Speaker cover adsorption feeding method and device based on image recognition

Abstract

The present application relates to the field of image recognition, and discloses a method and device for adsorption and feeding of a speaker cover based on image recognition, the method comprising: obtaining a speaker cover image of the speaker cover; wherein the speaker cover is provided with a plurality of grilles forming connecting ribs; determining a plurality of grille areas respectively corresponding to the plurality of grilles on the speaker cover in the speaker cover image, and determining the grille azimuth of each grille area relative to the center of the speaker cover image, and obtaining the adsorption head azimuths respectively corresponding to the plurality of adsorption heads of the feeding component; controlling the feeding component to rotate until the plurality of adsorption heads face the plurality of grilles of the speaker cover, and adsorbing the plurality of grilles respectively through the plurality of adsorption heads to feed the speaker cover. The plurality of grilles of the speaker cover intersect at the center of the speaker cover, and the present application realizes vacuum adsorption and feeding of the speaker cover with meshes through image recognition.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and more specifically, to a method and device for adsorption and loading of a loudspeaker cover based on image recognition. Background Art

[0002] In the mass production process of electronic equipment, the loading process of electronic equipment parts is increasingly dependent on efficient and accurate loading systems. In the prior art, when loading and assembling electronic equipment parts, there is a technical solution that uses a camera to capture the image of the electronic equipment parts and then adsorbs and loads the electronic equipment parts. When loading electronic equipment parts, image recognition technology can be used to identify information such as the shape and size of the electronic equipment parts, so that subsequent processing of the electronic equipment parts can be performed. When loading electronic equipment parts, adsorption technology is widely used in the automated loading process, mainly using vacuum suction cups to suck the electronic equipment parts from the storage area and accurately place them in the specified position.

[0003] For example, patent CN113460693B (application number: CN202110814742.8) provides a feeding device for assembling 3C products, which includes a feeding device body, which includes a carrier, an image module, a suction module and a mounting module. A material tray is placed on the carrier, and a plurality of second materials are installed in the material tray. The image module is used to obtain image information of the second material, and the suction module is used to suck and transfer the second material in the material tray. The mounting module includes a first base, a mounting shaft assembly and a first conveying assembly. The mounting shaft assembly is used to mount the second material adsorbed by it on the side wall of the first material. The second material moves to the mounting shaft assembly under the cooperation of the suction module and the image module; the feeding device uses the suction module to suck the second material from the material tray, and cooperates with the mounting module to move the second material to the first suction nozzle matched with it, so as to realize automatic loading of second materials with irregular shapes and improve loading efficiency and loading accuracy. However, during the production process of the speaker, the speaker cover is often provided with a plurality of mesh holes for passing sound waves. Therefore, during the process of adsorbing the speaker cover, the mesh holes on the speaker cover interfere with the vacuum adsorption, making it difficult to adsorb and load the material normally. Summary of the invention

[0004] The purpose of the present application is to provide a method and device for adsorption and feeding of a speaker cover based on image recognition, which solves the technical problem that the mesh holes on the speaker cover interfere with the vacuum adsorption, making it difficult to adsorb and feed the materials normally, and achieves the technical effect of realizing vacuum adsorption and feeding of a speaker cover with mesh holes through image recognition.

[0005] An embodiment of the present application provides a method for adsorption and loading of a speaker cover based on image recognition, the method comprising: obtaining a speaker cover image of the speaker cover; wherein the speaker cover is provided with a plurality of grilles forming connecting ribs; determining a plurality of grille areas respectively corresponding to the plurality of grilles on the speaker cover in the speaker cover image, and determining a grille azimuth angle of each grille area relative to the center of the speaker cover image, and obtaining adsorption head azimuth angles respectively corresponding to a plurality of adsorption heads of a loading component; controlling the loading component to rotate until the plurality of adsorption heads are facing the plurality of grilles of the speaker cover, and loading the speaker cover by adsorbing the plurality of grilles respectively through the plurality of adsorption heads.

[0006] In one possible implementation, multiple grilles of the speaker cover intersect at the center of the speaker cover, and the method further includes: determining the center point of the intersection area of ​​the multiple grille areas, controlling the center points corresponding to the multiple adsorption heads of the loading component to face the center point of the intersection area, controlling the loading component to rotate so that the multiple adsorption heads face the multiple grilles of the speaker cover, and using the multiple adsorption heads to respectively adsorb the multiple grilles to load the speaker cover.

[0007] In another possible implementation, the method also includes: when the angles between the multiple grilles on the speaker cover are equal, determining the grille angles between the multiple grilles on the speaker cover; when feeding the speaker cover by adsorbing the multiple grilles separately by multiple adsorption heads fails, controlling the multiple adsorption heads of the feeding assembly to rotate the grille angles around the centers of the multiple adsorption heads, and again adsorbing the multiple grilles separately by the multiple adsorption heads to feed the speaker cover.

