A method and device for generating a glue path track of a shoe sole

Abstract

The embodiment of the application discloses a kind of glue road track generation method and device of shoe sole, comprising: obtaining shoe sole point cloud data, whole shoe point cloud data and vamp point cloud data, based on shoe sole point cloud data, obtain shoe sole edge track and first local registration point cloud data, based on shoe sole edge track, first local registration point cloud data and whole shoe point cloud data, obtain glue coating track and second local registration point cloud data, based on glue coating track, second local registration point cloud data and vamp point cloud data, obtain glue road track, in use process, it is not necessary to customize and reprogram robot to generate the glue road track of shoe sole for different styles, different size shoes, only need to send the glue road track generated in the method in the application to robot, it can be glued by robot to the glue road of shoe sole, realize the automatic generation of the glue road track of shoe sole, and the method does not need manual participation, with the advantages of high efficiency, no error and good glue spraying effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automation, in particular to a glue path trajectory generation method and device for shoe sole. BACKGROUND

[0002] With the application of digital production technology in shoemaking industry, robots are gradually applied to the glue spraying process of shoes, that is, the glue path of the shoe sole is sprayed by the robot.

[0003] At present, the glue path of the shoe sole is sprayed by the robot, which realizes the automation of the glue spraying process to some extent, but the adaptability of the robot is not strong. For different styles and sizes of shoes, the robot needs to be programmed to generate the glue path trajectory of the shoe sole, and the programming process needs the participation of professionals, which is complicated and inefficient, and the accuracy is not easy to control. Basically, it is determined by visual inspection.

[0004] In addition, the prior art also appears to rely on three-dimensional imaging technology to model the sprayed part (i.e. the shoe) to generate the glue path trajectory of the shoe sole, so as to realize the spraying of the glue path of the shoe sole. However, this method is not mature enough and cannot be automated. The modeling process relies too much on professional participation, i.e. professionals need to post-process, manually edit and optimize the three-dimensional model, and manual editing is bound to have errors, which leads to inaccurate three-dimensional models and ultimately affects the spraying effect. SUMMARY

[0005] Therefore, it is necessary to propose a glue path trajectory generation method and device for shoe sole to solve the above problems, which can automatically generate the glue path trajectory of the shoe sole without human intervention, and has the advantages of high efficiency, no error and good spraying effect.

[0006] To achieve the above purpose, the present application provides a glue path trajectory generation method for shoe sole in the first aspect, which comprises:

[0007] obtaining shoe sole point cloud data, whole shoe point cloud data and upper point cloud data;

[0008] According to the shoe sole point cloud data, a first local coordinate system is constructed, and the shoe sole point cloud data is transformed into the first local coordinate system to obtain first initial point cloud data; according to the whole shoe point cloud data, a second local coordinate system is constructed, and the whole shoe point cloud data is transformed into the second local coordinate system to obtain second initial point cloud data; according to the upper point cloud data, a third local coordinate system is constructed, and the upper point cloud data is transformed into the third local coordinate system to obtain third initial point cloud data;

[0009] The first initial point cloud data is processed to obtain the shoe sole edge trajectory;

[0010] filtering the first initial point cloud data according to the sole edge trajectory to obtain first local registration point cloud data, and taking the sole edge trajectory and the first local registration point cloud data as a temporary template;

[0011] transforming the temporary template into the second local coordinate system, and registering the temporary template with the second initial point cloud data to obtain a glue coating trajectory;

[0012] filtering the second initial point cloud data according to the glue coating trajectory to obtain second local registration point cloud data, and taking the glue coating trajectory and the second registration point cloud data as a final template;

[0013] transforming the final template into the third local coordinate system, and registering the final template with the third initial point cloud data to obtain a transformed glue coating trajectory, and obtaining a glue path trajectory according to the transformed glue coating trajectory and the third initial point cloud data.

[0014] Optionally, the processing of the first initial point cloud data to obtain the sole edge trajectory comprises:

[0015] a straight line passing through the origin of the first local coordinate system is constructed in the direction of a theta angle, and all points in the first initial point cloud data with a distance less than a first distance threshold from the straight line are taken as slice point clouds at the theta angle, wherein the value of the theta angle is sequentially increased from 0 degrees to 360 degrees at a preset angle step, to obtain slice point clouds at different theta angles;

[0016] the point with the maximum value in the Z-axis direction of the first local coordinate system in each slice point cloud at the theta angle is taken as a critical point, to obtain a plurality of critical points, wherein the Z-axis direction is the shortest side direction of the shoe;

[0017] the sole edge trajectory is obtained according to the plurality of critical points.

[0018] Optionally, the filtering of the first initial point cloud data according to the sole edge trajectory to obtain the first local registration point cloud data comprises:

[0019] the first initial point cloud data is surrounded to obtain first initial local registration point cloud data according to the sole edge trajectory in a contour surrounding manner;

[0020] after projecting the first initial point cloud data to the XY plane of the first local coordinate system, all points in the first initial point cloud data with a distance less than a second distance threshold from any point in the sole edge trajectory are added to the first initial local registration point cloud data to obtain the first local registration point cloud data;

[0021] The X axis and the Y axis of the first local coordinate system are the longest side direction and the second longest side direction of the shoe respectively.

[0022] Optionally, the transforming the temporary template into the second local coordinate system and registering the temporary template with the second initial point cloud data to obtain a glue applying trajectory comprises:

[0023] calculating a first transformation matrix between the first local registration point cloud data in the temporary template and the second initial point cloud data;

[0024] coarsely aligning the temporary template with the second initial point cloud data according to the first transformation matrix to obtain first aligned local registration point cloud data and an aligned edge trajectory;

[0025] blocking the first aligned local registration point cloud data, the aligned edge trajectory and the second initial point cloud data as a whole to obtain a plurality of first sub-aligned local registration point cloud data, a plurality of sub-aligned edge trajectories and a plurality of second sub-initial point cloud data;

[0026] calculating a first sub-transformation matrix between each first sub-aligned local registration point cloud data and the corresponding second sub-initial point cloud data to obtain a plurality of first sub-transformation matrices;

[0027] precisely aligning the corresponding sub-aligned edge trajectory with the corresponding second sub-initial point cloud data according to each first sub-transformation matrix to obtain a plurality of blocked aligned edge trajectories;

[0028] performing curve fitting processing on the plurality of blocked aligned edge trajectories to obtain the glue applying trajectory.

[0029] Optionally, the screening the second initial point cloud data according to the glue applying trajectory to obtain second local registration point cloud data comprises:

[0030] surrounding the second initial point cloud data according to the glue applying trajectory in a contour surrounding manner to obtain second initial local registration point cloud data;

[0031] adding all points in the second initial point cloud data with a distance less than a third distance threshold to any point in the glue applying trajectory to the second initial local registration point cloud data to obtain the second local registration point cloud data after projecting the first initial point cloud data to an XY plane of the second local coordinate system;

[0032] The X axis and the Y axis of the second local coordinate system are the longest side direction and the second longest side direction of the shoe respectively.

