1. A template information acquisition method is characterized by comprising the following steps:

creating a plurality of layers of pyramid images according to the template image, and extracting gradient information of each layer of pyramid image to form template information for image identification, wherein the extracting of the gradient information of each layer of pyramid image to form the template information for image identification comprises the following steps:

generating a current-layer gradient amplitude median value according to the gradient amplitude of each pixel point in the current-layer pyramid image, and generating a high threshold value and a low threshold value according to the current-layer gradient amplitude median value;

obtaining edge position points according to the high threshold and the low threshold, and generating gradient information of a current layer pyramid image according to the edge position points, wherein the gradient information of the current layer pyramid image comprises a gradient position list, a gradient direction list and a gradient amplitude list, the gradient position list comprises coordinates of each edge position point, the gradient direction list comprises a gradient direction of each edge position point, and the gradient amplitude list comprises a gradient amplitude of each edge position point.

2. The template information acquisition method according to claim 1, characterized in that the method further comprises:

generating a first mask image according to gradient information of a bottom pyramid image, wherein the first mask image is formed by performing expansion processing on edge position points in the bottom pyramid image;

and for each layer of pyramid image, eliminating interference edge position points in each layer of pyramid image by using the first mask image.

3. The template information acquisition method according to claim 1 or 2, wherein the acquiring edge position points according to the high threshold and the low threshold includes:

for the current pyramid image, extracting and calculating the edge by using a Canny operator to obtain all edge pixel points meeting the requirements of a high threshold and a low threshold;

and performing connected domain operation on the edge pixel points to obtain a plurality of independent edge curve segments, and taking the edge pixel points on the edge curve segments meeting preset conditions as edge position points.

4. The template information obtaining method according to claim 3, wherein the taking edge pixel points on the edge curve segment that meet the preset condition as edge position points includes:

taking an edge curve segment with the length not less than a first preset length as an alternative edge curve segment;

and when the sum of the lengths of all the alternative edge curve segments is greater than a second preset length, deleting redundant edge pixel points in the alternative edge curve segments, and taking all the edge pixel points on the alternative edge curve segments after the redundant edge pixel points are deleted as edge position points.

5. The template information obtaining method according to claim 4, wherein the deleting redundant edge pixel points in the candidate edge curve segment includes:

taking adjacent edge pixel points with preset number on the alternative edge curve segment as pixel points to be processed, and acquiring the curvature of each pixel point to be processed and the average curvature of all the pixel points to be processed;

and deleting all the pixels to be processed with the curvatures not closest to the average curvature as redundant edge pixels.

6. The template information obtaining method according to claim 4, wherein the deleting redundant edge pixel points in the candidate edge curve segment includes:

taking adjacent preset number of edge pixel points on the alternative edge curve segment as pixels to be processed, and comparing gradient amplitudes of all the pixels to be processed;

and deleting all the pixels to be processed with the non-maximum gradient amplitude as redundant edge pixels.

7. The template information obtaining method of claim 1 or 2, wherein generating a current-layer median gradient amplitude value according to the gradient amplitude value of each pixel point in the current-layer pyramid image comprises:

acquiring the gradient amplitude of each pixel point in the pyramid image of the current layer;

creating an amplitude histogram according to the gradient amplitudes of all pixel points in the pyramid image of the current layer;

and generating a gradient amplitude median value of the current layer according to the amplitude histogram.

8. The template information acquisition method according to claim 1, characterized in that the method further comprises:

generating a second mask image according to external input information including a designated image area on the template image;

and for each layer of pyramid image, eliminating interference edge position points in each layer of pyramid image by using the second mask image.

9. A template information acquisition apparatus comprising a memory and a processor, characterized in that the memory has stored therein a computer program executable in the processor, and the processor implements the steps of the template information acquisition method according to any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform the steps of the template information acquisition method according to any one of claims 1 to 8.

Background

In various automation devices, a high-precision positioning mode is directly provided by a mechanical structure, so that the requirements on machining, installation and debugging and the like are very high, and the cost is high. The vision system is installed in the automation equipment, and the machine vision system is used for providing positioning, so that the method has the advantages of low cost, simplicity in application, high flexibility, strong self-adaption and the like.

