CN106355592A - Educational toy suite and its circuit elements and electric wires identifying method thereof - Google Patents

Abstract

The invention relates to the field of computer vision detection treatment technology, provides a kind of educational toy suite and its circuit elements and electric wires identifying method thereof. The toy suite comprises a base plate, circuit components and wires, wherein the base plant is placed on the plane, circuit components and wires are placed on the bottom plate. The method is characterized by comprising the steps of placing the circuit components and the electric wire on the game base plate, installing the game program inside the tablet computer, collecting the images of the circuit components and the electric wire placed on the bottom plate through a camera of the tablet computer; further identifying the circuit components and wires based on the predefined color, the outline information and the color coding information. The children connect the circuit components with the wires and determine whether the connection of the circuit is correct, thus enhancing their imagination, increasing the fun of games, letting the children learn the basic circuit knowledge and cultivating their interest.

Description

An educational toy kit and its identification method for circuit components and wires

technical field

The invention relates to the technical field of computer vision detection and processing, in particular to an educational toy kit and a method for identifying circuit components and wires thereof.

Background technique

Now there are many interesting preschool education game applications or children’s games on tablet PCs, but they often just let children finger and draw on the screen, which lacks interactivity. Looking at the screen for a long time is easy to cause eye damage, and there is a lack of physical knowledge education. The cultivation of logical thinking is lacking; and some of the current interactive traditional game toys have been out of the development of the times, and cannot meet the needs of children for learning and playing in form, and it is not convenient for children and parents to interact and communicate.

In order to solve the above problems, a kind of educational toy kit has been successfully developed in the field of computer vision and image processing technology, including: a bracket, a helmet detector and a base plate, and the game program is installed in the tablet computer, which is collected and placed on the plane by the camera of the tablet computer. image of the bottom plate. Although the above-mentioned educational toy kit solves the problem of lack of interactivity in games on the tablet computer, the form is still single, only simple interaction, without the embedding of physical knowledge, and it is impossible to cultivate children's electrical knowledge from an early age, and it is also impossible to cultivate Children's knowledge and interest in electricity.

Therefore, in the field of computer vision detection and processing technology, there is an urgent need for an educational toy kit and an identification method for its circuit components and wires. Collect images of circuit components and wires placed on the bottom plate, and then identify circuit components and wires based on predefined colors, outline information, and color-coded information. Children connect circuit components and wires to determine whether the connected circuit is correct. , enhance children's imagination, increase the fun of the game, so that children can learn basic circuit knowledge and cultivate children's interest.

Contents of the invention

In order to solve the above problems, the present invention provides an educational toy kit and a method for identifying circuit components and electric wires thereof. The technical scheme is as follows:

An educational toy kit includes: a base plate, circuit components and wires are placed on the base plate, and the circuit components and wires are placed on the base plate.

Preferably, in the aforementioned educational toy kit, the bottom plate is a rectangle with rounded corners, and calibration corners are provided on the four corners of the rectangle.

Preferably, in the above-mentioned educational toy kit, the calibration angle is a red arc line.

A method for identifying circuit components and wires in an educational toy kit, comprising the steps of:

Step 1, install the game program on the tablet computer, and then place the bottom board on a flat surface, making sure that the side of the calibration corner is facing up

Step 2, complete the connection of circuit components and wires on the base plate, collect color images in real time through the rear camera of the tablet computer, and move the tablet computer to ensure that the color images collected by the rear camera contain at least 3 calibration angles;

Step 3, extracting an effective recognition area from the color image in step 2;

Step 4, detecting circuit components located in the effective identification area of the color image;

Step 5, detecting electric wires located in the effective identification area of the color image;

Step 6, judging whether the connection between the circuit components and the electric wires is correct.

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the color image collected by the rear camera in step 2 is _Ixy , _Ixy =f(x, y)=( _Rxy , G _xy , B _xy ), where (x, y) represents the position coordinates of the color image pixel, f(x, y) represents the pixel value of the image at the pixel coordinate position, R _xy represents the image pixel in the red channel Color value, G _xy indicates the color value of the image pixel in the green channel, B _xy indicates the color value of the image pixel in the blue channel.