[0033] Optionally, the transforming the final template into the third local coordinate system and registering the final template with the third initial point cloud data to obtain a transformed glue track comprises:

[0034] calculating a second transformation matrix between the second local registration point cloud data in the final template and the third initial point cloud data;

[0035] coarsely aligning the final template with the third initial point cloud data according to the second transformation matrix to obtain second aligned local registration point cloud data and an aligned track;

[0036] blocking the second aligned local registration point cloud data, the aligned track and the second initial point cloud data as a whole to obtain a plurality of second sub-aligned local registration point cloud data, a plurality of sub-aligned tracks and a plurality of third sub-initial point cloud data;

[0037] calculating a second sub-transformation matrix between each second sub-aligned local registration point cloud data and the corresponding second sub-initial point cloud data to obtain a plurality of second sub-transformation matrices;

[0038] precisely aligning the corresponding sub-aligned track with the corresponding third sub-initial point cloud data according to each second sub-transformation matrix to obtain a plurality of blocked aligned tracks;

[0039] performing curve fitting processing on the plurality of blocked aligned tracks to obtain the transformed glue track.

[0040] Optionally, the obtaining a glue track according to the transformed glue track and the third initial point cloud data comprises:

[0041] establishing a multi-dimensional tree structure according to the third initial point cloud data;

[0042] searching for the nearest point to each point in the transformed glue track in the multi-dimensional tree structure, and replacing the points in the transformed glue track with the nearest points respectively to obtain the glue track.

[0043] Optionally, the method further comprises:

[0044] performing fitting processing on the glue track in a local linear fitting manner to obtain a standard glue track.

[0045] Optionally, the method further comprises:

[0046] performing correction processing on the glue track or the standard glue track to obtain a target glue track.

[0047] To achieve the above object, the present application provides a glue track generation device for a shoe sole in a second aspect, the device comprising:

[0048] an acquisition module configured to acquire sole point cloud data, whole shoe point cloud data, and upper point cloud data;

[0049] a coordinate system construction module configured to construct a first local coordinate system according to the sole point cloud data, transform the sole point cloud data into the first local coordinate system to obtain first initial point cloud data, construct a second local coordinate system according to the whole shoe point cloud data, transform the whole shoe point cloud data into the second local coordinate system to obtain second initial point cloud data, and construct a third local coordinate system according to the upper point cloud data, transform the upper point cloud data into the third local coordinate system to obtain third initial point cloud data;

[0050] a processing module configured to process the first initial point cloud data to obtain a sole edge track;

[0051] a first screening module configured to screen the first initial point cloud data according to the sole edge track to obtain first local registration point cloud data, and use the sole edge track and the first local registration point cloud data as a temporary template;

[0052] a first registration module configured to transform the temporary template into the second local coordinate system, and register the temporary template with the second initial point cloud data to obtain a glue applying track;

[0053] a second screening module configured to screen the second initial point cloud data according to the glue applying track to obtain second local registration point cloud data, and use the glue applying track and the second registration point cloud data as a final template;

[0054] a second registration module configured to transform the final template into the third local coordinate system, register the final template with the third initial point cloud data to obtain a transformed glue applying track, and obtain a glue path track according to the transformed glue applying track and the third initial point cloud data.

[0055] To achieve the above object, the present application provides a computer readable storage medium storing a computer program in a third aspect, the computer program is executed by the processor, so that the processor executes the steps of the method as claimed in any one of the first aspect.

[0056] To achieve the above object, the present application provides a computer device in a fourth aspect, characterized in that it comprises a memory and a processor, the memory stores a computer program, the computer program is executed by the processor, so that the processor executes the steps of the method as claimed in any one of the first aspect.

[0057] The embodiment of the present application has the following beneficial effects: the method obtains the sole point cloud data, the whole shoe point cloud data and the upper point cloud data, constructs the first local coordinate system, the second local coordinate system and the third local coordinate system according to the sole point cloud data, the whole shoe point cloud data and the upper point cloud data respectively, and transforms the sole point cloud data, the whole shoe point cloud data and the upper point cloud data into the corresponding local coordinate system to obtain the first initial point cloud data, the second initial point cloud data and the third initial point cloud data, then processes the first initial point cloud data to obtain the sole edge track, then screens the first initial point cloud data according to the sole edge track to obtain the first local registration point cloud data, and takes the sole edge track and the first local registration point cloud data as a temporary template, then transforms the temporary template into the second local coordinate system, and registers the temporary template with the second initial point cloud data to obtain the glue coating track, then screens the second initial point cloud data according to the glue coating track to obtain the second local registration point cloud data, and takes the glue coating track and the second registration point cloud data as a final template, then transforms the final template into the third local coordinate system, and registers the final template with the third initial point cloud data to obtain the transformed glue coating track, and finally obtains the glue path track according to the transformed glue coating track and the third initial point cloud data, that is, the sole edge track and the first local registration point cloud data are obtained based on the sole point cloud data, the glue coating track and the second local registration point cloud data are obtained based on the sole edge track, the first local registration point cloud data and the whole shoe point cloud data, and the glue path track is obtained based on the glue coating track, the second local registration point cloud data and the upper point cloud data, in the use process, the robot does not need to be programmed to generate the glue path track of the sole for different styles and different sizes of shoes, and only needs to send the generated glue path track to the robot, so that the robot can spray glue on the glue path of the sole, realizes automatic generation of the glue path track of the sole, realizes automatic spraying of the glue process, and the method does not need manual participation, has the advantages of high efficiency, no error and good spraying effect; in addition, the glue path track of the sole of each shoe of each style and size of shoe can also be obtained by using the method, so the method is suitable for generation of the glue path track of the sole of any style and any size of shoe. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0059] Among them:

[0060] Figure 1 FIG. 1 is a schematic diagram of a method for generating a glue path trajectory of a shoe sole according to an embodiment of the present application;

[0061] Figure 2 FIG. 2 is a schematic diagram of a shoe in a local coordinate system according to an embodiment of the present application;

[0062] Figure 3 FIG. 3 is a schematic diagram of a device for generating a glue path trajectory of a shoe sole according to an embodiment of the present application;

[0063] Figure 4 FIG. 4 shows an internal structure diagram of a computer device in some embodiments. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0065] Please refer to Figure 1 FIG. 1 is a schematic diagram of a method for generating a glue path trajectory of a shoe sole according to an embodiment of the present application, and the method comprises:

[0066] Step 110: obtaining shoe sole point cloud data, whole shoe point cloud data and shoe upper point cloud data.

[0067] It should be noted that the shoe sole point cloud data is obtained when the shoe has only a shoe sole and no shoe upper, the whole shoe point cloud data is obtained when the shoe sole of the shoe is attached to the shoe upper, and the shoe upper point cloud data is obtained when the shoe has only a shoe upper and no shoe sole.

[0068] In some embodiments, a 3D sensor can be used to scan the shoe sole to obtain the shoe sole point cloud data, a 3D sensor can be used to scan the whole shoe (i.e. the shoe sole attached to the shoe upper) to obtain the whole shoe point cloud data, and a 3D sensor can be used to scan the shoe upper to obtain the shoe upper point cloud data.

[0069] Further, in other embodiments, other ways in addition to the 3D sensor can also be used to obtain the shoe sole point cloud data, the whole shoe point cloud data and the shoe upper point cloud data. It can be understood that there are many ways to obtain point cloud data at present, and therefore, the operator can replace the 3D sensor method with other methods for obtaining point cloud data.

