Earphone sound outlet positioning method and system, computer device and storage medium

Abstract

The application provides an earphone sound outlet positioning method and system, a computer device and a storage medium. The method comprises the following steps: acquiring ear key point identification parameters; performing point position processing on the ear key point identification parameters and preset target parameters to obtain a key point position difference; and sending a positioning signal to an earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be directly opposite to the ear canal center. After the key points of the ear are determined, the shape of the ear is determined, and then the ear key point identification parameters are compared with the preset target parameters to determine the position deviation degree of the key points of the ear, that is, the key point position difference. Finally, a corresponding positioning signal is sent according to the difference degree of the key point position difference to adjust the structure of the earphone, so that the position of the earphone sound outlet changes to be directly opposite to the ear canal center, thereby effectively improving the direct opposite degree of the earphone sound outlet and the ear canal center.

Description

TECHNICAL FIELD

[0001] The present application relates to the earphone technical field, in particular to an earphone sound outlet positioning method and system, a computer device and a storage medium. BACKGROUND

[0002] Traditional in-ear or semi-in-ear air conduction earphones have a feeling of being blocked and pressed all the time, especially when worn for a long time, which can easily cause discomfort. However, the sound quality of traditional bone conduction earphones cannot be compared with that of air conduction earphones, so a new type of open earphone with air conduction has appeared on the market, especially a near-ear open earphone with a speaker close to the ear canal.

[0003] However, everyone's ear shape and size is different, and the frequency response of the traditional near-ear open earphone is closely related to the distance and angle of the earphone sound outlet to the center of the ear canal. In addition, some near-ear open earphones also use a front sound outlet plus a rear sound outlet design. Due to the acoustic characteristics similar to acoustic dipoles, the distance and angle of the front and rear sound outlets to the center of the ear canal further affect the frequency response and sound directivity, resulting in the problem that the earphone sound outlet cannot be aligned with the center of everyone's ear canal all the time. SUMMARY

[0004] The purpose of the present application is to overcome the shortcomings of the prior art and provide an earphone sound outlet positioning method, system, computer device and storage medium that effectively improve the alignment of the earphone sound outlet with the center of the ear canal.

[0005] The purpose of the present application is achieved by the following technical solutions:

[0006] An earphone sound outlet positioning method, the method comprising:

[0007] obtaining ear key point recognition parameters;

[0008] performing point position processing on the ear key point recognition parameters and preset target parameters to obtain key point position difference;

[0009] sending a positioning signal to an earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be aligned with the center of the ear canal;

[0010] The point position processing of the ear key point recognition parameters and the preset target parameters to obtain the key point position difference comprises:

[0011] obtaining a single-axis displacement of the distance between at least two ear key points;

[0012] obtaining a difference between the single-axis displacement and the preset orientation value to obtain an ear sound outlet offset difference corresponding to all key points.

[0013] In one of the embodiments, the point position processing of the ear key point recognition parameter and the preset target parameter to obtain the key point position difference includes: performing clustering analysis operation on the distance and the connecting line of each ear key point to obtain ear hanging model output; and the sending of the positioning signal to the earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be opposite to the ear canal center includes: outputting the corresponding ear hanging model according to the ear hanging model output.

[0014] In one of the embodiments, the point position processing of the ear key point recognition parameter and the preset target parameter to obtain the key point position difference includes: performing clustering analysis operation on the distance and the connecting line of each ear key point to obtain ear hanging model output; and the sending of the positioning signal to the earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be opposite to the ear canal center includes: outputting the corresponding ear hanging model according to the ear hanging model output.

[0015] In one of the embodiments, the sending of the positioning signal to the earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be opposite to the ear canal center further includes: obtaining the rear positioning midpoint coordinates according to the two ear key point recognition parameters; and determining the earphone rear sound outlet position as the extension of the straight line where the positioning position of the earphone sound outlet is located by a preset distance.

[0016] In one of the embodiments, the single-axis displacement includes the vertical projection distance of the distance between any two ear key points.

[0017] In one of the embodiments, the single-axis displacement includes the horizontal projection distance of the distance between any two ear key points.