Preferably, in the above-mentioned method for identifying circuit components and electric wires in an educational toy kit, the specific steps for extracting an effective identification area from the color image in step three are:

A) According to prior knowledge, segment 4 calibration corner regions from the color image in step 2, and perform binarization on the 4 calibration corner region images according to the prior threshold in HSV space, and obtain 4 calibration corner regions value map;

B) scanning the 4 blocks of calibration angle binary images obtained in step A) to obtain corresponding edge contour images, and then filtering out unreasonable contours according to the prior knowledge of the eccentricity and size of the edge contours;

C) According to the remaining edge profile obtained in step B), calculate the circumscribed rectangle of 4 calibration corners. During the recognition process, when at least three corner marks have qualified calibration corners, the circumscribed rectangle is calculated. effective identification area.

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the specific steps for detecting circuit components located in the color image recognition area in step 4 are:

1. Since the color of each circuit component shell is different, each circuit component is divided according to the color difference, and the inner contour of each circuit component shell is extracted;

2. Calculate the position and deflection angle of each circuit component according to the inner contour of the circuit component housing extracted in step 1;

3. Rotate the circuit components according to the deflection angle calculated in step 2, then divide the circuit components, and identify the category of the circuit components by color coding.

Preferably, in the above-mentioned method for identifying circuit components and electric wires in an educational toy kit, the specific steps of extracting the inner contour of each circuit component shell in step 1 are:

a) Because the color of circuit components is not conducive to segmentation in the RGB color space, and is also sensitive to illumination changes, the extracted image of the region of interest is converted from the RGB color space to the HSV color space that focuses on color representation , the specific conversion formula is:

V=max{C(R'), C(G'), C(B')};

Among them, H represents the hue value, S represents the saturation value, V represents the brightness value, and max{C(R'), C(G'), C(B')} indicates that a pixel in the original image is in the red, green , the maximum pixel value of the three channels of blue, min{C(R'), C(G'), C(B')} means that in the original image, the pixel of a pixel in the three channels of red, green and blue is the smallest value, and the value range of H is between 0-360;

b) In the HSV color space, according to the prior threshold value of the color involved in the circuit components in the HSV space, the color image is binarized, and the specific formula is as follows:

When B(x, y)=B_H(x, y)&B_S(x, y)&B_V(x, y) in the binary image, it is to generate a binary image;

Among them, B(x, y) represents the binary pixel value of the image pixel point (x, y), and H(x, y), S(x, y), V(x, y) represent the image pixel point (x, y) respectively. y) The hue value, saturation value, and brightness value in the HSV color space; B_H(x, y), B_S(x, y), and B_V(x, y) indicate whether the image pixel points (x, y) are respectively In the specified H, S, V area, if it is, the value is 1, otherwise, the value is 0; H _min and H _max respectively represent the priori of the hue of the color of a certain component shell in the HSV color space The minimum and maximum values; S _min and S _max represent the prior minimum and maximum values of the saturation of the color of a certain component shell in the HSV color space; V _min and V _max respectively represent the color of a certain component shell in HSV A priori minimum and maximum values for luminance within the color space.

c) scan the binarized image to find out all edge contours;

The binarized image can be regarded as a grayscale image with only two values. The edge of the image refers to the part of the grayscale image where the grayscale changes sharply. The degree of change in the grayscale value is quantified by the gradient change between adjacent pixels. Indicates that the gradient is the two-dimensional equivalent of the first-order two-dimensional derivative, and the specific calculation process is:

First, calculate the difference between adjacent pixels, the specific formula is:

G _x =f[i,j+1]-f[i,j]

G _y =f[i,j]-f[i+1,j]

Among them, G _x represents the difference between adjacent pixels in the x direction, G _y represents the difference between adjacent pixels in the y direction, and f[i, j+1] represents the pixel value of the i-th row and j+1 column of the image , f[i, j] represents the pixel value of the image at row i, column j; f[i+1, j] represents the pixel value of the image at row i+1, column j;

Further, calculate the gradient between adjacent pixels, the specific formula is:

Among them, G(x, y) represents the gradient value of the image at (x, y) point, Indicates that the pixel value is derived in the x direction, Indicates that the pixel value is derived in the y direction;

Further, the gradient magnitude of the edge points is calculated, and the gradient magnitude set of all edge points is the extracted edge contour;

Furthermore, the method of calculating the ears of non-stationary electric fans and other circuit components is to filter out unreasonable contours based on the prior knowledge of the contour shape, size and eccentricity of the circuit component ears, so as to obtain the two ears of circuit components s position;

Since the ears of the static fan may be partially or completely covered by the blades, it is necessary to perform color segmentation on step b), and segment the blue binary image and the green binary image;