[0070] Step 120: constructing a first local coordinate system according to the sole point cloud data, transforming the sole point cloud data into the first local coordinate system to obtain first initial point cloud data; constructing a second local coordinate system according to the whole shoe point cloud data, transforming the whole shoe point cloud data into the second local coordinate system to obtain second initial point cloud data; constructing a third local coordinate system according to the upper point cloud data, transforming the upper point cloud data into the third local coordinate system to obtain third initial point cloud data.

[0071] The points in the first initial point cloud data, the second initial point cloud data and the third initial point cloud data are points with X-axis, Y-axis and Z-axis coordinates, that is, the coordinates of the points in the first initial point cloud data are X-axis, Y-axis and Z-axis coordinates in the first local coordinate system, the coordinates of the points in the second initial point cloud data are X-axis, Y-axis and Z-axis coordinates in the second local coordinate system, and the coordinates of the points in the third initial point cloud data are X-axis, Y-axis and Z-axis coordinates in the third local coordinate system.

[0072] It should be noted that since the sole point cloud data obtained by scanning with the 3D sensor is a sole composed of a plurality of points, the whole shoe point cloud data is a whole shoe composed of a plurality of points, and the upper point cloud data is an upper composed of a plurality of points, and the points in the plurality of points have a relative relationship, in some embodiments, the first local coordinate system, the second local coordinate system and the third local coordinate system can be constructed according to the sole point cloud data, the whole shoe point cloud data and the upper point cloud data respectively, and the sole point cloud data, the whole shoe point cloud data and the upper point cloud data can be transformed into the first local coordinate system, the second local coordinate system and the third local coordinate system respectively to obtain the first initial point cloud data, the second initial point cloud data and the third initial point cloud data respectively.

[0073] In some embodiments, PCA can be used to analyze the sole point cloud data to construct a first local coordinate system, and transform the sole point cloud data into the first local coordinate system to obtain first initial point cloud data in the first local coordinate system; PCA can be used to analyze the whole shoe point cloud data to construct a second local coordinate system, and transform the whole shoe point cloud data into the second local coordinate system to obtain second initial point cloud data in the second local coordinate system; PCA can be used to analyze the upper point cloud data to construct a third local coordinate system, and transform the upper point cloud data into the third local coordinate system to obtain third initial point cloud data in the third local coordinate system; wherein PCA is Principal Component Analysis (PCA).

[0074] Step 130: processing the first initial point cloud data to obtain a sole edge track.

[0075] In some embodiments, the first initial point cloud data in the first local coordinate system can be processed to obtain the sole edge trajectory. It can be understood that the purpose of the processing is to determine which points in the first initial point cloud data corresponding to the sole are points of the edge trajectory of the sole, so as to take the trajectory composed of these points as the edge trajectory of the sole.

[0076] Step 140: screening the first initial point cloud data according to the sole edge trajectory to obtain the first local registration point cloud data, and taking the sole edge trajectory and the first local registration point cloud data as a temporary template.

[0077] It should be noted that the sole edge trajectory is obtained by processing the first initial point cloud data, and therefore the first initial point cloud data contains the points in the sole edge trajectory; the first local registration point cloud data is obtained by screening the first initial point cloud data according to the sole edge trajectory, and therefore the first initial point cloud data also contains the points in the first local registration point cloud data; wherein the first local registration point cloud data and the sole edge trajectory have a containing relationship, that is, the first local registration point cloud data contains the sole edge trajectory, and it can be understood that the sole edge trajectory and the first local registration point cloud data are an integral whole (i.e., a plurality of points constituting a sole) in the first local coordinate system, and therefore the sole edge trajectory and the first local registration point cloud data can be taken as a temporary template (i.e., a plurality of points constituting a sole are taken as a temporary template).

[0078] In some embodiments, the first initial point cloud data can be screened according to the sole edge trajectory to screen out some scattered points (or isolated points, invalid points, etc.) in the first initial point cloud data according to the sole edge trajectory, to obtain the first local registration point cloud data, and take the sole edge trajectory and the first local registration point cloud data as a temporary template.

[0079] Step 150: transforming the temporary template into the second local coordinate system, and registering the temporary template with the second initial point cloud data to obtain the glue coating trajectory.

[0080] It should be noted that since the coordinates of the sole edge track in the temporary template and the points in the first local registration point cloud data are coordinates in the first local coordinate system, and the first local coordinate system and the second local coordinate system are different, it is necessary to transform the coordinates of the sole edge track in the temporary template and the points in the first local registration point cloud data to coordinates in the second local coordinate system, and in the transformation process, the temporary template is registered with the second initial point cloud data to obtain the glue applying track. It can be understood that the second initial point cloud data is the point cloud data corresponding to the whole shoe (i.e., the point cloud data corresponding to the shoe upper to which the sole is attached), and the temporary template is the point cloud data corresponding to the sole. Therefore, the point cloud data of the sole part in the second initial point cloud data can be registered with the temporary template to obtain the glue applying track between the sole and the shoe upper.

[0081] It should be further noted that since the sole point cloud data in step 110 is obtained when the shoe only has the sole and does not have the shoe upper, and the whole shoe point cloud data is obtained when the sole of the shoe is attached to the shoe upper, the temporary template obtained based on the sole point cloud data is also the point cloud data corresponding to the sole, but is different from the point cloud data of the sole part in the second initial point cloud data obtained based on the whole shoe point cloud data. Therefore, it is necessary to register the point cloud data of the sole part in the second initial point cloud data with the temporary template.

[0082] Step 160: filtering the second initial point cloud data according to the glue applying track to obtain second local registration point cloud data, and taking the glue applying track and the second registration point cloud data as the final template.

[0083] It should be noted that the glue applying track is obtained by registering the temporary template with the second initial point cloud data, and therefore the second initial point cloud data contains the points in the glue applying track. The second local registration point cloud data is obtained by filtering the second initial point cloud data according to the glue applying track, and therefore the second initial point cloud data also contains the points in the second local registration point cloud data. The second local registration point cloud data and the glue applying track have a containing relationship, i.e., the second local registration point cloud data contains the glue applying track. In addition, it can be understood that the glue applying track and the second local registration point cloud data are a whole (i.e., constitute a plurality of points of the whole shoe) in the second local coordinate system. Therefore, the glue applying track and the second local registration point cloud data can be taken as the final template (i.e., the plurality of points constituting the whole shoe are taken as the temporary template).

[0084] In some embodiments, the second initial point cloud data can be filtered according to the glue applying track to filter out some relatively scattered points (or isolated points, invalid points, etc.) in the second initial point cloud data according to the glue applying track to obtain the second local registration point cloud data, and the glue applying track and the second local registration point cloud data are taken as the final template.

[0085] Step 170: transforming the final template into the third local coordinate system, and registering the final template with the third initial point cloud data to obtain a transformed glue applying track, and obtaining a glue path track according to the transformed glue applying track and the third initial point cloud data.

[0086] It should be noted that, since the coordinates of the glue applying track in the final template and the points in the second local registration point cloud data are coordinates in the second local coordinate system, and the second local coordinate system and the third local coordinate system are different, it is necessary to transform the coordinates of the glue applying track in the final template and the points in the second local registration point cloud data into coordinates in the third local coordinate system, and in the transformation process, the final template is registered with the third initial point cloud data to obtain a transformed glue applying track. It can be understood that the third initial point cloud data is the point cloud data corresponding to the upper, and the final template is the point cloud data corresponding to the whole shoe (i.e. the shoe sole is attached to the point cloud data corresponding to the upper), so the point cloud data of the upper part in the final template can be registered with the third initial point cloud data, thereby obtaining the transformed glue applying track between the shoe sole and the upper.