[0018] In one of the embodiments, the sending of the positioning signal to the earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be opposite to the ear canal center includes: detecting whether the key point position difference matches a preset point position difference; and when the key point position difference does not match the preset point position difference, sending a directional pipe adjusting signal to the earphone positioning monitoring system to adjust the position deviation of the earphone sound emitting body connecting pipe in a specified direction, wherein the position deviation includes at least one of the length, the curvature and the torsion angle of the earphone sound emitting body connecting pipe.

[0019] An earphone sound outlet positioning device, the device comprising:

[0020] A key point recognition module for obtaining ear key point recognition parameters;

[0021] a key point processing module, configured to perform point position processing on the ear key point recognition parameter and a preset target parameter to obtain a key point position difference;

[0022] a sound outlet position output module, configured to send a position adjusting signal to an earphone position adjusting and monitoring system according to the key point position difference, so as to adjust the positioning position of the sound outlet of the earphone; wherein the point position processing on the ear key point recognition parameter and the preset target parameter to obtain the key point position difference comprises: obtaining a single-axis displacement of a distance between at least two ear key points; and obtaining a difference between the single-axis displacement and the preset orientation value to obtain an ear sound outlet offset difference corresponding to all key points.

[0023] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0024] obtaining an ear key point recognition parameter;

[0025] performing point position processing on the ear key point recognition parameter and a preset target parameter to obtain a key point position difference;

[0026] sending a position adjusting signal to an earphone position adjusting and monitoring system according to the key point position difference, so as to adjust the positioning position of the sound outlet of the earphone to be directly opposite to the center of the ear canal; wherein the point position processing on the ear key point recognition parameter and the preset target parameter to obtain the key point position difference comprises: obtaining a single-axis displacement of a distance between at least two ear key points; and obtaining a difference between the single-axis displacement and the preset orientation value to obtain an ear sound outlet offset difference corresponding to all key points.

[0027] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0028] obtaining an ear key point recognition parameter;

[0029] performing point position processing on the ear key point recognition parameter and a preset target parameter to obtain a key point position difference;

[0030] sending a position adjusting signal to an earphone position adjusting and monitoring system according to the key point position difference, so as to adjust the positioning position of the sound outlet of the earphone to be directly opposite to the center of the ear canal; wherein the point position processing on the ear key point recognition parameter and the preset target parameter to obtain the key point position difference comprises: obtaining a single-axis displacement of a distance between at least two ear key points; and obtaining a difference between the single-axis displacement and the preset orientation value to obtain an ear sound outlet offset difference corresponding to all key points.

[0031] Compared with the prior art, the present application has at least the following advantages:

[0032] After the key points of the ear are determined, the shape of the ear is determined, and then the ear key point recognition parameters are compared with the preset target parameters to determine the position deviation degree of the key points of the ear, i.e., the key point position difference, and finally a corresponding positioning signal is sent according to the difference degree of the key point position difference to adjust the structure of the earphone, so that the position of the sound outlet of the earphone is changed to be directly opposite to the center of the ear canal, thereby effectively improving the direct opposite degree of the sound outlet of the earphone and the center of the ear canal. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0034] Figure 1 A flow chart of the earphone sound outlet positioning method in an embodiment;

[0035] Figure 2 A front view of the earphone sound outlet positioning method shown in Figure 1

[0036] Figure 3 A side view of the earphone sound outlet positioning method shown in Figure 1

[0037] Figure 4 Another front view of the earphone sound outlet positioning method shown in Figure 1

[0038] Figure 5 Another side view of the earphone sound outlet positioning method shown in Figure 1

[0039] Figure 6 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0040] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the related drawings. The preferred embodiments of the present application are shown in the drawings. However, the present application can be realized in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0041] ​​​​It should be noted that when an element is referred to as being "on" another element, it can be directly on the other element or intervening elements can also be present. When an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements can also be present. The terms "vertical", "horizontal", "left", "right" and similar expressions as used herein are for illustrative purposes only and are not intended to be limiting.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this description, the terms "and / or" includes any and all combinations of one or more of the associated listed items.