In machine vision systems, common matching and positioning methods are grayscale-based, feature point-based, and contour-based matching methods. The matching method based on the gray scale directly uses the gray scale information, and has large calculated amount, low speed and higher requirement on the consistency of the image; the matching method based on the feature points needs the feature points with specific structures, is complex in calculation and low in universality; the contour-based matching technology uses contour edge information, and has the advantages of small calculated amount, stable matching effect and higher precision.

Contour-based matching techniques are the most common positioning methods. The contour edge of the image contains the most important information in the image, so that the image is not easily interfered by various factors inside and outside, the stability and the consistency are high, the edge gradient of the image is very convenient when the conditions of translation, scaling, rotation and the like are processed, and the image can be finished only by simple geometric transformation operation without complex image operation. The method is the most common and effective technology in various current matching and positioning methods, and has become the most general standard method in the field of machine vision due to the advantages of simple calculation, strong anti-interference capability, stable and reliable matching result, easy parallel acceleration, simple processing rotation and scaling and the like.

As shown in fig. 1, the existing scheme for performing matching and positioning by using edge gradients of image contours includes an offline training process and an online matching process, wherein in the offline training process, a template image containing specific image features is trained to obtain template information; and in the online matching process, the template information and the target image are utilized, and the matching position of the template characteristic in the target image is finally obtained through the matching process.

According to the contour-based matching positioning scheme, in the off-line training process, the comparison values of the pixel points need to be manually specified to obtain the edge position points, and the positioning precision is easily influenced due to the fact that the comparison values are not properly set due to the fact that the colors, the contrast ratios and the like of the template images are different.

Disclosure of Invention

The embodiment of the invention provides a template information acquisition method, a device and a computer readable storage medium, aiming at the problem that the positioning accuracy is influenced by manually specifying a comparison value of a pixel point in the offline training process of the contour-based matching positioning scheme.

The technical solution for solving the above technical problem according to the embodiments of the present invention is to provide a template information obtaining method, including:

creating a plurality of layers of pyramid images according to the template image, and extracting gradient information of each layer of pyramid image to form template information for image identification, wherein the template gradient information of each layer of pyramid image is extracted to form the template information for image identification, and the method comprises the following steps:

generating a current-layer gradient amplitude median value according to the gradient amplitude of each pixel point in the current-layer pyramid image, and generating a high threshold value and a low threshold value according to the current-layer gradient amplitude median value;

obtaining edge position points according to the high threshold and the low threshold, and generating gradient information of a current layer pyramid image according to the edge position points, wherein the gradient information of the current layer pyramid image comprises a gradient position list, a gradient direction list and a gradient amplitude list, the gradient position list comprises coordinates of each edge position point, the gradient direction list comprises a gradient direction of each edge position point, and the gradient amplitude list comprises a gradient amplitude of each edge position point.

Preferably, the method further comprises:

generating a first mask image according to gradient information of a bottom pyramid image, wherein the first mask image is formed by performing expansion processing on edge position points in the bottom pyramid image;

and for each layer of pyramid image, eliminating interference edge position points in each layer of pyramid image by using the first mask image.

Preferably, the obtaining the edge location point according to the high threshold and the low threshold includes:

for the current pyramid image, extracting and calculating the edge by using a Canny operator to obtain all edge pixel points meeting the requirements of a high threshold and a low threshold;

and performing connected domain operation on the edge pixel points to obtain a plurality of independent edge curve segments, and taking the edge pixel points on the edge curve segments meeting preset conditions as edge position points.

Preferably, the taking an edge pixel point on an edge curve segment meeting a preset condition as an edge position point includes:

taking an edge curve segment with the length not less than a first preset length as an alternative edge curve segment;

and when the sum of the lengths of all the alternative edge curve segments is greater than a second preset length, deleting redundant edge pixel points in the alternative edge curve segments, and taking all the edge pixel points on the alternative edge curve segments after the redundant edge pixel points are deleted as edge position points.

Preferably, the deleting redundant edge pixel points in the candidate edge curve segment includes:

taking adjacent edge pixel points with preset number on the alternative edge curve segment as pixel points to be processed, and acquiring the curvature of each pixel point to be processed and the average curvature of all the pixel points to be processed;

and deleting all the pixels to be processed with the curvatures not closest to the average curvature as redundant edge pixels.

Preferably, the deleting redundant edge pixel points in the candidate edge curve segment includes:

taking adjacent preset number of edge pixel points on the alternative edge curve segment as pixels to be processed, and comparing gradient amplitudes of all the pixels to be processed;

and deleting all the pixels to be processed with the non-maximum gradient amplitude as redundant edge pixels.