Further, scan the blue binary image, and determine whether there is a fan blade through the prior knowledge of the contour shape, eccentricity, and size of the fan blade. If so, it is determined that the circuit component is a fan; otherwise, Skip directly to step 2;

Further, after it is determined that the circuit component is a fan, the calculation method for the ears of a stationary fan is as follows: cluster the green binary image in step 1, group the green points with closer distances into one group, and use the same class of The number of point sets, the size of the minimum enclosing rectangle of the point set, the eccentricity, and the prior knowledge of the position of the point set filter the point sets clustered into one class. If only two types of point sets are left after filtering, it is considered that the current fan blade If the position has a high probability of covering the ears of electrical components, the position of the center point of the ear of the circuit component is calculated based on the position of the center point of the two types of point sets and the contour information of the component.

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the specific steps for calculating the position and deflection angle of each circuit component in step 2 are:

According to the calculated ear position and center point position of the circuit component, the rotation angle of the circuit component is calculated to ensure that the ear of the circuit component is in the horizontal direction as a standard.

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the specific steps for identifying the category of circuit components in step 3 are:

First of all, it is necessary to set a coding rule for all circuit components in advance, so that each circuit component has a unique code; because the number of circuit components to be identified is limited, four easy-to-code rules of red, yellow, blue, and green are selected. The distinguished color is used as the coding feature color; the private printing of circuit components is mainly concentrated in the upper middle, middle middle, and lower middle. When a certain color pixel in these three places exceeds the color pixel threshold, the color is considered to be the the color of the area;

According to the color of the circuit component shell, the private printing color of the upper middle, middle middle and lower middle, red is marked as 1, yellow is marked as 2, blue is marked as 3, green is marked as 4, nothing is marked as 0, and the current color is also recorded regardless of the current color. If it is 0, 11 circuit components can be coded, and the type of the current detection circuit component can be uniquely determined according to the circuit component code;

Filter out the circuit components that do not conform to the code, and pass the remaining circuit component types, circuit component center points, and rotation angles to the upper-level software;

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the color pixel threshold is 30% of the area of each grid in the nine grids.

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the specific steps of detecting the wires located in the effective identification area of the color image in step five are:

Step 1), segment wires and extract bones through color differences;

Step 2), through the extracted bones, calculate the endpoints and bifurcation points of the wires.

Preferably, in the above-mentioned method for identifying circuit elements and electric wires in an educational toy kit, the specific steps of segmenting electric wires and extracting bones through color differences in step 1) are:

First, in the HSV space of the effective recognition area in step 3, according to the prior threshold value of the color of the wire in the HSV space, the image is binarized to obtain a binarized image of the wire;

Further, scan the binarized image of the wire, filter out the contours that do not conform to the characteristics of the wire through the prior knowledge of the shape and size of the wire contour, fill the remaining contours, and obtain a new binarized image with only wires ;

Further, bone thinning is carried out on the above-mentioned binary image with only electric wires to obtain the skeleton of electric wires.

Preferably, in the above-mentioned method for identifying circuit elements and electric wires in a kind of educational toy kit, the specific steps for calculating the endpoints and bifurcation points of the electric wires through the extracted bones in step 2) are: through step 1) to obtain The wire skeleton, as well as the prior knowledge of the endpoints and bifurcation point features of the wire, find the endpoints and bifurcation points in the wire skeleton, if there is a bifurcation point, separate the wire skeleton from the bifurcation point, and divide it into multiple line segments, if Without bifurcation points, the original wire skeleton is a line segment, and all the line segments and the types of line segment endpoints in the bone are provided to the upper software.

Preferably, in the above-mentioned method for identifying circuit components and wires in an educational toy kit, the specific steps for judging whether the connection between the circuit components and the wires in step 6 are accurate are as follows: the upper layer software recognizes the circuit components identified in step 4 The device is connected with the wires identified in step five, and then compared with the circuit diagram stored by the upper layer software. If it is consistent with the circuit diagram, the circuit connection is considered accurate.

Beneficial effects of the present invention:

1. The present invention cleverly uses computer vision graphic recognition technology combined with HSV color space, binarization processing, and image cutting technology to judge the type of circuit components and wires, and to judge whether the circuit connection is accurate. It has fast calculation speed, accurate positioning, well unifies hardware and software technology, and ingenious game interaction design; beautiful and simple, faster judgment, enhances children's imagination, increases game fun, and enables children to learn basic circuit knowledge , Cultivate children's interest.