[0043] The present application relates to a kind of earphone sound outlet positioning method.In one embodiment, the earphone sound outlet positioning method includes obtaining ear key point identification parameter;The ear key point identification parameter and preset target parameter are point position processing, and key point position difference is obtained;According to the key point position difference, positioning signal is sent to earphone positioning monitoring system, to adjust the positioning position of earphone sound outlet and the center of ear canal is directly opposite;Wherein, the ear key point identification parameter and preset target parameter are point position processing, and key point position difference is obtained, including: obtaining the single-axis displacement of the distance between at least two ear key points;Difference between the single-axis displacement and the preset orientation value is obtained, to obtain the ear sound outlet offset difference of all key points corresponding.Corresponding to the key point of ear after being determined, the shape of ear is determined, then ear key point identification parameter and preset target parameter are compared, to determine the position deviation degree of the key point of ear, i.e. key point position difference, finally according to the difference degree of key point position difference, corresponding positioning signal is sent, to adjust the structure of earphone, so that the position of earphone sound outlet changes to and the center of ear canal is directly opposite, thereby effectively improve the direct opposite degree of earphone sound outlet and the center of ear canal.

[0044] Please refer to Figure 1 It is the flow chart of the earphone sound outlet positioning method of an embodiment of the present application.The earphone sound outlet positioning method includes part or all of the following steps.

[0045] S100: obtaining ear key point identification parameter.

[0046] In the embodiment, the ear key point recognition parameter is the key point position information on the collected ear image, that is, the ear key point recognition parameter is the current position of the ear key point of the earphone wearer, that is, the ear key point recognition parameter corresponds to the current position of each ear key point. Through the acquisition of the ear key point recognition parameter, the ear shape of the earphone wearer is determined, so that the unique ear shape of the earphone wearer is determined, and then the position of the earphone sound outlet is adjusted according to the ear shape of the earphone wearer, so that the earphone sound outlet is directly opposite to the ear canal center of the earphone wearer. Wherein, the ear key point is collected through the corresponding training model, specifically, the ear target recognition model is trained through a large number of ear pictures manually calibrated by ear position, the general HOG gradient direction histogram feature+SVM support vector machine object detection algorithm is applied, the ear key point recognition model is trained through a large number of ear key points manually calibrated by ear pictures, so as to obtain various key points of the ear. And the general two-dimensional image feature point extraction algorithm based on Ensemble of Regression Trees multistage regression tree is applied to extract a plurality of key points which have the greatest influence on the sound outlet from the above key points. The training of these algorithms can be carried out in advance on PC or server, and finally two algorithm model files are obtained.

[0047] S200: The ear key point recognition parameter is processed with the preset target parameter to obtain a key point position difference.

[0048] In the embodiment, the ear key point recognition parameter is the key point position information on the collected ear image, that is, the ear key point recognition parameter is the current position of the ear key point of the earphone wearer, that is, the ear key point recognition parameter corresponds to the current position of each ear key point. The preset target parameter is the standard ear key point corresponding to the earphone, that is, the preset target parameter is the ear key point recognition parameter corresponding to the ear shape currently adapted by the earphone, that is, the preset target parameter corresponds to the ear key point of the ear canal center directly opposite to the current sound outlet position of the earphone. The ear key point recognition parameter and the preset target parameter are processed to determine the difference between the current ear key point of the earphone wearer and the ear key point corresponding to the earphone, so as to determine the deviation of the ear canal center of the earphone wearer and the earphone sound outlet, that is, the key point position difference.

[0049] S300: According to the key point position difference, a positioning signal is sent to the earphone positioning monitoring system to adjust the positioning position of the earphone sound outlet and the ear canal center.

[0050] In the embodiment, the key point position difference is the difference between the current ear key point of the earphone wearer and the ear key point corresponding to the earphone, that is, the key point position difference is the deviation between the ear canal center of the earphone wearer and the sound outlet of the earphone, that is, the key point position difference is the position deviation between the sound outlet of the earphone and the position of the ear canal center of the earphone wearer. In this way, after determining the deviation between the position of the ear canal center of the current earphone wearer and the current sound outlet position of the earphone, a positioning signal is sent to the earphone positioning monitoring system, so that the earphone positioning monitoring system knows that the sound outlet of the earphone needs to be adjusted, and specifically, the positioning signal includes the deflection angle and the telescopic length of the sound outlet of the earphone, so that the sound outlet of the earphone is opposite to the ear canal center of the earphone wearer, thereby improving the degree of alignment between the sound outlet of the earphone and the ear canal center of the earphone wearer.