[0087] It should be further noted that, since the whole shoe point cloud data in step 110 is obtained in the case that the shoe sole of the shoe is attached to the upper, and the upper point cloud data is obtained in the case that the shoe only has the upper without the shoe sole, although the third initial point cloud data is also the point cloud data corresponding to the upper, it is not the same as the point cloud data of the upper part in the final template obtained based on the whole shoe sole point cloud data and the temporary template, therefore, it is necessary to register the point cloud data of the upper part in the final template with the third initial point cloud data.

[0088] In some embodiments, after obtaining the transformed glue applying track between the shoe sole and the upper, it is also necessary to process according to the transformed glue applying track and the third initial point cloud data to obtain the glue path track between the shoe sole and the upper.

[0089] In another possible implementation, before step 120, the shoe sole point cloud data, the whole shoe point cloud data and the upper point cloud data obtained in step 110 need to be pre-processed respectively, and then step 120 and the subsequent steps are executed. It can be understood that the purpose of pre-processing the shoe sole point cloud data, the whole shoe point cloud data and the upper point cloud data respectively is to effectively remove some invalid points or isolated points in the shoe sole point cloud data, the whole shoe point cloud data and the upper point cloud data, reduce the number of points in the point cloud data, to obtain more simplified reduced point cloud data, and to remove edge burrs in the shoe sole point cloud data, the whole shoe point cloud data and the upper point cloud data, and eliminate background noise in the shoe sole point cloud data, the whole shoe point cloud data and the upper point cloud data, so that the features in the point cloud data can be better recognized; wherein the pre-processing includes but is not limited to voxel filtering, radius rejection, Euclidean distance segmentation, denoising, etc.

[0090] In addition, it needs to be specially pointed out that the method in the above embodiment does not limit the order of steps, that is, in actual operation, the order of the above steps can be exchanged according to the actual needs of the operator, that is, in some embodiments, in order to adapt to the order of the glue spraying process of the shoe factory, the steps in the above embodiment can be exchanged as follows: obtaining the sole point cloud data; constructing a first local coordinate system according to the sole point cloud data, transforming the sole point cloud data into the first local coordinate system to obtain first initial point cloud data; processing the first initial point cloud data to obtain a sole edge track; filtering the first initial point cloud data according to the sole edge track to obtain first local registration point cloud data, and taking the sole edge track and the first local registration point cloud data as a temporary template; obtaining the whole shoe point cloud data; constructing a second local coordinate system according to the whole shoe point cloud data, transforming the whole shoe point cloud data into the second local coordinate system to obtain second initial point cloud data; transforming the temporary template into the second local coordinate system, and registering the temporary template with the second initial point cloud data to obtain a glue spraying track; filtering the second initial point cloud data according to the glue spraying track to obtain second local registration point cloud data, and taking the glue spraying track and the second registration point cloud data as a final template; obtaining the upper point cloud data; constructing a third local coordinate system according to the upper point cloud data, transforming the upper point cloud data into the third local coordinate system to obtain third initial point cloud data; transforming the final template into the third local coordinate system, and registering the final template with the third initial point cloud data to obtain a transformed glue spraying track, and obtaining a glue path track according to the transformed glue spraying track and the third initial point cloud data.

[0091] In the embodiments of the present application, by obtaining the sole edge track and the first local registration point cloud data based on the sole point cloud data, obtaining the glue spraying track and the second local registration point cloud data based on the sole edge track, the first local registration point cloud data and the whole shoe point cloud data, and obtaining the glue path track based on the glue spraying track, the second local registration point cloud data and the upper point cloud data, in the use process, it is not necessary to reprogram the robot for different styles and different sizes of shoes to generate the glue path track of the sole, but only needs to send the generated glue path track to the robot, that is, the robot can spray glue on the glue path of the sole, realizing the automatic generation of the glue path track of the sole, that is, the automation of the glue spraying process is truly realized, and the method does not need manual intervention, has the advantages of high efficiency, no error and good glue spraying effect; in addition, since the glue path track of the sole of each style and size of shoe (or each shoe of each style and size of shoe) can also be obtained by the above method, therefore, the above method is suitable for the generation of the glue path track of the sole of any style and any size of shoe.

[0092] In a feasible implementation, the step 130 in the above embodiment, the processing of the first initial point cloud data to obtain the sole edge track, comprises: constructing a straight line passing through the origin of the first local coordinate system in the direction of the theta angle, and taking all points in the first initial point cloud data with a distance less than a first distance threshold from the straight line as slice point clouds under the theta angle, wherein the value of the theta angle is sequentially increased from 0 degrees to 360 degrees at a preset angle step, to obtain slice point clouds under different theta angles; taking the point with the maximum value in the Z-axis direction of the first local coordinate system in each slice point cloud under the theta angle as a critical point, to obtain a plurality of critical points, wherein the Z-axis direction is the shortest side direction of the shoe; and obtaining the sole edge track according to the plurality of critical points.

[0093] Wherein, the preset angle step and the first distance threshold are obtained by the operator according to a large number of tests and statistics, of course, the operator can also set the preset angle step and the first distance threshold according to the actual demand, which is not limited here.

[0094] It should be noted that the shortest side direction of the shoe is for the shoe corresponding to the sole point cloud data, the whole shoe point cloud data and the upper point cloud data, that is, in the embodiment of the application, the Z-axis direction of the first local coordinate system, the second local coordinate system and the third local coordinate system is the shortest side direction of the shoe, for example, please refer to Figure 2 , which is a schematic view of the shoe in the local coordinate system in the embodiment of the application.

[0095] In some embodiments, by taking the value of the theta angle from 0 degrees to 360 degrees at a preset angle step, slice point clouds under different theta angles are obtained, and the point with the maximum value in the Z-axis direction of the first local coordinate system in each slice point cloud under the theta angle is taken as a critical point, to obtain a plurality of critical points, since in the embodiment of the application, the Z-axis direction is the shortest side direction of the shoe, therefore, the sole edge track can be constructed according to the plurality of critical points under different theta angles.

[0096] In the embodiment of the application, by taking the value of the theta angle from 0 degrees to 360 degrees at a preset angle step, slice point clouds under different theta angles are obtained, and the point with the maximum value in the Z-axis direction of the first local coordinate system in each slice point cloud under the theta angle is taken as a critical point, to obtain a plurality of critical points, so as to obtain the sole edge track according to the plurality of critical points, which realizes the automatic obtaining of the sole edge track, and this embodiment is suitable for the sole edge track generation of the sole of any style and any size of shoe.

[0097] In a feasible implementation, the step 140 in the above embodiment, filtering the first initial point cloud data according to the sole edge trajectory to obtain the first local registration point cloud data, comprises: surrounding the first initial point cloud data according to the sole edge trajectory in a contour surrounding manner to obtain the first initial local registration point cloud data; after projecting the first initial point cloud data to the XY plane of the first local coordinate system, adding all points in the first initial point cloud data with a distance less than a second distance threshold to any point in the sole edge trajectory to the first initial local registration point cloud data to obtain the first local registration point cloud data; wherein the X axis and the Y axis of the first local coordinate system are the longest side direction and the second longest side direction of the shoe respectively.