2. The detection algorithm of the present invention is more scientific and mature. The combination of image color conversion, image convolution, image cutting, bone thinning and other algorithms can quickly determine the type of circuit components and wires.

3. The calculation speed of the present invention is fast; each positioning detection takes about 200ms, providing players with a smooth use experience.

4. The performance of the present invention is stable. Under different lighting conditions and different tablet computers installed in the educational toy kit, a collection test was carried out for 3,000 pictures, and the false recognition rate and missed detection rate were below 0.2%.

Description of drawings

Describe the present invention in detail below in conjunction with accompanying drawing and specific embodiment:

Fig. 1 is a schematic structural view of an educational toy kit according to the present invention.

Fig. 2 is a flowchart of a method for identifying circuit elements and wires in an educational toy kit according to the present invention.

Fig. 3 is a tabular diagram of specific circuit component codes in step 3 of step 4 in an educational toy kit of the present invention.

Wherein, the corresponding relationship between the reference numerals and the part names in Fig. 1-3 is:

Base plate 1, circuit components 2, wires 3.

detailed description

In order to make the measures, creative features, goals and effects achieved by the technology of the present invention easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the The described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Fig. 1 is a schematic structural view of an educational toy kit according to the present invention.

As shown in Figure 1, a toy kit and its identification method for circuit components and wires, base plate 1, circuit components 2 and wires 3, base plate 1 is placed on a plane, circuit components 2 and wires 3 are placed on base plate 3 .

In this embodiment, the bottom plate is a rectangle with rounded corners, and calibration corners are provided on the four corners of the rectangle; preferably, the calibration corners are red circular arc lines.

Fig. 2 is a flowchart of a method for identifying circuit elements and wires in an educational toy kit according to the present invention.

As shown in Figure 2, a method for identifying circuit elements and electric wires in an educational toy kit includes the following steps:

Step 1, install the game program on the tablet computer, and then place the base plate on a flat surface, making sure that the calibration corner is facing up;

Step 2, complete the connection of circuit components and wires on the base plate, collect color images in real time through the rear camera of the tablet computer, and move the tablet computer to ensure that the color images collected by the rear camera contain at least 3 calibration angles. The specific steps are as follows: :

The color image collected by the rear camera is I _xy , I _xy = f(x, y) = (R _xy , G _xy , B _xy ), where (x, y) represents the position coordinates of the color image pixel, f( x, y) represents the pixel value of the image at the pixel coordinate position, 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 image pixel in the blue channel The color value of the color channel;

Step 3, extracting an effective recognition area from the color image in step 2, the specific steps are:

A) According to prior knowledge, segment 4 calibration corner regions from the color image in step 2, and perform binarization on the 4 calibration corner region images according to the prior threshold in HSV space, and obtain 4 calibration corner regions value map;

B) scanning the 4 blocks of calibration angle binary images obtained in step A) to obtain corresponding edge contour images, and then filtering out unreasonable contours according to the prior knowledge of the eccentricity and size of the edge contours;

C) According to the remaining edge profile obtained in step B), calculate the circumscribed rectangle of 4 calibration corners. During the recognition process, when at least three corner marks have qualified calibration corners, the circumscribed rectangle is calculated. effective identification area;

Step 4, detecting the circuit components located in the effective recognition area of the color image, the specific steps are:

1. Since the color of each circuit component shell is different, each circuit component is divided according to the color difference, and the inner contour of each circuit component shell is extracted. The specific steps are:

a) Because the color of circuit components is not conducive to segmentation in the RGB color space, and is also sensitive to illumination changes, the extracted image of the region of interest is converted from the RGB color space to the HSV color space that focuses on color representation , the specific conversion formula is:

V=max{C(R'), C(G'), C(B')};

Among them, H represents the hue value, S represents the saturation value, V represents the brightness value, and max{C(R'), C(G'), C(B')} indicates that a pixel in the original image is in the red, green , the maximum pixel value of the three channels of blue, min{C(R'), C(G'), C(B')} means that in the original image, the pixel of a pixel in the three channels of red, green and blue is the smallest value, and the value range of H is between 0-360;

b) In the HSV color space, the color image is binarized according to the prior threshold value of the color involved in the outer shell of the circuit component in the HSV space, and the specific formula is as follows:

When B(x, y)=B_H(x, y)&B_S(x, y)&B_V(x, y) in the binary image, it is to generate a binary image;

Among them, B(x, y) represents the binary pixel value of the image pixel point (x, y), and H(x, y), S(x, y), V(x, y) represent the image pixel point (x, y) respectively. y) The hue value, saturation value, and brightness value in the HSV color space; B_H(x, y), B_S(x, y), and B_V(x, y) indicate whether the image pixel points (x, y) are respectively In the specified H, S, V area, if it is, the value is 1, otherwise, the value is 0; H _min and H _max respectively represent the priori of the hue of the color of a certain component shell in the HSV color space The minimum and maximum values; S _min and S _max represent the prior minimum and maximum values of the saturation of the color of a certain component shell in the HSV color space; V _min and V _max respectively represent the color of a certain component shell in HSV a priori minimum and maximum values of brightness in the color space;

c) scan the binarized image to find out all edge contours;

The binarized image can be regarded as only two worth grayscale images. The edge of the image refers to the part of the grayscale image where the grayscale changes sharply. The change degree of the grayscale value is quantitatively expressed by the gradient change between adjacent pixels. , the gradient is the two-dimensional equivalent of the first-order two-dimensional derivative, and the specific calculation process is:

First, calculate the difference between adjacent pixels, the specific formula is:

G _x =f[i,j+1]-f[i,j]

G _y =f[i,j]-f[i+1,j]

Among them, G _x represents the difference between adjacent pixels in the x direction, G _y represents the difference between adjacent pixels in the y direction, and f[i, j+1] represents the pixel value of the i-th row and j+1 column of the image , f[i, j] represents the pixel value of the image at row i, column j; f[i+1, j] represents the pixel value of the image at row i+1, column j,

Further, calculate the gradient between adjacent pixels, the specific formula is:

Among them, G(x, y) represents the gradient value of the image at (x, y) point, Indicates that the pixel value is derived in the x direction, Indicates that the pixel value is derived in the y direction;

Further, the gradient magnitude of the edge points is calculated, and the gradient magnitude set of all edge points is the extracted edge contour;

Furthermore, the method of calculating the ears of non-stationary electric fans and other circuit components is to filter out unreasonable contours based on the prior knowledge of the contour shape, size and eccentricity of the circuit component ears, so as to obtain the two ears of circuit components s position;

Since the ears of the static fan may be partially or completely covered by the blades, it is necessary to perform color segmentation on step b), and segment the blue binary image and the green binary image;

Further, scan the blue binary image, and determine whether there is a fan blade through the prior knowledge of the contour shape, eccentricity, and size of the fan blade. If so, it is determined that the circuit component is a fan; otherwise, Skip directly to step 2;

Further, after it is determined that the circuit component is a fan, the calculation method for the ears of a stationary fan is as follows: cluster the green binary image in step 1, group the green points with closer distances into one group, and use the same class of The number of point sets, the size of the minimum enclosing rectangle of the point set, the eccentricity, and the prior knowledge of the position of the point set filter the point sets clustered into one class. If only two types of point sets are left after filtering, it is considered that the current fan blade If the position has a high probability of covering the ear of the electrical component, the position of the center point of the ear of the circuit component is calculated based on the position of the center point of the two types of point sets and the contour information of the component;

2. Calculate the position and deflection angle of each circuit component according to the outline of the circuit components extracted in step 1. The specific steps are:

According to the calculated ear position and center point position of the circuit component, the rotation angle of the circuit component is calculated to ensure that the ear of the circuit component is in the horizontal direction as a standard. According to the calculated ear position and center point position of the circuit component, the rotation angle of the circuit component is calculated to ensure that the ear of the circuit component is in the horizontal direction as a standard;

3. Rotate the circuit components according to the deflection angle calculated in step 2, then divide the circuit components, and identify the category of the circuit components through color coding. The specific steps are:

First of all, it is necessary to set a coding rule for all circuit components in advance, so that each circuit component has a unique code; because the number of circuit components to be identified is limited, four easy-to-code rules of red, yellow, blue, and green are selected. The distinguished color is used as the coding feature color; the private printing of circuit components is mainly concentrated in the upper middle, middle middle, and lower middle places. When the pixel value of a certain color in these three places exceeds the prior threshold, the color is considered to be the color of the area;