[0008] In another possible implementation, the method also includes: when loading the speaker cover by respectively adsorbing the multiple grilles through multiple adsorption heads fails, controlling the multiple adsorption heads of the loading assembly to rotate around the centers of the multiple adsorption heads at a first angle in a first direction, and again using the multiple adsorption heads to respectively adsorb the multiple grilles to load the speaker cover; when loading fails after controlling the multiple adsorption heads of the loading assembly to rotate around the centers of the multiple adsorption heads at a first angle in a first direction, controlling the multiple adsorption heads of the loading assembly to rotate around the centers of the multiple adsorption heads at a second angle in the opposite direction of the first direction, and again using the multiple adsorption heads to respectively adsorb the multiple grilles to load the speaker cover; wherein the first angle is 1° to 5°, and the second angle is 1.5 times to 2.5 times the first angle.

[0009] In another possible implementation, the method also includes: controlling multiple adsorption heads of the loading assembly to rotate a second angle in the opposite direction of the first direction, and when the adsorption of multiple grilles by the multiple adsorption heads again fails to load the speaker cover, skipping the adsorption and loading process of the current speaker cover, and carrying out the adsorption and loading of the next speaker cover.

[0010] In another possible implementation, the speaker cover is arranged in the material cavity of the loading tray during loading, and the method also includes: obtaining a speaker cover image including the speaker cover and the loading tray, determining the material cavity contour of the material cavity in the speaker cover image, and determining the cover contour of the speaker cover in the speaker cover image, and determining the obstructed material cavity contour length obscured by the cover contour, and obtaining the material cavity depth of the material cavity; when the obstructed material cavity contour length is greater than a preset obstructed material cavity contour length, and when the material cavity depth is greater than a preset material cavity depth, skipping the adsorption and loading process of the current speaker cover, and performing adsorption and loading of the next speaker cover; when the obstructed material cavity contour length is greater than the preset obstructed material cavity contour length, and when the material cavity depth is less than the preset material cavity depth, not skipping the adsorption and loading process of the current speaker cover.

[0011] An embodiment of the present application also provides a speaker cover adsorption and loading device based on image recognition, comprising a unit for executing any of the methods described above.

[0012] An embodiment of the present application also provides a speaker cover adsorption and loading device based on image recognition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0013] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0014] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of any of the methods described above when executed by a processor.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0016] The embodiment of the present application provides a method for adsorption and feeding of a speaker cover based on image recognition, the method comprising: obtaining a speaker cover image of the speaker cover; wherein the speaker cover is provided with a plurality of grilles forming connecting ribs; determining a plurality of grille areas respectively corresponding to the plurality of grilles on the speaker cover in the speaker cover image, and determining the grille azimuth of each grille area relative to the center of the speaker cover image, and obtaining the adsorption head azimuths respectively corresponding to the plurality of adsorption heads of the feeding component; controlling the feeding component to rotate until the plurality of adsorption heads are facing the plurality of grilles of the speaker cover, and adsorbing the plurality of grilles respectively through the plurality of adsorption heads to feed the speaker cover. The method in the embodiment of the present application can identify the grille area in the speaker cover image, and adsorb and feed the speaker cover by adsorbing the grille area, and can eliminate the interference of the mesh on the speaker cover with the vacuum adsorption feeding, thereby realizing the efficient adsorption and feeding of the speaker cover and improving the efficiency of the speaker cover feeding. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 A schematic diagram of a flow chart of a method for adsorbing and loading a loudspeaker cover based on image recognition provided in an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of a top view of a speaker cover adsorption and feeding device based on image recognition in an embodiment of the present application;

[0020] Figure 3 This is a schematic diagram of the bottom-up structure of an adsorption head in an embodiment of the present application;

[0021] Figure 4 This is a schematic diagram of the main structure of an adsorption head in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of a speaker cover image provided in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of another speaker cover image provided in an embodiment of the present application;

[0024] Figure 7 A schematic diagram of the structure of a speaker cover and a material tray provided in an embodiment of the present application;

[0025] Figure 8It is a schematic diagram of the partial structure of an adsorption head in an embodiment of the present application;

[0026] Fig. 9 A schematic diagram of the logical structure of a speaker cover adsorption and feeding device based on image recognition provided in an embodiment of the present application;

[0027] Fig.10 A schematic diagram of the physical structure of a speaker cover adsorption and loading device based on image recognition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] During the production process of speakers, the speaker cover is often provided with a plurality of mesh holes for passing sound waves. Therefore, during the process of adsorbing the speaker cover, the mesh holes on the speaker cover interfere with the vacuum adsorption, making it difficult to adsorb and load the material normally.

[0034] Based on the above reasons, the embodiment of the present application provides a method for adsorption and loading of a speaker cover based on image recognition, the method comprising: obtaining a speaker cover image of the speaker cover; wherein the speaker cover is provided with a plurality of grilles forming connecting ribs; determining a plurality of grille areas corresponding to the plurality of grilles on the speaker cover in the speaker cover image, and determining the grille azimuth of each grille area relative to the center of the speaker cover image, and obtaining the adsorption head azimuths corresponding to the plurality of adsorption heads of the loading assembly; controlling the loading assembly to rotate until the plurality of adsorption heads are facing the plurality of grilles of the speaker cover, and loading the speaker cover by adsorbing the plurality of grilles respectively through the plurality of adsorption heads. The method in the embodiment of the present application can identify the grille area in the speaker cover image, and adsorb and load the speaker cover by adsorbing the grille area, and can eliminate the interference of the mesh on the speaker cover with the vacuum adsorption loading, thereby realizing the efficient adsorption loading of the speaker cover and improving the efficiency of the speaker cover loading.