[0051] In the above embodiment, after the key points of the ear are determined, the shape of the ear is determined, and then the ear key point recognition parameter is compared with the preset target parameter to determine the position deviation degree of the key points of the ear, that is, the key point position difference, and finally according to the difference degree of the key point position difference, a corresponding positioning signal is sent to adjust the structure of the earphone, so that the position of the sound outlet of the earphone changes to be opposite to the ear canal center, thereby effectively improving the alignment degree between the sound outlet of the earphone and the ear canal center.

[0052] In one of the embodiments, the ear key point recognition parameter is compared with the preset target parameter to obtain the key point position difference, including: obtaining a key point directional value according to the ear key point recognition parameter; and performing directional position deviation processing on the key point directional value and a preset directional value to obtain the key point position difference. In the embodiment, the ear key point recognition parameter includes the position of the ear key point, and specifically, the ear key point recognition parameter includes the key point directional value. The key point directional value is the position offset of the ear key point in a specified direction, and the key point directional value is used to reflect the position change of the ear key point in a fixed direction. The preset directional value is a standard position deviation value in a specified direction, that is, the preset directional value is used to reflect the standard position of the current sound outlet of the earphone in the specified direction. The directional position deviation processing on the key point directional value and the preset directional value is convenient for determining the alignment deviation between the ear canal center of the earphone wearer and the current sound outlet of the earphone in the specified direction, thereby facilitating subsequent position adjustment of the sound outlet of the earphone in the specified direction to further improve the alignment degree between the ear canal center of the earphone wearer and the sound outlet of the earphone.

[0053] Further, the key point directional value is obtained according to the ear key point recognition parameter, and the method comprises: obtaining a single-axis displacement of a distance between at least two ear key points. In the embodiment, the key point directional value is a single-axis displacement, which is a component of the distance between the at least two ear key points, that is, the single-axis displacement is a displacement variable generated based on the at least two ear key points, that is, the single-axis displacement is a component distance between the at least two ear key points. The component distance between the at least two ear key points is calculated separately in a single-axis direction, so as to position the positions of the ear key points in multiple directions, and then the ear canal center of the earphone wearer and the normal position relationship of the earphone sound outlet are determined.

[0054] Further, the key point directional value is obtained according to the ear key point recognition parameter, and the method comprises: obtaining a single-axis displacement of a distance between at least two ear key points. In the embodiment, the key point directional value is a single-axis displacement, which is a component of the distance between the at least two ear key points, that is, the single-axis displacement is a displacement variable generated based on the at least two ear key points, that is, the single-axis displacement is a component distance between the at least two ear key points. The component distance between the at least two ear key points is calculated separately in a single-axis direction, so as to position the positions of the ear key points in multiple directions, and then the ear canal center of the earphone wearer and the normal position relationship of the earphone sound outlet are determined.

[0055] In another embodiment, the single-axis displacement comprises a vertical projection distance of a distance between any two ear key points, and specifically, the single-axis displacement is a component of the distance between the two ear key points in the Y-axis direction. The single-axis displacement is a vertical component of the distance between the two ear key points, so as to specifically distinguish the distance between the two ear key points in the Y-axis direction, to position the relative positions of the ear key points in the vertical direction, and then to provide a reference for adjusting the position of the earphone sound outlet in the vertical direction. For different ear key points in the image, the component calculation and difference comparison in the vertical direction are performed.

[0056] In another embodiment, the single-axis displacement amount includes a horizontal projection distance of a distance between any two ear key points, and specifically, the single-axis displacement amount is a component of the distance between the two ear key points on the X-axis. The single-axis displacement amount as the horizontal component of the distance between the two ear key points facilitates specific distinction of the distance between the two ear key points in the X-axis direction, thereby facilitating positioning of the relative positions between the ear key points in the horizontal direction, and further facilitating providing a reference for adjusting the position of the earphone sound outlet in the horizontal direction. For each key point on the image of the different ear, the component calculation and difference comparison in the horizontal direction can be performed.