[0098] The second distance threshold is obtained by an operator according to a large number of tests and statistics, and of course, the operator can also set the second distance threshold according to actual needs, which is not limited here.

[0099] It should be noted that the XY plane of the first local coordinate system is the plane formed by the X axis and the Y axis of the first local coordinate system; the longest side direction and the second longest side direction of the shoe are for the shoe corresponding to the sole point cloud data, the whole shoe point cloud data and the upper point cloud data, i.e. in the embodiments of the present application, the X axis of the first local coordinate system, the second local coordinate system and the third local coordinate system is the longest side direction of the shoe, and the Y axis of the first local coordinate system, the second local coordinate system and the third local coordinate system is the second longest side direction of the shoe. For example, please continue to refer to Figure 2 , which is a schematic diagram of the shoe in the local coordinate system in the embodiments of the present application.

[0100] In some embodiments, the contour surrounding manner can be used, and then the points of the first initial point cloud data within the sole edge trajectory are surrounded according to the sole edge trajectory, i.e. some scattered points (or isolated points, invalid points, etc.) in the first initial point cloud data are filtered out according to the sole edge trajectory, so as to obtain the first initial local registration point cloud data. After projecting the first initial point cloud data to the XY plane of the first local coordinate system, it can be judged whether the points filtered out from the first initial point cloud data according to the sole edge trajectory can still be retained (as points of the first initial local registration point cloud data), i.e. after adding all points in the first initial point cloud data with a distance less than a second distance threshold to any point in the sole edge trajectory to the first initial local registration point cloud data, the first local registration point cloud data is obtained.

[0101] It should be further explained that, since the first initial point cloud data includes the sole edge track and the first initial local registration point cloud data, the sole edge track and the first initial local registration point cloud data are also projected to the XY plane of the first local coordinate system. In the XY plane of the first local coordinate system, it is determined whether the points in the first initial point cloud data meet the reservation judgment condition according to the points in the projected sole edge track. In the case where the points in the first initial point cloud data meet the reservation judgment condition, the points in the first initial point cloud data are added to the first initial local registration point cloud data. It can be understood that, in the case where the points in the first initial point cloud data are added to the first initial local registration point cloud data, the points in the first initial point cloud data before projection are added to the first initial local registration point cloud data before projection, that is, the points in the first initial point cloud data are still points with the X-axis, Y-axis and Z-axis coordinates of the first local coordinate system.

[0102] In the embodiments of the present application, the first initial local registration point cloud data is obtained by surrounding the first initial point cloud data according to the sole edge track in a contour surrounding manner. Then, after the first initial point cloud data is projected to the XY plane of the first local coordinate system, some points in the first initial point cloud data that meet the reservation judgment condition are reserved according to the sole edge track, so as to obtain the first local registration point cloud data. That is, the points in the first initial point cloud data that are relatively scattered (or isolated points, invalid points, etc.) are automatically filtered out according to the sole edge track, so that the characteristics of the point cloud data of the sole can be better recognized, thereby facilitating the subsequent registration of the point cloud data of the sole and the point cloud data of the whole shoe.

[0103] In some possible implementation manners, the step 150 in the above-mentioned embodiments, the temporary template is transformed into the second local coordinate system, and the temporary template is registered with the second initial point cloud data to obtain the glue applying track, includes: calculating a first transformation matrix between the first local registration point cloud data in the temporary template and the second initial point cloud data; performing rough alignment on the temporary template and the second initial point cloud data according to the first transformation matrix to obtain first aligned local registration point cloud data and an aligned edge track; performing block division on the first aligned local registration point cloud data, the aligned edge track and the second initial point cloud data as a whole to obtain a plurality of first sub-aligned local registration point cloud data, a plurality of sub-aligned edge tracks and a plurality of second sub-initial point cloud data; calculating a first sub-transformation matrix between each first sub-aligned local registration point cloud data and the corresponding second sub-initial point cloud data to obtain a plurality of first sub-transformation matrices; performing accurate alignment on the corresponding sub-aligned edge track and the corresponding second sub-initial point cloud data according to each first sub-transformation matrix to obtain a plurality of block-aligned edge tracks; and performing curve fitting processing on the plurality of block-aligned edge tracks to obtain the glue applying track.

[0104] It should be noted that, since the coordinates of the sole edge track in the temporary template and the points in the first local registration point cloud data are coordinates in the first local coordinate system, and the first local coordinate system and the second local coordinate system are different, and the first local registration point cloud data in the temporary template contains the sole edge track, therefore, in the case of transforming the coordinates of the sole edge track in the temporary template and the points in the first local registration point cloud data to the second local coordinate system, only the first transformation matrix between the first local registration point cloud data in the temporary template and the second initial point cloud data needs to be calculated.

[0105] It should be further noted that, for the calculation method of all transformation matrices in the embodiments of the present application, for example, the calculation of the transformation matrix C between the point cloud data A and the point cloud data B can be performed in the manner shown in the embodiments of the present application, for example, first set the transformation matrix as The points in the point cloud data A are The points in the point cloud data B are Wherein, n is the number of points in the point cloud data A, m is the number of points in the point cloud data B, and k is the number of iterations; then search for the point corresponding to the point in the point cloud data A, so that reaches the minimum, otherwise the iteration number k+1; the rotation matrix R and the translation variable T k are calculated by using the formula k ; in the case that d k+1 is less than a fixed threshold, or the iteration number reaches a preset maximum iteration number, R k and T k are taken as the rotation matrix R and the translation variable T respectively. In addition, for all transformation matrices in the embodiments of the present application, the operator can also select other ways to calculate the transformation matrix between two point cloud data according to actual needs. It can be understood that the present application only discloses one way to calculate the transformation matrix between two point cloud data.

[0106] In some embodiments, since the first local registration point cloud data in the temporary template contains the sole edge track, that is, the first local registration point cloud data in the temporary template is an entirety with the sole edge track, the temporary template can be roughly aligned with the second initial point cloud data according to the first transformation matrix to obtain the first aligned local registration point cloud data and the aligned edge track (that is, the temporary template after the temporary template is roughly aligned with the second initial point cloud data in the second local coordinate system); since the first aligned local registration point cloud data and the aligned edge track are obtained after the temporary template is roughly aligned with the second initial point cloud data, the first aligned local registration point cloud data, the aligned edge track and the second initial point cloud data can be regarded as an entirety, and then the entirety is blocked to obtain the first aligned local registration point cloud data after blocking, the plurality of first sub-aligned local registration point cloud data, the aligned edge track after blocking, the plurality of sub-aligned edge tracks and the second initial point cloud data after blocking, and then for each corresponding block, the following is included: calculating the first sub-transformation matrix between the first sub-aligned local registration point cloud data and the second sub-initial point cloud data, accurately aligning the sub-aligned edge track with the second sub-initial point cloud data according to each first sub-transformation matrix to obtain the blocked aligned edge track, and finally performing curve fitting processing on the plurality of blocked aligned edge tracks to obtain the glue applying track.