[0035] In some scenarios, a speaker cover adsorption and feeding method based on image recognition in an embodiment of the present application can be applied to the feeding of the speaker cover, which can eliminate the adsorption and feeding effect of the speaker cover and improve the feeding efficiency of the speaker cover.

[0036] The following is a detailed description of a speaker cover adsorption and loading method based on image recognition provided in an embodiment of the present application with reference to specific examples.

[0037] Figure 1 A schematic diagram of a flow chart of a speaker cover adsorption and loading method based on image recognition provided in an embodiment of the present application, such as Figure 1 As shown, the method includes S110 to S130, and S110 to S130 are described in detail below.

[0038] S110, obtaining a speaker cover image 2 of the speaker cover 1. The speaker cover 1 is provided with a plurality of grilles 11 forming connecting ribs.

[0039] Figure 2 A schematic diagram of a top view of a speaker cover adsorption and feeding device based on image recognition provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the speaker cover adsorption and feeding device based on image recognition used in the present method includes a feeding component 3 and an adsorption head 31. The adsorption head 31 is arranged on the feeding component 3. The adsorption head 31 can be raised and lowered and can be rotated in a horizontal plane to realize the adsorption and feeding of the speaker cover 1.

[0040] Structurally, a conveyor belt is provided on one side of the adsorption head 31, and the conveyor belt conveys the speaker cover 1 in a conveying direction.

[0041] Structurally, a shooting component is provided on the adsorption head 31 , and the adsorption head 31 can obtain an image of the speaker cover 1 through the shooting component, so as to facilitate the identification and adsorption of the speaker cover 1 .

[0042] When loading the speaker cover, the method first obtains the speaker cover image 2 of the speaker cover 1 so as to facilitate identification through the speaker cover image 2 and to facilitate adsorption of the speaker cover 1.

[0043] Figure 5 A schematic diagram of a speaker cover image provided in an embodiment of the present application, such as Figure 2 and Figure 5 As shown, the speaker cover 1 is provided with a plurality of grilles 11 forming connecting ribs, and the plurality of grilles 11 correspond to the grille area 21 in the speaker cover image 2. When the speaker cover is adsorbed and loaded, the mesh holes on the speaker cover make it impossible to form a vacuum environment in the mesh hole area. Since the speaker cover has no mesh holes in the area where the grilles 11 are located, a vacuum environment can be formed in the area where the grilles 11 of the speaker cover are located, so that the speaker cover 1 can be loaded by adsorbing the grilles 11.

[0044] S120. Determine in the speaker cover image 2 the multiple grille areas 21 corresponding to the multiple grilles 11 on the speaker cover 1, determine the grille azimuth of each grille area 21 relative to the center of the speaker cover image 2, and obtain the adsorption head azimuths corresponding to the multiple adsorption heads 31 of the loading component 3.

[0045] like Figure 2 and Figure 5 As shown, the method in the embodiment of the present application can first determine in the speaker cover image 2 a plurality of grille areas 21 respectively corresponding to the plurality of grilles 11 on the speaker cover 1, the grille area 21 being the area where the grille 11 is located, and then can realize the adsorption and loading of the speaker cover 1 by adsorbing the grilles 11 corresponding to the grille area 21.

[0046] After the grille area 21 is identified, the grille azimuth of each grille area 21 relative to the center of the speaker cover image 2 can be further determined so that the adsorption head can be rotated according to the grille azimuth to achieve adsorption of the speaker cover.

[0047] For example, Figure 5As shown, the grille azimuth angle of each grille area 21 relative to the center of the speaker cover image 2 may be a grille azimuth angle α, so that the grille area 21 can be positioned by the grille azimuth angle α.

[0048] When identifying each grid region 21 and the grid azimuth angle α, the grid region 21 may be identified by an image key point recognition algorithm, and the grid azimuth angle α may be calculated by the boundary of the grid region 21 .

[0049] When adsorbing the speaker cover, the adsorption head azimuth angles corresponding to the multiple adsorption heads 31 of the loading component 3 can also be obtained. The adsorption head azimuth angles represent the positions of the multiple adsorption heads 31 of the loading component 3, and then the positions of the multiple adsorption heads 31 of the loading component 3 can be adjusted to adsorb the speaker cover.

[0050] Figure 3 : is a schematic diagram of the structure of an adsorption head in an embodiment of the present application from a bottom view, Figure 4 Schematic diagram of the main structure of an adsorption head in an embodiment of the present application, such as Figure 3 and Figure 4 As shown, the adsorption head azimuth angles corresponding to the multiple adsorption heads 31 can be the adsorption head azimuth angle γ, and the adsorption head azimuth angle γ can be used to characterize the positions of the multiple adsorption heads 31.