[0057] In one embodiment, the sending of the positioning signal to the earphone positioning monitoring system according to the key point difference amount to adjust the positioning position of the earphone sound outlet to be directly opposite to the ear canal center includes: detecting whether the key point difference amount matches a preset point difference amount; and when the key point difference amount does not match the preset point difference amount, sending a directional tube adjustment signal to the earphone positioning monitoring system to adjust the positional deviation of the earphone sound body connecting tube in a specified direction, wherein the positional deviation includes at least one of the length, the curvature, and the torsion angle of the earphone sound body connecting tube. In this embodiment, the key point difference amount is the difference degree between the current ear key point of the earphone wearer and the ear key point corresponding to the earphone, i.e., the key point difference amount is the direct deviation between the ear canal center of the earphone wearer and the earphone sound outlet, i.e., the key point difference amount is the position deviation degree between the position of the earphone sound outlet and the position of the ear canal center of the earphone wearer. The preset point difference amount is the standard position deviation degree between the position of the earphone sound outlet and the position of the ear canal center of the earphone wearer, i.e., the preset point difference amount corresponds to the standard positional deviation of the earphone sound outlet. The key point difference amount does not match the preset point difference amount, indicating that there is a positional deviation between the ear canal center of the earphone wearer and the current earphone sound outlet, i.e., the ear canal center of the earphone wearer is not directly opposite to the current earphone sound outlet. In this way, the directional tube adjustment signal is sent to the earphone positioning monitoring system to adjust the position of the earphone sound outlet, for example, at least one of the length, the curvature, and the torsion angle of the earphone sound body connecting tube in a specified direction is adjusted, so that the earphone sound outlet is adjusted to be directly opposite to the ear canal center of the earphone wearer, thereby improving the directness of the earphone sound outlet and the ear canal center of the earphone wearer.

[0058] In another embodiment, the point position processing of the ear key point recognition parameter and the preset target parameter to obtain a key point position difference comprises: performing a mean value operation on the positions of each ear key point to obtain a general sound outlet position; and performing a clustering analysis operation on the positions of each ear key point and the general sound outlet position to obtain an output of the sound outlet model. The sending of the positioning signal to the earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet to be directly opposite to the ear canal center comprises: outputting a corresponding sound outlet model according to the output of the sound outlet model. In this embodiment, for the ear hanging structure, i.e., the hook structure connected with the earphone sound body connecting pipe, when the ear hanging structure is a structure that cannot be disassembled on the earphone, and the ear hanging structure itself has no stretching or rotating freedom, a large number of people can be subjected to data collection in advance by using the object detection algorithm of HOG gradient direction histogram features + SVM support vector machine and the two-dimensional image feature point extraction algorithm based on Ensemble of Regression Trees multi-level regression tree, and a key point database is established. The statistical average position of the key points is obtained according to the key point database, and a general ear hanging structure of a certain shape and size is designed according to the average position of the key points. Then, the key points in the database and the sound outlet position of the general ear hanging structure are clustered and analyzed to obtain several sound outlet accessories that compensate for the distance from the best sound outlet position, i.e., the specific model of the corresponding sound outlet. Finally, the user himself is photographed according to the above two algorithm models, the key points are obtained through image recognition, and one of the above several prepared sound outlet accessories that best fit the user's ears is selected through clustering analysis of the key points. Meanwhile, the prepared sound outlet accessory is a structure that can be disassembled on the earphone, and can be installed and replaced on the earphone sound body structure.

[0059] Wherein, the same way is adopted for the acquisition of the ear key point recognition parameter and the preset target parameter. Specifically, taking the acquisition of the preset target parameter as an example, the preset target parameter corresponds to a general ear hanging structure of a certain type of earphone. The front view image and the side view image of the ear are collected, the front view image is an image of the ear collected from the front direction of the earphone wearer, and the side view image is an image of the ear collected from the side direction of the earphone wearer, please refer to Figure 2 and Figure 3 for details, the front view image and the side view image each have corresponding four key points, the key points of the front view image are A, B, C and D, and the key points of the side view image are A', B', C' and E. At least part of the key points of the front view image and the key points of the side view image are the same positions of the ear.