According to the color of the circuit component shell, the private printing color of the upper middle, middle middle and lower middle, red is marked as 1, yellow is marked as 2, blue is marked as 3, green is marked as 4, nothing is marked as 0, and the current color is also recorded regardless of the current color. If it is 0, 11 circuit components can be coded, and the type of the current detection circuit component can be uniquely determined according to the circuit component code;

Filter out the circuit components that do not conform to the coding, and pass the remaining circuit component types, circuit component center points, and rotation angles to the upper-level software. The specific circuit component coding is shown in Figure 3;

Step five, detect the electric wires located in the effective recognition area of the color image, the specific steps are:

Step 1), segment wires and extract bones through color differences, the specific steps are:

First, in the HSV space of the effective recognition area in step 3, according to the prior threshold value of the color of the wire in the HSV space, the image is binarized to obtain a binarized image of the wire;

Further, scan the binarized image of the wire, filter out the contours that do not conform to the characteristics of the wire through the prior knowledge of the shape and size of the wire contour, fill the remaining contours, and obtain a new binarized image with only wires ;

Further, perform bone refinement on the above-mentioned binary image with only wires to obtain the skeleton of wires;

Step 2), through the extracted bones, calculate the endpoints and bifurcation points of the wires, the specific steps are: through the wire skeletons obtained in step 1), and the prior knowledge of the characteristics of the endpoints and bifurcation points of the wires, find the wire skeleton If there is a bifurcation point, separate the wire bone from the bifurcation point and divide it into multiple line segments. If there is no bifurcation point, the original wire bone is a line segment. Put all the line segments and line segment endpoints in the bone The type in is provided to the upper layer software;

Step 6, determine whether the connection between circuit components and wires is accurate, the specific steps are:

The upper-layer software connects the circuit components identified in step 4 with the wires identified in step 5, and then compares it with the circuit diagram stored by the upper-layer software. If it is consistent with the circuit diagram, the circuit connection is considered accurate.

In this embodiment, the color pixel threshold is 30% of the area of each grid in the nine grids.

The present invention cleverly combines computer vision graphic recognition technology with HSV color space, binarization processing, and image cutting technology to determine the type of circuit components and wires, and to determine whether the circuit connection is accurate. Fast speed, accurate positioning, good integration of hardware and software technology, ingenious game interaction design; beautiful and simple, faster judgment, enhance children's imagination, increase game fun, so that children can learn basic circuit knowledge, cultivate child's interest.

The detection algorithm of the invention is more scientific and mature, and the image color conversion, image convolution, image cutting, bone thinning and other algorithms are used in combination, and the type of circuit components and wires can be quickly judged.

The calculation speed of the present invention is fast; each positioning detection takes about 200 ms, providing players with a smooth use experience.

The performance of the present invention is stable, and under the condition of different lighting and different tablet computers installed in the educational toy kit, a collection test is carried out for 3,000 pictures, and the misrecognition rate and missed detection rate are below 0.2%.

The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the industry should understand that the present invention is not limited by the above-mentioned embodiments, and that described in the above-mentioned embodiments and the description only illustrates the principles of the present invention, and the present invention also has various aspects without departing from the spirit and scope of the present invention. Variations and improvements all fall within the scope of the claimed invention. The protection scope of the present invention is defined by the appended claims and their equivalents.

Claims (10)