[0107] In the embodiments of the present application, by transforming the temporary template in the first local coordinate system to the second local coordinate system, and roughly aligning the temporary template with the second initial point cloud data as an entirety to obtain the first aligned local registration point cloud data and the aligned edge track, after the rough alignment, the first aligned local registration point cloud data, the aligned edge track and the second initial point cloud data are blocked, and then each block is accurately aligned, thereby obtaining the plurality of blocked aligned edge tracks, and finally performing curve fitting processing on the plurality of blocked aligned edge tracks to obtain the glue applying track, which realizes the automatic registration of the temporary template with the second initial point cloud data to obtain the glue applying track, and makes the obtained glue applying track more accurate, so as to obtain an accurate glue path track based on the glue applying track, the second local registration point cloud data and the upper point cloud data.

[0108] In a feasible implementation, the step 160 in the above embodiment, filtering the second initial point cloud data according to the glue applying track to obtain the second local registration point cloud data, comprises: surrounding the second initial point cloud data according to the glue applying track in a contour surrounding manner to obtain second initial local registration point cloud data; after projecting the first initial point cloud data to the XY plane of the second local coordinate system, adding all points in the second initial point cloud data with a distance less than a third distance threshold to any point in the glue applying track to the second initial local registration point cloud data to obtain the second local registration point cloud data; wherein the X axis and the Y axis of the second local coordinate system are the longest side direction and the second longest side direction of the shoe respectively.

[0109] The third distance threshold is obtained by an operator according to a large number of tests and statistics, and of course, the operator can also set the third distance threshold according to actual needs, which is not limited here.

[0110] It should be noted that the XY plane of the second local coordinate system is the plane formed by the X axis and the Y axis of the second local coordinate system; the longest side direction and the second longest side direction of the shoe have been introduced in the above embodiment, and examples are described in the above embodiment, which will not be repeated here. Figure 2

[0111] In some embodiments, the contour surrounding manner can be used, and then the points of the second initial point cloud data within the glue applying track are surrounded according to the glue applying track, that is, some scattered points (or isolated points, invalid points, etc.) in the second initial point cloud data are filtered out according to the glue applying track, to obtain the second initial local registration point cloud data. After projecting the second initial point cloud data to the XY plane of the second local coordinate system, it can be judged whether the scattered points (or isolated points, invalid points, etc.) filtered out from the second initial point cloud data according to the glue applying track can still be retained (as points of the second initial local registration point cloud data), that is, after adding all points in the second initial point cloud data with a distance less than a third distance threshold to any point in the glue applying track to the second initial local registration point cloud data, the second local registration point cloud data is obtained.

[0112] ​It needs to be further explained that, since the second initial point cloud data includes the glue applying track and the second initial local registration point cloud data, the glue applying track and the second initial local registration point cloud data are also projected to the XY plane of the second local coordinate system. In the XY plane of the second local coordinate system, whether the points in the second initial point cloud data meet the reservation judgment condition is determined according to the points in the projected glue applying track. In the case where the second initial point cloud data meets the reservation judgment condition, the points in the second initial point cloud data are added to the second initial local registration point cloud data. It can be understood that, in the case where the points in the second initial point cloud data are added to the second initial local registration point cloud data, the points in the second initial point cloud data before projection are added to the second initial local registration point cloud data before projection, that is, the points in the second initial point cloud data are still points with the X-axis, Y-axis and Z-axis coordinates of the second local coordinate system.

[0113] In the embodiment of the present application, the second initial local registration point cloud data is obtained by surrounding the second initial point cloud data according to the glue applying track in a contour surrounding manner. Then, after the second initial point cloud data is projected to the XY plane of the second local coordinate system, some points in the second initial point cloud data that meet the reservation judgment condition are reserved according to the shoe sole edge track, so as to obtain the second local registration point cloud data, that is, to automatically filter out some relatively scattered points (or isolated points, invalid points, etc.) in the second initial point cloud data according to the glue applying track, so that the characteristics of the point cloud data of the whole shoe can be better recognized, thereby facilitating the subsequent registration of the point cloud data of the whole shoe and the point cloud data of the shoe upper.

[0114] In a feasible implementation manner, the step 170 in the above embodiment, the final template is transformed into the third local coordinate system, and the final template is registered with the third initial point cloud data to obtain a transformed glue applying track, including: calculating a second transformation matrix between the second local registration point cloud data in the final template and the third initial point cloud data; performing rough alignment of the final template and the third initial point cloud data according to the second transformation matrix to obtain second aligned local registration point cloud data and an aligned track; performing block division on the second aligned local registration point cloud data, the aligned track and the second initial point cloud data as a whole to obtain a plurality of second sub-aligned local registration point cloud data, a plurality of sub-aligned tracks and a plurality of third sub-initial point cloud data; calculating a second sub-transformation matrix between each second sub-aligned local registration point cloud data and the corresponding second sub-initial point cloud data to obtain a plurality of second sub-transformation matrices; performing accurate alignment of the corresponding sub-aligned track and the corresponding third sub-initial point cloud data according to each second sub-transformation matrix to obtain a plurality of block-aligned tracks; and performing curve fitting processing on the plurality of block-aligned tracks to obtain the transformed glue applying track.

[0115] It should be noted that, since the coordinates of the glue applying track in the final template and the points in the second local registration point cloud data are coordinates in the second local coordinate system, and the second local coordinate system and the third local coordinate system are different, and the second local registration point cloud data in the final template contains the glue applying track, therefore, in the case of transforming the coordinates of the glue applying track in the final template and the points in the second local registration point cloud data to the third local coordinate system, only the second transformation matrix between the second local registration point cloud data in the final template and the third initial point cloud data needs to be calculated.

[0116] It should be further noted that, for the calculation method of all transformation matrices in the embodiments of the present application, the calculation method in the above-mentioned example has been shown, of course, the operator can also select other calculation methods of the transformation matrix between two point cloud data according to actual needs, and it can be understood that in the above-mentioned example, the present application only discloses one method for calculating the transformation matrix between two point cloud data by way of example.

[0117] In some embodiments, since the second local registration point cloud data in the final template contains the glue applying track, that is, the second local registration point cloud data in the final template and the glue applying track are an integral whole, therefore, the second alignment local registration point cloud data and the alignment track (i.e. the final template after the final template is roughly aligned with the third initial point cloud data in the third local coordinate system) can be obtained by roughly aligning the final template with the third initial point cloud data according to the second transformation matrix. Since the second alignment local registration point cloud data and the alignment track are obtained after the final template is roughly aligned with the third initial point cloud data, therefore, the second alignment local registration point cloud data, the alignment track and the third initial point cloud data can be regarded as an integral whole, and then the integral whole is divided into blocks, thereby obtaining the second alignment local registration point cloud data after block division, the alignment track after block division and the third initial point cloud data after block division, and then for each corresponding block, including: calculating the second sub-transformation matrix between the second sub-alignment local registration point cloud data and the third sub-initial point cloud data, accurately aligning the sub-alignment track with the third sub-initial point cloud data according to each second sub-transformation matrix to obtain a block alignment track, and finally performing curve fitting processing on the plurality of block alignment tracks to obtain the transformed glue applying track.