[0060] The projection H1 of the distance L1 between the key point A and the key point B in the vertical direction (perpendicular to the ground direction) is calculated, the projection H2 of the distance L2 between the key point A and the key point C in the vertical direction (perpendicular to the ground direction) is calculated, and the middle value of H1 and H2 is taken as the best height H, such as: H=k1*H1+k2*H2 (0.1<k1<0.9, 0.1<k2<0.9, k1+k2=1), and the radius size R of the top of the ear hanging structure in the front view image is also considered, and H+R is obtained as a preset target parameter, that is, the position of the ear canal center of the earphone wearer in the vertical direction of the front view image is compared with the ear key point recognition parameter to determine the front view vertical directness between the sound outlet of the earphone and the ear canal center of the earphone wearer. The transmitted positioning signal includes adjusting the length and the curvature of the connecting pipe between the ear hanging and the sound emitting main structure of the earphone, that is, the length and the curvature of the connecting pipe between the ear hanging and the sound emitting main structure of the earphone are adjusted in the plane of the front view image, so that the sound outlet of the earphone is directly opposite to the ear canal center of the earphone wearer.

[0061] The projection V1 of the distance L3 between the key point A and the key point D in the horizontal direction (parallel to the ground, connecting the left and right ears) is calculated, and m*V1 (0.2<m<1.2) is obtained as a preset target parameter, that is, the position of the ear canal center of the earphone wearer in the horizontal direction of the front view image is compared with the ear key point recognition parameter to determine the front view horizontal directness between the sound outlet of the earphone and the ear canal center of the earphone wearer. The transmitted positioning signal includes adjusting the length and the torsion angle of the connecting pipe between the ear hanging and the sound emitting main structure of the earphone, that is, the length and the torsion angle of the connecting pipe between the ear hanging and the sound emitting main structure of the earphone are adjusted in the plane of the front view image, so that the sound outlet of the earphone is directly opposite to the ear canal center of the earphone wearer.

[0062] The distance L4 of the key point A' and the key point B' is projected W1 in the horizontal direction (parallel to the ground, the front and back direction of the face), the distance L5 of the key point A' and the key point C' is projected W2 in the horizontal direction (parallel to the ground, the front and back direction of the face), Wa=(W1+W2) / 2. The distance L6 of the key point E and the key point B' is projected W3 in the horizontal direction (parallel to the ground, the front and back direction of the face), the distance L7 of the key point E and the key point C' is projected W4 in the horizontal direction (parallel to the ground, the front and back direction of the face), Wb=(W3+W4) / 2, and n*Wb-Wa(0.2<n<0.8) is a preset target parameter, that is, in the horizontal direction of the side view image, the position of the ear canal center of the earphone wearer is compared with the ear key point recognition parameter to determine the side view horizontal directness between the sound outlet of the earphone and the ear canal center of the earphone wearer. Wherein, the sending of the positioning signal includes adjusting the length and the arc of the ear hook and the sound emitting main body structure connecting pipe, that is, the length and the arc of the ear hook and the sound emitting main body structure connecting pipe are adjusted in the plane of the side view image, so that the sound outlet of the earphone is directly opposite to the ear canal center of the earphone wearer.

[0063] In another embodiment, after determining the position of the earphone sound outlet, that is, determining the front sound outlet of the earphone, it is also necessary to determine the rear sound outlet, and the positioning signal is sent to the earphone positioning monitoring system according to the key point difference amount, so as to adjust the positioning position of the earphone sound outlet to be directly opposite to the ear canal center, and then the following steps are included:

[0064] According to the two ear key point recognition parameters, the rear positioning midpoint coordinates are obtained.

[0065] The positioning midpoint coordinates and the positioning position of the earphone sound outlet are determined as the rear sound outlet position of the earphone within a preset distance.

[0066] In this embodiment, the two ear key point recognition parameters are two key points close to the ear canal center position, and the rear positioning midpoint coordinates are the midpoint coordinates of the two key points, and then the position of the rear sound outlet of the earphone is determined in combination with the positioning position of the earphone sound outlet, for example, the straight line of the rear positioning midpoint coordinates and the positioning position of the earphone sound outlet is determined as the position of the rear sound outlet at a certain distance away from the front sound outlet of the earphone.

[0067] Specifically, please refer to Figure 4 and Figure 5The midpoint P of the key point B and the key point C is connected with the front sound outlet, and is extended to the ear outward direction by a distance T1, and the rear sound outlet is determined at a position of 1-2cm.