Preferably, generating a median gradient amplitude value of the current layer according to the gradient amplitude value of each pixel point in the pyramid image of the current layer includes:

acquiring the gradient amplitude of each pixel point in the pyramid image of the current layer;

creating an amplitude histogram according to the gradient amplitudes of all pixel points in the pyramid image of the current layer;

and generating a gradient amplitude median value of the current layer according to the amplitude histogram.

Preferably, the method further comprises:

generating a second mask image according to external input information including a designated image area on the template image;

and for each layer of pyramid image, eliminating interference edge position points in each layer of pyramid image by using the second mask image.

The embodiment of the present invention further provides a template information acquiring apparatus, including a memory and a processor, where the memory stores a computer program executable in the processor, and the processor implements the steps of the template information acquiring method according to any one of the above items when executing the computer program.

An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are configured to enable a computer to execute the steps of the template information obtaining method according to any one of the above descriptions.

According to the template information acquisition method, the template information acquisition equipment and the computer-readable storage medium, the list for determining the edge position points is automatically generated through each layer of pyramid images, so that the precision of the template information can be greatly improved, and the progress of matching positioning points is further improved. The invention also eliminates the interference edge position points in each pyramid image through the first mask image formed by expanding the edge position points of the bottom pyramid image, thereby further improving the precision of the template information.

Drawings

FIG. 1 is a schematic diagram of a matching localization scheme using edge gradients of an image contour;

fig. 2 is a schematic flowchart of a template information obtaining method according to an embodiment of the present invention;

fig. 3 is a schematic flow chart illustrating a process of obtaining a median gradient amplitude of a current layer in the template information obtaining method according to the embodiment of the present invention;

fig. 4 is a schematic flowchart of acquiring edge position points according to an edge curve segment in the template information acquisition method according to the embodiment of the present invention;

fig. 5 is a schematic flow chart illustrating a process of generating gradient information of a pyramid image of a current layer in the template information obtaining method according to the embodiment of the present invention;

fig. 6 is a schematic diagram of eliminating an interference point in the template information obtaining method according to the embodiment of the present invention;

fig. 7 is a schematic diagram of a template information acquiring apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The template information acquisition method can be applied to a machine vision system based on edge gradient matching, and edge position point extraction is carried out by using a method for automatically calculating the Canny edge high-low threshold value when extracting edge information from a template image on the basis of the traditional pyramid strategy matching, so that the precision of the template information is greatly improved.

Fig. 2 is a schematic flow chart of a template information obtaining method according to an embodiment of the present invention, where the method generates template information corresponding to a template image in a visual system through template training. The method of the present embodiment obtains template information for image recognition by creating several layers of pyramid images and extracting gradient information of each layer of pyramid image. Specifically, the method of the present embodiment includes the following steps:

step S21: and acquiring the template image as a pyramid image of the current layer, namely, taking the template image as the bottom layer of the pyramid image, and setting the number of pyramid layers as one. The template image can be generated by shooting through a camera and contains specific image characteristics. Of course, in practical applications, the template image may be generated by other means, such as being directly drawn by graphics software.

Step S22: and judging whether the size of the current-layer pyramid image is smaller than a first preset size Smin or not, and executing the step S27 when the size of the current-layer pyramid image is smaller than the first preset size Smin, otherwise executing the step S23.

In this step, the determination may be made using the image length and width as the size of the pyramid image of the current layer. In practical applications, the maximum minimum position distance of the edge points in the current-layer pyramid image can also be used as the size of the current-layer pyramid image.

The first preset size Smin can be set as a fixed value, and can also be automatically or manually adjusted according to practical application, for example, the first preset size Smin can be set according to the size of the template image, the position matching precision requirement of a machine vision system and the like, and the number of edge position points in the pyramid image of the current layer is ensured not to be too small, so that matching cannot be completed due to too little template information during online matching.

Step S23: and generating a current layer gradient amplitude median value according to the gradient amplitude of each pixel point in the current layer pyramid image, and generating a high threshold value and a low threshold value according to the current layer gradient amplitude median value.