[0118] In the embodiment of the present application, by transforming the final template in the second local coordinate system to the third local coordinate system, and performing overall rough alignment of the final template and the third initial point cloud data to obtain the second aligned local registration point cloud data and the alignment track, after rough alignment, the second aligned local registration point cloud data, the alignment track and the third initial point cloud data are divided into blocks, and then accurate alignment of each block is performed, thereby obtaining a plurality of block alignment tracks, and finally the plurality of block alignment tracks are subjected to curve fitting processing, thereby obtaining the transformed glue application track, which realizes automatic registration of the final template and the third initial point cloud data to obtain the transformed glue application track, so that a more accurate glue application track is obtained, facilitating subsequent track transformation of the glue application track and the third initial point cloud data to obtain an accurate glue track.

[0119] In a feasible implementation manner, the step 170 in the above embodiment, obtaining the glue track according to the transformed glue application track and the third initial point cloud data, comprises: establishing a multi-dimensional tree structure according to the third initial point cloud data; searching for a nearest point to each point in the transformed glue application track in the multi-dimensional tree structure, and replacing the points in the transformed glue application track with the nearest points respectively to obtain the glue track.

[0120] In the embodiment of the present application, by establishing a multi-dimensional tree structure according to the third initial point cloud data, and searching for a nearest point to each point in the transformed glue application track in the multi-dimensional tree structure, and replacing the points in the transformed glue application track with the nearest points respectively, that is, by replacing the nearest points in the transformed glue application track with the points in the third initial point cloud data to form the glue track, an accurate glue track is obtained, and automatic generation of the glue track of the shoe sole is realized, that is, the automation of the glue spraying process is truly realized.

[0121] In a feasible implementation manner, the method in the above embodiment further comprises: adopting a local linear fitting manner to perform fitting processing on the glue track to obtain a standard glue track.

[0122] In the embodiment of the present application, by adopting a local linear fitting manner to perform fitting processing on the glue track, a more accurate standard glue track is obtained, and by fitting the glue track, the obtained standard glue track is more standard, so as to adapt to the requirements of the glue spraying process of the shoe factory.

[0123] In a feasible implementation manner, the method in the above embodiment further comprises: performing correction processing on the glue track or the standard glue track to obtain a target glue track.

[0124] It should be noted that the correction processing includes but is not limited to smoothing, interpolation and the like, and in some embodiments, the smoothing adopts mean filter smoothing, and the interpolation adopts B-spline interpolation.

[0125] In the embodiments of the present application, the target glue path trajectory can be obtained by modifying the glue path trajectory or the standard glue path trajectory, i.e., by adjusting the noise, brightness, deformation, etc. of the glue path trajectory or the standard glue path trajectory.

[0126] In some embodiments, the present application also provides a glue path trajectory generation device for a shoe sole.

[0127] Please refer to Figure 3 , a schematic diagram of a glue path trajectory generation device for a shoe sole in the embodiments of the present application, the device 310 comprises:

[0128] The acquisition module 311 is configured to acquire the shoe sole point cloud data, the whole shoe point cloud data and the upper point cloud data.

[0129] The coordinate system construction module 312 is configured to construct a first local coordinate system according to the shoe sole point cloud data, transform the shoe sole point cloud data into the first local coordinate system, and obtain first initial point cloud data; construct a second local coordinate system according to the whole shoe point cloud data, transform the whole shoe point cloud data into the second local coordinate system, and obtain second initial point cloud data; and construct a third local coordinate system according to the upper point cloud data, transform the upper point cloud data into the third local coordinate system, and obtain third initial point cloud data.

[0130] The processing module 313 is configured to process the first initial point cloud data to obtain a shoe sole edge trajectory.

[0131] The first screening module 314 is configured to screen the first initial point cloud data according to the shoe sole edge trajectory to obtain first local registration point cloud data, and use the shoe sole edge trajectory and the first local registration point cloud data as a temporary template.

[0132] The first registration module 315 is configured to transform the temporary template into the second local coordinate system, and register the temporary template with the second initial point cloud data to obtain a glue coating trajectory.

[0133] The second screening module 316 is configured to screen the second initial point cloud data according to the glue coating trajectory to obtain second local registration point cloud data, and use the glue coating trajectory and the second registration point cloud data as a final template.

[0134] The second registration module 317 is configured to transform the final template into the third local coordinate system, and register the final template with the third initial point cloud data to obtain a transformed glue coating trajectory, and obtain a glue path trajectory according to the transformed glue coating trajectory and the third initial point cloud data.

[0135] In the embodiments of the present application, the related content of the above-mentioned acquisition module 311, coordinate system construction module 312, processing module 313, first screening module 314, first registration module 315, second screening module 316 and second registration module 317 can be referred toFigure 1 The details are not described here.

[0136] It should be noted that the device 310 of the present application also includes some other modules. It can be understood that the method of the present application has a one-to-one correspondence with the device 310, and therefore some other modules of the device 310 of the present application are the corresponding contents of the method of the present application in the above embodiments.

[0137] In the embodiments of the present application, the sole edge track and the first local registration point cloud data are obtained based on the sole point cloud data, the glue coating track and the second local registration point cloud data are obtained based on the sole edge track, the first local registration point cloud data and the whole shoe point cloud data, and the glue path track is obtained based on the glue coating track, the second local registration point cloud data and the upper point cloud data. In use, it is not necessary to customize the robot for different styles and sizes of shoes to generate the glue path track of the sole, but only the generated glue path track needs to be sent to the robot by using the above method, so that the robot can spray glue on the glue path of the sole. The automatic generation of the glue path track of the sole is realized, that is, the automation of the glue spraying process is truly realized. The method does not require human participation and has the advantages of high efficiency, no error and good glue spraying effect. In addition, since the glue path track of the sole of each style and size of shoe (or each shoe of each style and size of shoe) can also be obtained by using the above method, the above method is suitable for the generation of the glue path track of the sole of any style and size of shoe.

[0138] In some embodiments, the present application also provides a computer readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the shoe sole glue path track generation method in the above method embodiment.

[0139] In some embodiments, the present application also provides a computer device including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the shoe sole glue path track generation method in the above method embodiment.

[0140] Figure 4 An internal structure diagram of a computer device in some embodiments is shown. The computer device can be a terminal, a server, or a gateway. As Figure 4 shown, the computer device includes a processor, a memory and a network interface connected through a system bus.

[0141] The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and can also store a computer program. When the computer program is executed by the processor, the processor can implement each step in the above method embodiments. The internal memory can also store a computer program. When the computer program is executed by the processor, the processor can execute each step in the above method embodiments. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. A specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] Those of ordinary skill in the art can understand that all or part of the processes in the above embodiments can be completed by a computer program instructing related hardware. The program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above embodiments.

[0143] Any reference to memory, storage, databases, or other media in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0144] Each technical feature of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combinations of the technical features do not contradict each other, they should be considered within the scope of the present application.