[0068] It can be understood that for the ear images collected in two vertical directions, the key points based on the same position need to be compared, that is, the key points on the front view image and the side view image are partially the same ear position, and by comparing the key point positions of the ear images in different angles, the sound outlet of the earphone and the ear canal center of the earphone wearer are determined in multiple directions, so as to improve the alignment degree.

[0069] However, whether the collection directions of the front view image and the side view image are perpendicular directly affects the comparison of the bit offset of each key point, and also affects the judgment accuracy of the alignment degree of the sound outlet of the earphone and the ear canal center of the earphone wearer. In order to improve the judgment accuracy of the alignment degree of the sound outlet of the earphone and the ear canal center of the earphone wearer, the ear key point recognition parameter and the preset target parameter are subjected to point position processing to obtain a key point bit difference, and the following steps are further included:

[0070] According to the ear key point recognition parameter, each same point coordinate is obtained;

[0071] The same point coordinates are subjected to point shape conversion processing to obtain a first same point shape and a second same point shape, wherein the first same point shape and the second same point shape are same point line shapes on two different ear key point collection images;

[0072] The first same point shape and the second same point shape are subjected to stretching ratio processing to obtain a same point stretching ratio value;

[0073] It is detected whether the same point stretching ratio value matches a preset stretching ratio value;

[0074] When the same point stretching ratio value does not match the preset stretching ratio value, a key point collection abnormal alarm signal is sent to the earphone positioning monitoring system.

[0075] In the embodiment, the same point coordinates are coordinates of key points of the same positions of the ear images collected in different directions, that is, the same point coordinates are positions corresponding to the same key points on different ear images, that is, the same point coordinates are position coordinates of the same ear positions on different ear images. The point shape conversion processing of each same point coordinate is to perform graphic conversion on the key points of the same positions on different ear images, specifically, the key points of the same ear positions form corresponding graphics to form corresponding same point graphics on different ear images. The first same point graphic and the second same point graphic correspond to graphics of the same key points of two different ear images respectively, and the first same point graphic and the second same point graphic are used to reflect the graphic structure surrounded by the same points of different ear images. The stretching ratio processing of the first same point graphic and the second same point graphic to obtain the same point stretching ratio value is to perform stretching comparison on the first same point graphic and the second same point graphic, specifically, taking the first same point graphic as a reference graphic, stretching in a single image collection rotation direction, and then performing similarity comparison on the stretching graphic and the second same point graphic, and taking the comparison result as the stretching difference ratio between the first same point graphic and the second same point graphic, that is, the same point stretching ratio value, so as to facilitate determination of the difference degree of the first same point graphic and the second same point graphic after stretching. The same point stretching ratio value does not match the preset stretching ratio value, indicating that the stretching difference of the first same point graphic and the second same point graphic is too large, that is, indicating that the graphic of the first same point graphic after rotating and stretching by 90 degrees is different from the second same point graphic, that is, indicating that the first same point graphic cannot be rotated and stretched to become a graphic similar to the second same point graphic, and at this time, a key point collection abnormality alarm signal is sent to the earphone positioning monitoring system to determine that the collected ear images in different directions do not satisfy the verticality.

[0076] In another embodiment, when the same point stretching ratio value matches the preset stretching ratio value, step S200 is performed to facilitate subsequent sound outlet positioning based on key points of ear images collected in two mutually perpendicular directions, so as to improve the degree of alignment of the sound outlet of the earphone with the center of the ear canal of the person wearing the earphone.

[0077] Further, the first same point graphic and the second same point graphic are same point lines on two different ear key point collection images, that is, the vertices of the first same point graphic and the vertices of the second same point graphic are the same on the ear, and when the positions of the key points of the same point graphics are basically kept on the same straight line, it is easy to cause inaccurate sound outlet positioning based on the key points, that is, the component of the key points in another direction is too small.