[0051] S130, control the feeding assembly 3 to rotate until the multiple adsorption heads 31 are facing the multiple grilles 11 of the speaker cover 1, and use the multiple adsorption heads 31 to respectively adsorb the multiple grilles 11 to feed the speaker cover 1.

[0052] When adsorbing the speaker cover 1, since the adsorption head azimuth angles γ corresponding to the multiple adsorption heads 31 of the loading component 3 and the grille azimuth angle α of the center of the speaker cover image 2 have been obtained, the loading component 3 can be controlled to rotate until the multiple adsorption heads 31 are facing the multiple grilles 11 of the speaker cover 1, so that the adsorption heads 31 can adsorb the grilles 11, thereby realizing the loading of the speaker cover 1 by respectively adsorbing the multiple grilles 11 by the multiple adsorption heads 31.

[0053] Exemplarily, when controlling the multiple adsorption heads 31 to rotate to face the multiple grilles 11 of the speaker cover 1, the rotation angles that the multiple adsorption heads 31 need to rotate can be calculated by the adsorption head azimuth angle γ and the grille azimuth angle α, and the multiple adsorption heads 31 can be controlled to rotate to face the multiple grilles 11 of the speaker cover 1 according to the rotation angles.

[0054] The beneficial effect brought about by the above-mentioned implementation method is that it can eliminate the interference of the mesh holes on the speaker cover body with the vacuum adsorption and loading, thereby realizing the efficient adsorption and loading of the speaker cover body.

[0055] The beneficial effect brought about by the above-mentioned implementation method is that by identifying each grille area and grille azimuth angle, and being able to control the adsorption head to rotate to multiple grilles facing the speaker cover, it is convenient to realize the adsorption and loading of the speaker cover.

[0056] In some implementations, the multiple grilles 11 of the speaker cover 1 intersect at the center of the speaker cover 1, and the method further includes: determining the center point of the intersection area 211 of the multiple grille areas 21, controlling the corresponding center points of the multiple adsorption heads 31 of the loading component 3 to face the center point of the intersection area 211, controlling the loading component 3 to rotate so that the multiple adsorption heads 31 face the multiple grilles 11 of the speaker cover 1, and respectively adsorbing the multiple grilles 11 through the multiple adsorption heads 31 to load the speaker cover 1.

[0057] like Figure 2 and Figure 5 As shown, the multiple grilles 11 of the speaker cover 1 intersect at the center of the speaker cover 1, so that the speaker cover 1 can be positioned through the center of the speaker cover 1 to achieve adsorption and loading of the speaker cover 1.

[0058] When the speaker cover 1 is adsorbed, the center point of the intersection area 211 of the multiple grille areas 21 can be determined, and then the corresponding center points of the multiple adsorption heads 31 of the loading component 3 can be controlled to face the center point of the intersection area 211, so that the centers of the multiple adsorption heads 31 can be positioned. The loading component 3 can be further controlled to rotate until the multiple adsorption heads 31 face the multiple grilles 11 of the speaker cover 1, and the multiple grilles 11 can be adsorbed by the multiple adsorption heads 31 respectively to feed the speaker cover 1, thereby achieving adsorption and feeding of the speaker cover 1.

[0059] Exemplarily, when determining the center point of the intersection region 211 of the plurality of grid regions 21 , the intersection region 211 may be quickly determined by a key point recognition algorithm, and the center point of the intersection region 211 may be further calculated.

[0060] The beneficial effect brought about by the above-mentioned implementation method is that by first determining the center point of the intersection area, it is convenient to control the center points corresponding to the multiple adsorption heads of the loading assembly to face the center point of the intersection area, thereby facilitating the loading of the speaker cover and improving the efficiency of loading the speaker cover.

[0061] In some implementations, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0062] S210. When the included angles between the multiple grilles 11 on the speaker cover 1 are equal, determine the grille included angles between the multiple grilles 11 on the speaker cover 1.

[0063] like Figure 2 and Figure 5 As shown, when the speaker cover 1 is subjected to adsorption and loading, the adsorption and loading of the speaker cover 1 may often fail, so it is possible to try to repeat the adsorption and loading of the speaker cover 1 that has failed.

[0064] During operation, when the angles between the multiple grilles 11 on the speaker cover 1 are equal, the grille angles between the multiple grilles 11 on the speaker cover 1 can be determined, and the grille angles can be used to control the re-attempt of adsorption and loading of the speaker cover that failed in adsorption and loading.

[0065] like Figure 5 As shown, the grille angle between the multiple grilles 11 on the speaker cover 1 can be a grille angle β.

[0066] S220. When the multiple adsorption heads 31 fail to respectively adsorb the multiple grilles 11 to feed the speaker cover 1, control the multiple adsorption heads 31 of the feeding assembly 3 to rotate the grille angle around the center of the multiple adsorption heads 31, and again use the multiple adsorption heads 31 to respectively adsorb the multiple grilles 11 to feed the speaker cover 1.