[0145] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method of generating a tread pattern of a shoe sole, characterized by, The method comprises: obtaining sole point cloud data, whole shoe point cloud data and upper point cloud data; constructing a first local coordinate system according to the sole point cloud data, transforming the sole point cloud data into the first local coordinate system to obtain first initial point cloud data; constructing a second local coordinate system according to the whole shoe point cloud data, transforming the whole shoe point cloud data into the second local coordinate system to obtain second initial point cloud data; constructing a third local coordinate system according to the upper point cloud data, transforming the upper point cloud data into the third local coordinate system to obtain third initial point cloud data; processing the first initial point cloud data to obtain a sole edge track; screening the first initial point cloud data according to the sole edge track to obtain first local registration point cloud data, and taking the sole edge track and the first local registration point cloud data as a temporary template; transforming the temporary template into the second local coordinate system, and registering the temporary template with the second initial point cloud data to obtain a glue applying track; screening the second initial point cloud data according to the glue applying track to obtain second local registration point cloud data, and taking the glue applying track and the second registration point cloud data as a final template; transforming the final template into the third local coordinate system, and registering the final template with the third initial point cloud data to obtain a transformed glue applying track, and obtaining a glue path track according to the transformed glue applying track and the third initial point cloud data; wherein the processing the first initial point cloud data to obtain a sole edge track comprises: constructing a straight line passing through the origin of the first local coordinate system in the direction of a theta angle, and taking all points in the first initial point cloud data with a distance less than a first distance threshold from the straight line as slice point cloud under the theta angle, wherein the value of the theta angle is sequentially increased from 0 degrees to 360 degrees at a preset angle step, to obtain slice point cloud under different theta angles; taking the point with the maximum value in the Z-axis direction of the first local coordinate system in each theta angle slice point cloud as a critical point to obtain a plurality of critical points, wherein the Z-axis direction is the shortest side direction of the shoe; obtaining the sole edge track according to the plurality of critical points.

2. The method of claim 1, wherein, The screening the first initial point cloud data according to the sole edge track to obtain first local registration point cloud data comprises: surrounding the first initial point cloud data according to the sole edge track to obtain first initial local registration point cloud data in a contour surrounding manner; after projecting the first initial point cloud data to the XY plane of the first local coordinate system, adding all points in the first initial point cloud data with a distance less than a second distance threshold from any point in the sole edge track to the first initial local registration point cloud data to obtain the first local registration point cloud data; wherein the X-axis and Y-axis of the first local coordinate system are the longest side direction and the second longest side direction of the shoe respectively.

3. The method of claim 1, wherein, The transforming the temporary template into the second local coordinate system and registering the temporary template with the second initial point cloud data to obtain a gluing track comprises: calculating a first transformation matrix between the first local registration point cloud data in the temporary template and the second initial point cloud data; roughly aligning the temporary template with the second initial point cloud data according to the first transformation matrix to obtain first aligned local registration point cloud data and an aligned edge track; blocking the first aligned local registration point cloud data, the aligned edge track and the second initial point cloud data as a whole to obtain a plurality of first sub-aligned local registration point cloud data, a plurality of sub-aligned edge tracks and a plurality of second sub-initial point cloud data; calculating a first sub-transformation matrix between each first sub-aligned local registration point cloud data and the corresponding second sub-initial point cloud data to obtain a plurality of first sub-transformation matrices; precisely aligning the corresponding sub-aligned edge track with the corresponding second sub-initial point cloud data according to each first sub-transformation matrix to obtain a plurality of blocked aligned edge tracks; performing curve fitting processing on the plurality of blocked aligned edge tracks to obtain the gluing track.

4. The method of claim 1, wherein, The screening the second initial point cloud data according to the gluing track to obtain second local registration point cloud data comprises: surrounding the second initial point cloud data according to the gluing track in a contour surrounding manner to obtain second initial local registration point cloud data; after projecting the first initial point cloud data to an XY plane of the second local coordinate system, adding all points in the second initial point cloud data with a distance less than a third distance threshold to any point in the gluing track to the second initial local registration point cloud data to obtain the second local registration point cloud data; wherein an X axis and a Y axis of the second local coordinate system are a longest side direction and a second longest side direction of a shoe respectively.

5. The method of claim 1, wherein, The transforming the final template into the third local coordinate system and registering the final template with the third initial point cloud data to obtain a transformed gluing track comprises: calculating a second transformation matrix between the second local registration point cloud data in the final template and the third initial point cloud data; roughly aligning the final template with the third initial point cloud data according to the second transformation matrix to obtain second aligned local registration point cloud data and an aligned track; blocking the second aligned local registration point cloud data, the aligned track and the second initial point cloud data as a whole to obtain a plurality of second sub-aligned local registration point cloud data, a plurality of sub-aligned tracks and a plurality of third sub-initial point cloud data; calculating a second sub-transformation matrix between each second sub-aligned local registration point cloud data and the corresponding second sub-initial point cloud data to obtain a plurality of second sub-transformation matrices; precisely aligning the corresponding sub-aligned track with the corresponding third sub-initial point cloud data according to each second sub-transformation matrix to obtain a plurality of blocked aligned tracks; performing curve fitting processing on the plurality of blocked aligned tracks to obtain the transformed gluing track.

6. The method of claim 1, wherein, The obtaining a glue path track according to the transformed gluing track and the third initial point cloud data comprises: establishing a multi-dimensional tree structure according to the third initial point cloud data; searching for a nearest point to each point in the transformed glue coating track in the multi-dimensional tree structure, replacing the points in the transformed glue coating track with the nearest points respectively, and obtaining the glue path track.

7. The method of claim 1, wherein, The method further comprises: fitting the glue path track in a local straight line fitting manner to obtain a standard glue path track.

8. The method according to claim 1 or 7, characterized in that, The method further comprises: correcting the glue path track or the standard glue path track to obtain a target glue path track.

9. A tread pattern generating device for a shoe sole, characterized by comprising: The device comprises: an acquisition module configured to acquire sole point cloud data, whole shoe point cloud data, and upper point cloud data; a coordinate system construction module configured to construct a first local coordinate system according to the sole point cloud data, transform the sole point cloud data into the first local coordinate system to obtain first initial point cloud data, construct a second local coordinate system according to the whole shoe point cloud data, transform the whole shoe point cloud data into the second local coordinate system to obtain second initial point cloud data, and construct a third local coordinate system according to the upper point cloud data, and transform the upper point cloud data into the third local coordinate system to obtain third initial point cloud data; a processing module configured to process the first initial point cloud data to obtain a sole edge track; a first screening module configured to screen the first initial point cloud data according to the sole edge track to obtain first local registration point cloud data, and use the sole edge track and the first local registration point cloud data as a temporary template; a first registration module configured to transform the temporary template into the second local coordinate system, and register the temporary template with the second initial point cloud data to obtain a glue coating track; a second screening module configured to screen the second initial point cloud data according to the glue coating track to obtain second local registration point cloud data, and use the glue coating track and the second registration point cloud data as a final template; a second registration module configured to transform the final template into the third local coordinate system, register the final template with the third initial point cloud data to obtain a transformed glue coating track, and obtain a glue path track according to the transformed glue coating track and the third initial point cloud data; The processing of the first initial point cloud data to obtain the sole edge track comprises: constructing a straight line passing through the origin of the first local coordinate system in a theta angle direction, and using all points in the first initial point cloud data having a distance less than a first distance threshold from the straight line as slice point cloud in the theta angle, wherein the theta angle is sequentially increased from 0 degrees to 360 degrees at a preset angle step, and slice point cloud in different theta angles is obtained; using the point with the maximum value in the Z-axis direction of the first local coordinate system in each theta angle slice point cloud as a critical point, and obtaining a plurality of critical points, wherein the Z-axis direction is the shortest side direction of the shoe; obtaining the sole edge track according to the plurality of critical points.

Images