In the step, firstly, the gray gradients in the x direction and the y direction (namely, two directions perpendicular to each other in the pyramid image of the current layer) of each pixel point in the pyramid image of the current layer are calculated through a Sobel operator, and then the gradients in the x direction and the y direction obtained through calculation of the Sobel operator are subjected to polar coordinate transformation to obtain the gradient direction and the gradient amplitude of each pixel point. The Sobel operator is a relatively general method for calculating the image gradient, and is not described herein again. In practical application, other general methods for calculating image gradient can be used to obtain the gradient amplitude of each pixel point in the pyramid image of the current layer.

After the gradient amplitude of each pixel point in the current layer pyramid image is obtained, the gradient amplitude median of the current layer pyramid image is obtained according to the gradient amplitude of each pixel point, and a high threshold and a low threshold used for a Canny edge detection algorithm are generated. Specifically, the high threshold may be a product of a median gradient magnitude and a first coefficient, and the low threshold may be a product of a median gradient magnitude and a second coefficient, where the first coefficient and the second coefficient are numbers greater than zero and less than 1, respectively, and the first coefficient is greater than a value of the second coefficient. The first coefficient and the second coefficient may be set empirically in advance, for example, in one embodiment of the present invention, the first coefficient may be set to 0.9 and the second coefficient to 0.7.

By the method, the high threshold and the low threshold of the Canny edge detection algorithm are automatically generated according to the characteristics of each pixel point in the current layer pyramid image without manually setting the high threshold and the low threshold of the Canny edge detection algorithm, so that the high threshold and the low threshold are matched with the characteristics (including shape, color and the like) of the current layer pyramid image.

Step S24: acquiring edge position points of the current-layer pyramid image according to the high threshold and the low threshold acquired in step S23, and generating gradient information of the current-layer pyramid image according to the acquired edge position points, where the gradient information of the current-layer pyramid image includes a gradient position list, a gradient direction list, and a gradient amplitude list, the gradient position list includes coordinates of each edge position point, the gradient direction list includes a gradient direction of each edge position point, and the gradient amplitude list includes a gradient amplitude of each edge position point.

In this embodiment, the number of edge position points in the gradient position list, the number of elements in the gradient direction list, and the number of elements in the gradient magnitude list are the same, and the number of any one is the gradient information length of the pyramid image of the current layer.

Step S25: judging whether the gradient information length of the current layer pyramid image is smaller than a second preset size Ptmin, and executing the step S27 when the gradient information length of the current layer pyramid image is smaller than the second preset size Ptmin, otherwise executing the step S26.

Similarly, the second preset size Ptmin may be set as a fixed value, or may be automatically or manually adjusted according to practical applications, for example, the second preset size Ptmin may be set according to the size of the template image itself, the position matching accuracy requirement of the machine vision system, and the like, and it is only required to ensure that the gradient information in the pyramid image of the current layer is not too small, so that when performing online matching, matching cannot be completed because the template information is too small.

Step S26: the pyramid image of the current layer is reduced by a preset ratio to be used as a new pyramid image of the current layer, and the number of pyramid layers is increased by one, and then step S22 is performed. For example, the current-layer pyramid image may be reduced in size by half as a new current-layer pyramid image. In practical application, the preset proportion can be adjusted according to requirements such as identification precision and the like.

Step S27: template information data of the template image is generated.

In the step, a gradient position list, a gradient direction list and a gradient amplitude list of pyramid images of all layers are taken to obtain an edge point gradient list of the current template image, and then the edge point gradient list and the pyramid layer number are jointly formed into template information data which can be used for subsequent matching.

According to the template information acquisition method, the comparison value for determining the edge position point is automatically generated through each layer of pyramid image, namely the high threshold and the low threshold used for the Canny edge detection algorithm, the precision of the template information can be greatly improved, and the progress of matching the positioning points is further improved.

Fig. 3 is a schematic flow chart of acquiring a median gradient amplitude of a current layer in the template information acquiring method according to the embodiment of the present invention, and specifically, the median gradient amplitude of the current layer may be acquired through the following steps:

step S231: and acquiring the gradient amplitude of each pixel point in the pyramid image of the current layer. For example, the gray gradients in the x and y directions (i.e., two directions perpendicular to each other in the pyramid image of the current layer) of each pixel point in the pyramid image of the current layer are calculated by a Sobel operator, and then the gradients in the x and y directions calculated by the Sobel operator are subjected to polar coordinate transformation to obtain the gradient direction and gradient amplitude of each pixel point.