[0067] When the speaker cover 1 fails to be fed by adsorbing the multiple grilles 11 respectively by the multiple adsorption heads 31, an attempt can be made to adsorb and feed the speaker cover 1 on which the adsorption and feeding failed again, and the multiple adsorption heads 31 of the feeding assembly 3 can be controlled to rotate the grille angles so as to attempt to adsorb the grilles 11 at other azimuth angles by the multiple adsorption heads 31, thereby achieving the goal of feeding the speaker cover 1 by adsorbing the multiple grilles 11 respectively by the multiple adsorption heads 31 again.

[0068] Exemplarily, when the speaker cover 1 has a tilt angle, feeding the speaker cover 1 by respectively adsorbing the multiple grilles 11 through the multiple adsorption heads 31 may fail. Therefore, the multiple adsorption heads 31 of the feeding assembly 3 can be controlled to rotate the grille angle so that the multiple adsorption heads 31 avoid the maximum tilt angle of the speaker cover 1 after rotation, thereby achieving effective adsorption of the speaker cover 1.

[0069] The beneficial effect brought about by the above-mentioned implementation method is that when multiple adsorption heads fail to adsorb multiple grilles to feed the speaker cover, the multiple adsorption heads of the feeding assembly can be controlled to rotate the grille angles, and the multiple adsorption heads try to adsorb grilles at other azimuth angles, thereby effectively adsorbing and feeding the speaker cover.

[0070] The beneficial effect brought about by the above-mentioned implementation method is that when the speaker cover has an inclination angle, the multiple adsorption heads rotate to avoid the maximum inclination angle of the speaker cover, thereby achieving effective adsorption of the speaker cover.

[0071] In some implementations, the above method further includes: when the multiple adsorption heads 31 fail to respectively adsorb the multiple grilles 11 to feed the speaker cover 1, the multiple adsorption heads 31 of the feeding component 3 are controlled to rotate around the center of the multiple adsorption heads 31 by a first angle in a first direction, and the multiple adsorption heads 31 are again used to respectively adsorb the multiple grilles 11 to feed the speaker cover 1. When the multiple adsorption heads 31 of the feeding component 3 fail to feed after being controlled to rotate around the center of the multiple adsorption heads 31 by a first angle in a first direction, the multiple adsorption heads 31 of the feeding component 3 are controlled to rotate around the center of the multiple adsorption heads 31 by a second angle in the opposite direction of the first direction, and the multiple adsorption heads 31 are again used to respectively adsorb the multiple grilles 11 to feed the speaker cover 1. The first angle is 1° to 5°, and the second angle is 1.5 times to 2.5 times the first angle.

[0072] When trying to re-adsorb and feed the speaker cover, if the multiple grilles 11 on the speaker cover 1 cannot be adsorbed respectively by the multiple adsorption heads 31, it indicates that the adsorption of the speaker cover may fail due to the misalignment of the grilles on the speaker cover and the adsorption heads. At this time, the multiple adsorption heads 31 of the feeding assembly 3 can be controlled to rotate at a first angle in a first direction around the center of the multiple adsorption heads 31 to avoid the misaligned area between the grilles on the speaker cover and the adsorption heads, and then the multiple grilles 11 on the speaker cover 1 can be adsorbed respectively by the multiple adsorption heads 31 again to achieve effective feeding of the speaker cover 1.

[0073] Exemplarily, the first angle may be 1° to 5°.

[0074] When trying to re-adsorb and feed the speaker cover, if feeding fails after controlling the multiple adsorption heads 31 of the feeding component 3 to rotate around the centers of the multiple adsorption heads 31 according to the first direction at a first angle, it means that after the multiple adsorption heads 31 are rotated around the centers of the multiple adsorption heads 31 according to the first direction at a first angle, the grilles and the adsorption head misalignment area on the speaker cover are still not effectively avoided. The multiple adsorption heads 31 of the feeding component 3 can be further controlled to rotate around the centers of the multiple adsorption heads 31 according to the second angle in the opposite direction of the first direction, and then the speaker cover can be tried again to be adsorbed and fed in the opposite direction of the first direction, and the multiple grilles 11 can be adsorbed by the multiple adsorption heads 31 again to feed the speaker cover 1.

[0075] Exemplarily, the second angle may be 1.5 to 2.5 times the first angle.

[0076] Exemplarily, after combining the above-mentioned S210 to S220 to avoid the tilt angle of the speaker cover, the multiple adsorption heads 31 of the loading assembly 3 can be further controlled according to the above-mentioned method to rotate around the center of the multiple adsorption heads 31 in a first direction by a first angle to load the materials, or the multiple adsorption heads 31 can be controlled to rotate in the opposite direction of the first direction to adsorb and load the materials, thereby achieving effective loading of the speaker cover.

[0077] The beneficial effect brought about by the above-mentioned implementation method is that when the grille and the adsorption head on the speaker cover are misaligned, resulting in failure of adsorption of the speaker cover, the multiple adsorption heads of the feeding assembly can be controlled to rotate in a first direction around the center of the multiple adsorption heads at a first angle to avoid misalignment of the grille and the adsorption head, thereby improving the adsorption and feeding effect of the speaker cover.