1. An educational toy kit, characterized in that it comprises: a base plate, circuit components and electric wires, the base plate is placed on a plane, and the circuit components and electric wires are placed on the base plate. 2. A kind of educational toy kit according to claim 1, characterized in that, the base plate is a rectangle with rounded corners, and calibration corners are arranged on the four corners of the rectangle; the calibration corners are red circles arc. 3. A method for identifying circuit elements and electric wires in an educational toy kit, comprising the steps of: Step 1, install the game program on the tablet computer, and then place the base plate on a flat surface, making sure that the calibration corner is facing up; Step 2, complete the connection of circuit components and wires on the base plate, collect color images in real time through the rear camera of the tablet computer, and move the tablet computer to ensure that the color images collected by the rear camera contain at least 3 calibration angles. The specific steps are as follows: : The color image collected by the rear camera is I _xy , I _xy = f(x, y) = (R _xy , G _xy , B _xy ), where (x, y) represents the position coordinates of the color image pixel, f( x, y) represents the pixel value of the image at the pixel coordinate position, 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 The color value of the color channel. Step 3, extracting an effective recognition area from the color image in step 2; Step 4, detecting circuit components located in the effective identification area of the color image; Step 5, detecting electric wires located in the effective identification area of the color image; Step 6, judging whether the connection between the circuit components and the electric wires is correct. 4. the identification method of circuit element and electric wire in a kind of educational toy kit according to claim 3, it is characterized in that, the specific step of extracting effective identification area from color image in described step 3 is: A) According to prior knowledge, segment 4 calibration corner regions from the color image in step 2, and perform binarization on the 4 calibration corner region images according to the prior threshold in HSV space, and obtain 4 calibration corner regions value map; B) scanning the 4 blocks of calibration angle binary images obtained in step A) to obtain corresponding edge contour images, and then filtering out unreasonable contours according to the prior knowledge of the eccentricity and size of the edge contours; C) According to the remaining edge profile obtained in step B), calculate the circumscribed rectangle of 4 calibration corners. During the recognition process, when at least three corner marks have qualified calibration corners, the circumscribed rectangle is calculated. effective identification area. 5. the identification method of circuit element and electric wire in a kind of educational toy kit according to claim 3, it is characterized in that, in the described step 4, the step of detecting the circuit element located in the color image recognition area is: 1. Since the color of each component shell is different, each circuit component is segmented through the color difference, and the inner contour of each circuit component shell is extracted; 2. Calculate the position and deflection angle of each circuit component according to the inner contour of the circuit component housing extracted in step 1; 3. Rotate the circuit components according to the deflection angle calculated in step 2, then divide the circuit components, and identify the category of the circuit components by color coding. 6. the identification method of circuit element and electric wire in a kind of educational toy kit according to claim 5, it is characterized in that, the concrete step of extracting the outline of each circuit element in the described step 1 is: a) Because the color of circuit components is not conducive to segmentation in the RGB color space, and is also sensitive to illumination changes, the extracted image of the region of interest is converted from the RGB color space to the HSV color space that focuses on color representation , the specific conversion formula is: V=max{C(R'), C(G'), C(B')}; Among them, H represents the hue value, S represents the saturation value, V represents the brightness value, and max{C(R'), C(G'), C(B')} indicates that a pixel in the original image is in the red, green , the maximum pixel value of the three channels of blue, min{C(R'), C(G'), C(B')} means that in the original image, the pixel of a pixel in the three channels of red, green and blue is the smallest value, and the value range of H is between 0-360; b) In the HSV color space, the color image is binarized according to the prior threshold value of the color involved in the outer shell of the circuit component in the HSV space, and the specific formula is as follows: When B(x, y)=B_H(x, y)&B_S(x, y)&B_V(x, y) in the binary image, it is to generate a binary image; Among them, B(x, y) represents the binary pixel value of the image pixel point (x, y), and H(x, y), S(x, y), V(x, y) represent the image pixel point (x, y) respectively. y) The hue value, saturation value, and brightness value in the HSV color space; B_H(x, y), B_S(x, y), and B_V(x, y) indicate whether the image pixel points (x, y) are respectively In the specified H, S, V area, if it is, the value is 1, otherwise, the value is 0; H _min and H _max respectively represent the priori of the hue of the color of a certain component shell in the HSV color space The minimum and maximum values; S _min and S _max represent the prior minimum and maximum values of the saturation of the color of a certain component shell in the HSV color space; V _min and V _max respectively represent the color of a certain component shell in HSV a priori minimum and maximum values of brightness in the color space; c) scan the binarized image to find out all edge contours; The binarized image can be regarded as a grayscale image with only two values. The edge of the image refers to the part of the grayscale image where the grayscale changes sharply. The degree of change in the grayscale value is quantified by the gradient change between adjacent pixels. Indicates that the gradient is the two-dimensional equivalent of the first-order two-dimensional derivative, and the specific calculation process is: First, calculate the difference between adjacent pixels, the specific formula is: G _x =f[i,j+1]-f[i,j] G _y =f[i,j]-f[i+1,j] Among them, G _x represents the difference between adjacent pixels in the x