Step S232: creating an amplitude histogram hm (n) according to the gradient amplitudes of all pixel points in the pyramid image of the current layer, wherein the amplitude histogram hm (n) is expressed as follows:

where Mi is a value of an ith element in the histogram, n is a gradient amplitude of an nth pixel point in the pyramid image of the current layer, and n is an integer greater than or equal to 1.

Step S233: and generating a gradient amplitude median value of the current layer according to the amplitude histogram. Specifically, the median value mimemean of the gradient amplitudes of the current layer can be obtained by calculation according to the following calculation formula (2):

accordingly, when the first coefficient is 0.9 and the second coefficient is 0.7, the high threshold Tmax and the low threshold Tmin for the Canny edge detection algorithm are respectively:

Tmax＝0.9×Mimedian (3)

Tmin＝0.7×Mimedian (4)

in practical application, in addition to obtaining the current layer gradient amplitude median value through the histogram, the current layer gradient amplitude median value can also be obtained through other modes, for example, by calculating a weighted average value of the gradient amplitude of each pixel point in the current layer pyramid image, and the like, when a high threshold value Tmax and a low threshold value Tmin for a Canny edge detection algorithm are calculated according to the current layer gradient amplitude median value, the precision of template information data can be ensured by adjusting the corresponding first coefficient and second coefficient.

Fig. 4 is a schematic flow chart of acquiring edge position points of a pyramid image of a current layer in the template information acquisition method according to the embodiment of the present invention, and specifically, the edge position points of the pyramid image of the current layer may be acquired through the following steps:

step S241: and for the pyramid image of the current layer, extracting and calculating the edge by using a Canny operator to obtain all pixel edge points meeting the requirements of a high threshold value Tmax and a low threshold value Tmin.

For example, during the extraction calculation of the edge, the pixel points of which the gray value is greater than the high threshold in the pyramid image of the current layer are marked as white, the pixel points of which the gray value is less than the low threshold are marked as black, and if the gray value of the pixel is between the high threshold and the low threshold, the pixel becomes a boundary with the essential condition that the pixel is directly connected with the edge pixel (eight neighborhoods) and is connected with the edge pixel through the pixel points of which the gray value is between the high threshold and the low threshold.

Step S242: and after the edge pixel points are obtained, performing connected domain operation on the edge pixel points, and connecting adjacent edge pixel points to obtain a plurality of independent edge curve segments. The connected component operation belongs to the known technology in the art, and is not described herein.

Step S243: and taking the edge pixel points on the edge curve segment which accord with the preset condition as edge position points. After obtaining a plurality of independent edge curve segments, selecting the edge curve segments meeting preset conditions from the independent edge curve segments, and obtaining edge pixel points from the selected edge curve segments.

Fig. 5 is a schematic flow chart illustrating a process of acquiring edge position points according to an edge curve segment in the template information acquisition method according to the embodiment of the present invention, and specifically, the edge position points of the pyramid image of the current layer may be acquired according to the edge curve segment through the following steps:

step S2431: and taking the edge curve segment with the length not less than the first preset length Lmin as an alternative edge curve segment. The edge curve segment with the length less than or equal to the first preset length Lmin is usually only the area with larger noise or fine texture on the image surface, not the contour line, and needs to be deleted. If the number of the alternative edge curve segments is zero, three empty lists of a gradient position list, a gradient direction list and a gradient amplitude list are directly returned.

Step S2432: and when the sum of the lengths of all the alternative edge curve segments is greater than the second preset length Ptman, deleting redundant edge pixel points in the alternative edge curve segments to enable the number of the total edge position points to be less than the second preset length Ptmax, and taking all the edge pixel points on the alternative edge curve segments after the redundant edge pixel points are deleted as edge position points.

For example, the set granularity coefficient Gmin may be used to select the edge pixel points by limiting the distance by the set granularity parameter Gmin, and the actually set granularity coefficient Gmin may be adjusted according to the current actual edge pixel points and the second preset length Ptmax. In one scenario, the set granularity coefficient Gmin can be used, deletion is performed in a trend edge mode, the average curvature of adjacent Gmin edge points is obtained, excessive curvature is removed, only the point with the curvature closest to the average curvature is left, and other points are deleted. In the method, firstly, adjacent edge pixel points with preset number (namely Gmin) on the alternative edge curve segment are used as pixel points to be processed, and the curvature of each pixel point to be processed and the average curvature of all the pixel points to be processed are obtained; and then deleting all the pixels to be processed with the curvatures which are not the closest to the average curvature as redundant edge pixels.