[0078] The beneficial effect brought about by the above-mentioned implementation method is that after the multiple adsorption heads are rotated by a first angle in a first direction around the center of the multiple adsorption heads, when the grille and the adsorption head misalignment area on the speaker cover are still not effectively avoided, the multiple adsorption heads 31 of the feeding assembly 3 are controlled to rotate by a second angle in the opposite direction of the first direction around the center of the multiple adsorption heads 31, which can further attempt to avoid the misalignment of the grille and the adsorption head, thereby improving the adsorption and feeding effect on the speaker cover.

[0079] In some implementations, the above method also includes: controlling the multiple adsorption heads 31 of the loading assembly 3 to rotate a second angle in the opposite direction of the first direction, and when the multiple adsorption heads 31 fail to respectively adsorb the multiple grilles 11 to load the speaker cover 1 again, skipping the adsorption and loading process of the current speaker cover 1, and carrying out the adsorption and loading of the next speaker cover 1.

[0080] When adsorbing and feeding the speaker cover, the multiple adsorption heads 31 of the feeding assembly 3 are controlled to rotate at a second angle in the opposite direction of the first direction. When the multiple adsorption heads 31 respectively adsorb the multiple grilles 11 to feed the speaker cover 1 again and fail, it means that the misalignment of the grilles and the adsorption heads has not been avoided. The adsorption and feeding process of the current speaker cover 1 can be skipped, and the adsorption and feeding of the next speaker cover 1 can be carried out, thereby ensuring the continuity of the feeding of the speaker cover.

[0081] The beneficial effect brought about by the above-mentioned implementation method is that when controlling multiple adsorption heads to rotate in the first direction or in the second direction still fails to avoid misalignment of the grille and the adsorption heads, the adsorption and loading process of the current speaker cover can be skipped, thereby ensuring the continuity of the adsorption and loading process of the speaker cover.

[0082] In some implementations, the speaker cover 1 is disposed in the material cavity 41 of the loading tray 4 during loading, and the above method further includes S310 to S320, which will be described in detail below.

[0083] S310, obtain the speaker cover image 2 including the speaker cover 1 and the material tray 4, determine the material cavity contour 411 of the material cavity 41 in the speaker cover image 2, determine the cover contour 22 of the speaker cover 1 in the speaker cover image 2, determine the length of the material cavity contour 411 obscured by the cover contour 22, and obtain the material cavity depth of the material cavity 41.

[0084] When the speaker cover 1 is loaded, the speaker cover 1 is generally placed in a material tray 4 for loading. In order to improve the loading effect when the speaker cover 1 is placed in the material tray 4, the image of the speaker cover 1 in the material tray 4 can be identified to improve the loading effect.

[0085] Figure 6 A schematic diagram of another speaker cover image provided in an embodiment of the present application, Figure 7 A schematic diagram of the structure of a speaker cover and a material tray provided in an embodiment of the present application, such as Figure 6 and Figure 7 As shown, a speaker cover image 2 including the speaker cover 1 and the material tray 4 can be obtained. After obtaining the speaker cover image 2 including the speaker cover 1 and the material tray 4, a material cavity contour 411 of the material cavity 41 can be determined in the speaker cover image 2, and the material cavity contour 411 is the position of the material cavity 41 on the material tray 4. A cover contour 22 of the speaker cover 1 can be determined in the speaker cover image 2, and the cover contour 22 is the position of the speaker cover 1.

[0086] After obtaining the material cavity contour 411 obstructed by the cover body contour 22, the length of the obstructed material cavity contour 411 obstructed by the cover body contour 22 can be determined, so as to evaluate the boundary range of the speaker cover 1 exceeding the material cavity contour 411 according to the obstructed material cavity contour length. The degree to which the speaker cover 1 slides out of the material cavity 41 can be evaluated by the boundary range of the speaker cover 1 exceeding the material cavity contour 411. When the degree to which the speaker cover 1 slides out of the material cavity 41 is too great, the speaker cover 1 will tilt too greatly due to the support of the material cavity 41 when sliding out of the material cavity 41, which may lead to the failure of adsorption and loading of the speaker cover 1.

[0087] When evaluating the loading process, the depth of the material cavity 41 can be obtained. When the depth of the material cavity increases, the speaker cover 1 will slide out of the material cavity 41 and the support of the material cavity 41 will cause the inclination of the speaker cover 1 to increase. Then, the success rate of the loading process of adsorbing and loading the speaker cover 1 can be evaluated based on the depth of the material cavity 41.

[0088] S320: When the length of the shielding cavity outline is greater than the preset shielding cavity outline length, and when the cavity depth is greater than the preset cavity depth, skip the adsorption and loading process of the current speaker cover 1, and proceed to the adsorption and loading of the next speaker cover 1. When the length of the shielding cavity outline is greater than the preset shielding cavity outline length, and when the cavity depth is less than the preset cavity depth, do not skip the adsorption and loading process of the current speaker cover 1.