direction, G _y represents the difference between adjacent pixels in the y direction, and f[i, j+1] represents the pixel value of the i-th row and j+1 column of the image , f[i, j] represents the pixel value of the image at row i, column j; f[i+1, j] represents the pixel value of the image at row i+1, column j, Further, calculate the gradient between adjacent pixels, the specific formula is: Among them, G(x, y) represents the gradient value of the image at (x, y) point, Indicates that the pixel value is derived in the x direction, Indicates that the pixel value is derived in the y direction; Further, the gradient magnitude of the edge points is calculated, and the gradient magnitude set of all edge points is the extracted edge contour; Furthermore, the method of calculating the ears of non-stationary electric fans and other circuit components is to filter out unreasonable contours based on the prior knowledge of the contour shape, size and eccentricity of the circuit component ears, so as to obtain the two ears of circuit components s position; Since the ears of the static fan may be partially or completely covered by the blades, it is necessary to perform color segmentation on step b), and segment the blue binary image and the green binary image; Further, scan the blue binary image, and determine whether there is a fan blade through the prior knowledge of the contour shape, eccentricity, and size of the fan blade. If so, it is determined that the circuit component is a fan; otherwise, Skip directly to step 2; Further, after it is determined that the circuit component is a fan, the calculation method for the ears of a stationary fan is as follows: cluster the green binary image in step 1, group the green points with closer distances into one group, and use the same class of The number of point sets, the size of the minimum enclosing rectangle of the point set, the eccentricity, and the prior knowledge of the position of the point set filter the point sets clustered into one class. If only two types of point sets are left after filtering, it is considered that the current fan blade If the position has a high probability of covering the ears of electrical components, the position of the center point of the ear of the circuit component is calculated based on the position of the center point of the two types of point sets and the contour information of the component. 7. The identification method of circuit elements and electric wires in a kind of educational toy kit according to claim 6, characterized in that, the specific steps of calculating the position and deflection angle of each circuit element in said step 2 are: According to the calculated ear position and center point position of the circuit component, the rotation angle of the circuit component is calculated to ensure that the ear of the circuit component is in the horizontal direction as a standard. 8. The method for identifying circuit elements and electric wires in a kind of educational toy kit according to claim 5, characterized in that, the specific steps of identifying the category of circuit elements in the step 3 are: First of all, it is necessary to set a coding rule for all circuit components in advance, so that each circuit component has a unique code; because the number of circuit components to be identified is limited, four easy-to-code rules of red, yellow, blue, and green are selected. The distinguished color is used as the coding feature color; the private printing of circuit components is mainly concentrated in the upper middle, middle middle, and lower middle places. When the pixel value of a certain color in these three places exceeds the prior threshold, the color is considered is the color of the region. According to the color of the circuit component shell, the private printing color of the upper middle, middle middle and lower middle, red is marked as 1, yellow is marked as 2, blue is marked as 3, green is marked as 4, nothing is marked as 0, and the current color is also recorded regardless of the current color. If it is 0, 11 circuit components can be coded, and the type of the current detection circuit component can be uniquely determined according to the circuit component code; Filter out the circuit components that do not conform to the code, and pass the remaining circuit component types, circuit component center points, and rotation angles to the upper-layer software. 9. the identification method of circuit element and electric wire in a kind of educational toy kit according to claim 4, it is characterized in that, in the described step 5, the specific steps of detecting electric wires located in the effective identification area of color image are: Step 1), segment wires and extract bones through color differences, the specific steps are: First, in the HSV space of the effective recognition area in the step 3, according to the prior threshold value of the color of the wire in the HSV space, the image is binarized to obtain a binarized image of the wire; Further, scan the binarized image of the wire, filter out the contours that do not conform to the characteristics of the wire through the prior knowledge of the shape and size of the wire contour, fill the remaining contours, and obtain a new binarized image with only wires ; Further, bone thinning is carried out on the above-mentioned binary image with only electric wires to obtain the skeleton of electric wires. Step 2), through the extracted bones, calculate the endpoints and bifurcation points of the wires, the specific steps are: Through the wire skeleton obtained in step 1), as well as the prior knowledge of the endpoints and bifurcation point features of the wire, find the endpoint and bifurcation point in the wire skeleton. If there is a bifurcation point, separate the wire skeleton from the bifurcation point, Divided into multiple line segments, if there is no bifurcation point, the original wire skeleton is a line segment, and all the line segments and the type of the end points of the line segment in the bone are provided to the upper software. 10. The method for identifying circuit components and electric wires in an educational toy kit according to claims 8 and 9, wherein the specific steps for determining whether the connection between the circuit components and the electric wires are accurate in the step 6 are as follows: The upper-layer software connects the circuit components identified in step 4 with the wires identified in step 5, and then compares it with the circuit diagram stored by the upper-layer software. If it is consistent with the circuit diagram, the circuit connection is considered accurate.