In addition, gradient amplitude information can be utilized, namely, the edge pixel point with the maximum gradient amplitude is reserved in the adjacent Gmin edge pixel points. In this way, adjacent edge pixel points of a preset number (namely Gmin) on the alternative edge curve segment can be used as pixel points to be processed, and the gradient amplitudes of all the pixel points to be processed are compared; and then all the pixel points to be processed with the non-maximum gradient amplitude are used as redundant edge pixel points to be deleted.

After the total number of edge pixel points in the alternative edge curve segment is smaller than the second preset length Ptmax, extracting the gradient direction Di and the gradient amplitude Mi (wherein the gradient direction Di needs to be normalized) corresponding to the position of each remaining edge pixel point (namely the edge position point), adding the gradient direction Di and the gradient amplitude Mi into a gradient direction list and a gradient amplitude list, adding the coordinate of each edge position point into a gradient position list ListPi, and returning the three lists after all the addition is finished.

In the case of inputting only a template image, the training condition of the template edge can be modified only by adjusting the template training parameters, and when the template image contains other interference edges, such as flaws and dirt, there is no way to eliminate the interference by adjusting the parameters. In this case, manual intervention is required to generate the template edges. As shown in fig. 6, the manual intervention can be performed by inputting a mask image, i.e. the second mask image 62, the second mask image 62 is a black and white binary image, a white area indicates that the edge points in the area can be used, and a black area indicates that the edge points in the area need to be removed. This way, a suitable interactive function can be performed on the human-computer interface of the application program, and the user can generate the second mask image 62 by interaction. For example, in the human-computer interaction interface, a template image is displayed, the extracted edge points are also displayed on the template image, a painting (i.e., generating external input information) is drawn on the template image through a mouse, the area where the interference points are located is painted, then the human-computer interaction interface generates the second mask image 62 according to the external input information, and the second mask image is transferred to the training process (e.g., step S24 in fig. 2). Since the pyramid images are multi-layered, it is cumbersome to display the edge location points of all layers, and in one embodiment of the invention, the second mask image 62 may be generated based on only the edge location points of the underlying pyramid image by alternating the smearing.

If there is a strong interference point edge in a region of a layer of the pyramid image, there is no way to eliminate the interference point edge of the layer of the pyramid image. In an embodiment of the present invention, a first mask image 61 may be introduced, and the first mask image 61 may be generated by performing a dilation process on the edge position points of the underlying pyramid image, that is, extending the coordinates of each edge position point by a region (for example, extending m pixels in each direction, where m is an integer greater than 1) and using the region formed by extending all the edge position points as the first mask image 61, and transferring the first mask image 61 into a training process (for example, step S24 in fig. 2).

In each layer of the pyramid image, the actual effect is equivalent to performing an and operation on the first mask image 61 and the second mask 62, and then using them as the actual mask image of the pyramid image of the current layer. By adding this first mask image 61 it is ensured that the influence of the disturbing spot area is eliminated in all layer pyramid images.

The embodiment of the invention also provides template information acquisition equipment which can be positioned in a machine vision system and realizes matching and positioning. The template information acquiring device 7 of the present embodiment comprises a memory 71 and a processor 72, wherein the memory 71 stores therein a computer program executable in the processor 72, and the processor 72 executes the computer program to implement the steps of the template information acquiring method as described in the embodiments of fig. 2 to 6.

The motor controller in this embodiment and the template information obtaining method in the embodiment corresponding to fig. 2 to 6 belong to the same concept, and specific implementation processes thereof are described in detail in the corresponding method embodiments, and technical features in the method embodiments are correspondingly applicable in the apparatus embodiments, and are not described herein again.

An embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the template information acquisition method as described above.

The computer-readable storage medium in this embodiment and the template information obtaining method in the embodiment corresponding to fig. 2 to 6 belong to the same concept, and specific implementation processes thereof are detailed in the corresponding method embodiments, and technical features in the method embodiments are correspondingly applicable in this device embodiment, which is not described herein again.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed template information obtaining method and apparatus may be implemented in other ways.

All or part of the flow in the method of the embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a processor, to instruct related hardware to implement the steps of the embodiments of the methods. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any physical or interface switching device, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunication signal, software distribution medium, etc., capable of carrying said computer program code. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.

The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention. Furthermore, the embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.