[0089] When evaluating the success rate of adsorption and feeding, when the length of the blocked material cavity contour is greater than the preset blocked material cavity contour length, it means that the length of the speaker cover 1 sliding out of the material cavity 41 is large, and when the material cavity depth is greater than the preset material cavity depth, it means that when the speaker cover 1 slides out of the material cavity 41 to a certain extent and the material cavity depth is large, the inclination angle of the speaker cover 1 may be too large, indicating that the adsorption success rate of the speaker cover 1 corresponding to the currently recognized speaker cover image 11 is small, and then the adsorption and feeding process of the current speaker cover 1 can be skipped, and the adsorption and feeding process of the next speaker cover 1 can be carried out.

[0090] When evaluating the success rate of adsorption and feeding, when the length of the blocked material cavity contour is greater than the preset blocked material cavity contour length, it means that the speaker cover 1 has slid out of the material cavity 41 to a certain extent and the material cavity depth is large, which may cause the inclination angle of the speaker cover 1 to be too large, and when the material cavity depth is less than the preset material cavity depth, it means that the speaker cover 1 has slid out of the material cavity 41 to a certain extent but the material cavity depth is not large, and the inclination angle of the speaker cover 1 is not large, indicating that the adsorption success rate of the speaker cover 1 corresponding to the currently recognized speaker cover image 2 is relatively large, and the adsorption and feeding process of the current speaker cover 1 can be skipped to achieve effective feeding of the speaker cover 1.

[0091] Exemplarily, the preset shielding cavity contour length may be 1 / 4 to 1 / 3 of the cavity contour length.

[0092] Exemplarily, the preset material cavity depth may be determined by empirical values ​​corresponding to the preset material cavity depth and the preset shielding material cavity contour length, and the preset material cavity depth may be 1 cm to 2 cm.

[0093] The beneficial effect brought about by the above-mentioned implementation method is that when the speaker cover slides out of the material cavity to a certain extent and the depth of the material cavity is large, which may cause the speaker cover to tilt at a too large angle, the adsorption and loading process of the current speaker cover can be skipped and the adsorption and loading of the next speaker cover can be carried out to improve the adsorption and loading efficiency.

[0094] The beneficial effect brought about by the above-mentioned implementation method is that when the speaker cover slides out of the material cavity to a certain extent and the depth of the material cavity is large, which may cause the speaker cover to tilt at a too large angle, the adsorption and loading process of the current speaker cover is skipped, which can avoid the speaker cover being squeezed and deformed by the adsorption head and causing damage to the speaker cover, thereby improving the use effect of the speaker cover.

[0095] The beneficial effect brought about by the above-mentioned implementation method is that when the speaker cover slides out of the material cavity to a certain extent and the depth of the material cavity is small, which will not cause the tilt angle of the speaker cover to be too large, the adsorption and loading process of the current speaker cover can be carried out without skipping, so as to improve the adsorption and loading efficiency.

[0096] In some implementations, a plurality of adsorption heads 31 are provided with soft rubber heads 311 , and the tilting angle of the soft rubber heads 311 when adsorbing materials is greater than the minimum tilting angle when the speaker cover 1 slides out of the material cavity 41 .

[0097] Figure 8 is a schematic diagram of a partial structure of an adsorption head in an embodiment of the present application, such as Figure 8 As shown, a plurality of adsorption heads 31 are provided with soft rubber heads 311 , and the soft rubber heads 311 can be deformed when adsorbing the speaker cover 1 , so that the soft rubber heads 311 can adapt to a certain degree of inclination of the speaker cover 1 .

[0098] Structurally, the tilting angle of the soft rubber head 311 when adsorbing the material is greater than the minimum tilting angle when the speaker cover 1 slides out of the material cavity 41, so that the soft rubber head 311 can adapt to the minimum tilting angle when the speaker cover 1 slides out of the material cavity 41, so as to be able to adsorb the speaker cover 1 when the speaker cover 1 slides out of the material cavity 41.

[0099] Exemplarily, the minimum tilt angle of the speaker cover 1 when sliding out of the material cavity 41 can be 3° to 5°.

[0100] The beneficial effect brought about by the above-mentioned implementation method is that the soft rubber head can adapt to the minimum tilt angle when the speaker cover slides out of the material cavity, so as to be able to adsorb the speaker cover when the speaker cover slides out of the material cavity.

[0101] An embodiment of the present application also provides a speaker cover adsorption and loading device based on image recognition, comprising a unit for executing any of the methods described above.

[0102] Fig. 9 A schematic diagram of the logical structure of a speaker cover adsorption feeding device based on image recognition provided in an embodiment of the present application is shown in FIG. Fig. 9As shown, the device 5 of this embodiment includes a processing unit 51, a storage unit 52 and a transceiver unit 53. The processing unit 51 is used to process data, the storage unit 52 is used to store data, and the transceiver unit 53 is used to send and receive data. The processing unit 51, the storage unit 52 and the transceiver unit 53 cooperate with each other to implement the above method. The beneficial effects brought by the embodiment of the present application have been described in the above method and will not be repeated here.

