玩具套件及检测七巧板摆放形状、位置的方法
CN105498200A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其七巧板颜色识别方法
CN105513086B (zh) * 2016-01-26 2019-02-19 上海葡萄纬度科技有限公司 一种教育玩具套件及其基于形状匹配的魔方检测定位方法
CN106097833B (zh) * 2016-08-19 2019-08-30 上海葡萄纬度科技有限公司 一种教育玩具套件及其数字识别方法
CN106267843A (zh) * 2016-08-19 2017-01-04 上海葡萄纬度科技有限公司 一种教育玩具套件及其海洋模具识别方法
CN106297492B (zh) * 2016-08-19 2019-06-25 上海葡萄纬度科技有限公司 一种教育玩具套件及利用颜色和轮廓识别编程模块的方法
CN106296710A (zh) * 2016-08-19 2017-01-04 上海葡萄纬度科技有限公司 一种教育玩具套件及其敲击动作检测方法

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496021A (zh) * 2011-11-23 2012-06-13 南开大学 基于小波变换的图像二值化方法
US20140119665A1 (en) * 2012-10-31 2014-05-01 Cognex Corporation System and method for finding saddle point-like structures in an image and determining information from the same
CN105096348A (zh) * 2014-04-30 2015-11-25 富士通株式会社 检测图像中的色彩板的装置和方法
CN105194884A (zh) * 2015-10-27 2015-12-30 上海葡萄纬度科技有限公司 教育玩具套件
CN105513086A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其基于形状匹配的魔方检测定位方法
CN105498253A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其定位孔检测定位方法
CN205164140U (zh) * 2015-10-27 2016-04-20 上海葡萄纬度科技有限公司 教育玩具套件
CN105498200A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其七巧板颜色识别方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060096873A1 (en) * 2004-11-09 2006-05-11 Fromm Wayne G Miniature comic book kit
CN104269079A (zh) * 2014-09-30 2015-01-07 张启熙 基于镜面反射和增强现实技术的移动终端幼教系统及方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496021A (zh) * 2011-11-23 2012-06-13 南开大学 基于小波变换的图像二值化方法
US20140119665A1 (en) * 2012-10-31 2014-05-01 Cognex Corporation System and method for finding saddle point-like structures in an image and determining information from the same
CN105096348A (zh) * 2014-04-30 2015-11-25 富士通株式会社 检测图像中的色彩板的装置和方法
CN105194884A (zh) * 2015-10-27 2015-12-30 上海葡萄纬度科技有限公司 教育玩具套件
CN205164140U (zh) * 2015-10-27 2016-04-20 上海葡萄纬度科技有限公司 教育玩具套件
CN105513086A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其基于形状匹配的魔方检测定位方法
CN105498253A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其定位孔检测定位方法
CN105498200A (zh) * 2016-01-26 2016-04-20 上海葡萄纬度科技有限公司 一种教育玩具套件及其七巧板颜色识别方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111724444A (zh) * 2020-06-16 2020-09-29 中国联合网络通信集团有限公司 目标物的抓取点的确定方法、装置及抓取系统
CN111724444B (zh) * 2020-06-16 2023-08-22 中国联合网络通信集团有限公司 目标物的抓取点的确定方法、装置及抓取系统

Also Published As

Publication number Publication date
CN105709434B (zh) 2017-10-13
CN105709434A (zh) 2016-06-29

Similar Documents

Publication Publication Date Title
WO2017128603A1 (zh) 一种教育玩具套件及其反光镜位置检测方法
WO2017128602A1 (zh) 一种教育玩具套件及其定位孔检测定位方法
CN111243032B (zh) 一种棋盘格角点全自动检测方法
WO2017128606A1 (zh) 一种教育玩具套件及其七巧板颜色识别方法
WO2017128605A1 (zh) 一种教育玩具套件及其基于hsv的魔方颜色识别方法
WO2018032626A1 (zh) 一种教育玩具套件及其数字识别方法
CN107169494B (zh) 基于手持终端的车牌图像分割校正方法
WO2017128604A1 (zh) 一种教育玩具套件及其基于形状匹配的魔方检测定位方法
WO2017181724A1 (zh) 电子元件漏件检测方法和系统
WO2017128607A1 (zh) 一种教育玩具套件及检测七巧板摆放形状、位置的方法
WO2018032630A1 (zh) 一种教育玩具套件及利用颜色和轮廓识别编程模块的方法
TWI549482B (zh) 用於相機之檢測方法
CN102988052B (zh) 足长测量方法及系统
CN110858899A (zh) 一种摄像机机芯光轴中心和视场角的测量方法及系统
CN108965839B (zh) 一种自动调整投影画面的方法及装置
CN108709500B (zh) 一种电路板元件定位匹配方法
WO2018032627A1 (zh) 一种教育玩具套件及其海洋模具识别方法
WO2021195873A1 (zh) 识别sfr测试卡图像中感兴趣区域的方法及装置、介质
CN109829354A (zh) 一种基于深度学习的人脸识别方法
CN108520260A (zh) 瓶装口服液中可见异物的识别方法
KR20040050569A (ko) 피두셜 마크의 중심 위치 측정방법
CN112419225A (zh) 一种基于引脚分割的sop型芯片检测方法及系统
CN112284983A (zh) 通过图像处理测量接触角的方法
CN109839061B (zh) 一种镜头模组检测方法和系统
CN115598136B (zh) 屏幕涂胶质量的检测装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16887485

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16887485

Country of ref document: EP

Kind code of ref document: A1