[0103] An embodiment of the present application also provides a speaker cover adsorption and loading device based on image recognition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0104] Fig.10 A schematic diagram of the physical structure of a speaker cover adsorption and feeding device based on image recognition provided in one embodiment of the present application, such as Fig.10 As shown, the device 6 of this embodiment includes: at least one processor 60 ( Fig.10 Only one processor 60 is shown in the figure), a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the steps in any of the above-mentioned method embodiments are implemented. The beneficial effects brought about by the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0105] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0106] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0107] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0108] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0110] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for adsorbing and loading a loudspeaker cover based on image recognition, characterized in that: The method comprises: obtaining a speaker cover image (2) of a speaker cover (1); wherein the speaker cover (1) is provided with a plurality of grilles (11) forming connecting ribs; determining a plurality of grille areas (21) corresponding to the plurality of grilles (11) on the speaker cover (1) in the speaker cover image (2), determining a grille azimuth angle of each grille area (21) relative to the center of the speaker cover image (2), and obtaining adsorption head azimuth angles corresponding to a plurality of adsorption heads (31) of a feeding component (3); controlling the feeding component (3) to rotate so that the plurality of adsorption heads (31) face the plurality of grilles (11) of the speaker cover (1), and feeding the speaker cover (1) by adsorbing the plurality of grilles (11) respectively through the plurality of adsorption heads (31); The plurality of grilles (11) of the speaker cover (1) intersect at the center of the speaker cover (1), and the method further comprises: determining the center point of the intersection area (211) of the plurality of grille areas (21), controlling the corresponding center points of the plurality of adsorption heads (31) of the loading component (3) to face the center point of the intersection area (211), controlling the loading component (3) to rotate so that the plurality of adsorption heads (31) face the plurality of grilles (11) of the speaker cover (1), and loading the speaker cover (1) by adsorbing the plurality of grilles (11) respectively through the plurality of adsorption heads (31); The method further comprises: when the angles between the multiple grilles (11) on the speaker cover (1) are equal, determining the grille angles between the multiple grilles (11) on the speaker cover (1); when the multiple adsorption heads (31) fail to feed the speaker cover (1) by adsorbing the multiple grilles (11) respectively, controlling the multiple adsorption heads (31) of the feeding assembly (3) to rotate the grille angles around the center of the multiple adsorption heads (31), and again adsorbing the multiple grilles (11) respectively by the multiple adsorption heads (31) to feed the speaker cover (1).

2. The method according to claim 1, characterized in that The method further comprises: when the multiple adsorption heads (31) fail to respectively adsorb the multiple grilles (11) to feed the speaker cover (1), controlling the multiple adsorption heads (31) of the feeding component (3) to rotate around the center of the multiple adsorption heads (31) by a first angle in a first direction, and again using the multiple adsorption heads (31) to respectively adsorb the multiple grilles (11) to feed the speaker cover (1); when the multiple adsorption heads (31) of the feeding component (3) fail to feed after being controlled to rotate around the center of the multiple adsorption heads (31) by a first angle in a first direction, controlling the multiple adsorption heads (31) of the feeding component (3) to rotate around the center of the multiple adsorption heads (31) by a second angle in a direction opposite to the first direction, and again using the multiple adsorption heads (31) to respectively adsorb the multiple grilles (11) to feed the speaker cover (1); wherein the first angle is 1° to 5°, and the second angle is 1.5 times to 2.5 times the first angle.

3. The method according to claim 2, characterized in that The method further comprises: controlling the plurality of adsorption heads (31) of the loading assembly (3) to rotate at a second angle in the opposite direction to the first direction, and when the plurality of adsorption heads (31) respectively adsorb the plurality of grilles (11) to load the speaker cover (1) again fails, skipping the adsorption loading process for the current speaker cover (1) and carrying out the adsorption loading for the next speaker cover (1).

4. The method according to claim 3, characterized in that The speaker cover (1) is arranged in a material cavity (41) of a loading tray (4) during loading, and the method further comprises: obtaining a speaker cover image (2) including the speaker cover (1) and the loading tray (4), determining a material cavity contour (411) of the material cavity (41) in the speaker cover image (2), determining a cover contour (22) of the speaker cover (1) in the speaker cover image (2), determining a length of a blocked material cavity contour of the material cavity contour (411) blocked by the cover contour (22), and obtaining a material cavity depth of the material cavity (41); when the blocked material cavity contour length is greater than a preset blocked material cavity contour length, and when the material cavity depth is greater than a preset material cavity depth, skipping the adsorption loading process of the current speaker cover (1), and performing adsorption loading of the next speaker cover (1); when the blocked material cavity contour length is greater than a preset blocked material cavity contour length, and when the material cavity depth is less than a preset material cavity depth, not skipping the adsorption loading process of the current speaker cover (1).

5. A speaker cover adsorption and feeding device based on image recognition, characterized in that: The method comprises means for performing the method according to any one of claims 1 to 4.

6. A speaker cover adsorption and feeding device based on image recognition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images