[0078] In order to further improve the degree of alignment of the sound outlet of the earphone with the center of the ear canal of the person wearing the earphone, the stretching ratio processing of the first same point graphic and the second same point graphic to obtain the same point stretching ratio value further comprises the following steps:

[0079] obtaining a first pattern proportion according to the first same-point pattern;

[0080] detecting whether the first pattern proportion is greater than or equal to a first preset proportion;

[0081] obtaining a second pattern proportion according to the second same-point pattern when the first pattern proportion is greater than or equal to the first preset proportion;

[0082] detecting whether the second pattern proportion is greater than or equal to a second preset proportion;

[0083] sending a same-point pattern abnormality alarm signal to the earphone position monitoring system when the second pattern proportion is less than the second preset proportion.

[0084] In the embodiment, the first pattern proportion is obtained based on the first same-point pattern, and the second pattern proportion is obtained based on the second same-point pattern. Specifically, the first pattern proportion is an area ratio of the first same-point pattern to a front view image, and the second pattern proportion is an area ratio of the second same-point pattern to a side view image. The first pattern proportion and the second pattern proportion are used to reflect the area ratio of the key points at the same position on different ear images. The first pattern proportion is used to reflect the area ratio of the region formed by the same key point on the front view image, and the second pattern proportion is used to reflect the area ratio of the region formed by the same key point on the side view image. The first pattern proportion being greater than or equal to the first preset proportion indicates that the area of the first same-point pattern on the ear image in the front view direction is large, that is, the distribution of the key points of the first same-point pattern on the ear image in the front view direction is sufficient, and that is, the first same-point pattern on the ear image in the front view direction does not appear on the same straight line. The second pattern proportion being less than the second preset proportion indicates that the area of the second same-point pattern on the ear image in the side view direction is too small, that is, the distribution of the key points of the second same-point pattern on the ear image in the side view direction is too concentrated, and that is, the second same-point pattern on the ear image in the side view direction is distributed close to the same straight line. Since the second same-point pattern is collected after the first same-point pattern is rotated and stretched, the key points of the second same-point pattern are the same as those of the first same-point pattern. Therefore, the same position key points used at present are too concentrated and do not sufficiently cover more ear positions, which can easily cause deviation in positioning the position of the earphone sound outlet. At this time, the same-point pattern abnormality alarm signal is sent to the earphone position monitoring system, so as to timely determine that the selection of the same key points is abnormal, thereby facilitating timely replacement of other key points at the same position, and further facilitating subsequent timely adjustment of the position selection of the same key points, so as to further improve the degree of alignment of the earphone sound outlet with the ear canal center of the earphone wearer.

[0085] In one of the embodiments, the application further provides an earphone sound outlet positioning device, which is implemented by using the earphone sound outlet positioning method in any of the above embodiments. In one of the embodiments, the earphone sound outlet positioning device has function modules corresponding to the steps of the earphone sound outlet positioning method. The earphone sound outlet positioning device comprises a key point identification module, a key point processing module and a sound outlet positioning output module. The key point identification module is configured to obtain ear key point identification parameters. The key point processing module is configured to perform point position processing on the ear key point identification parameters and preset target parameters to obtain a key point position difference. The sound outlet positioning output module is configured to send a positioning signal to an earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet.

[0086] In the embodiment, after the key point identification module determines the key points of the ear, the shape of the ear is determined. Then, the key point processing module compares the ear key point identification parameters with the preset target parameters to determine the degree of position deviation of the key points of the ear, i.e., the key point position difference. Finally, the sound outlet positioning output module sends a corresponding positioning signal according to the degree of difference of the key point position difference, so that the person wearing the earphone adjusts the structure of the earphone, so that the position of the earphone sound outlet changes to be opposite to the center of the ear canal, thereby effectively improving the degree of alignment of the earphone sound outlet and the center of the ear canal.

[0087] For specific limitations of the earphone sound outlet positioning device, refer to the limitations of the earphone sound outlet positioning device in the above, which will not be repeated here. Each module in the above earphone sound outlet positioning device can be implemented by software, hardware and a combination thereof in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0088] In another embodiment, the point position processing of the ear key point recognition parameter and the preset target parameter to obtain a key point position difference includes: performing clustering analysis on the distance and the connecting line of each ear key point to obtain an ear hanging model output; and the sending of the positioning signal to the earphone positioning monitoring system according to the key point position difference to adjust the positioning position of the earphone sound outlet and the center of the ear canal includes: outputting a corresponding ear hanging model according to the ear hanging model output. In this embodiment, a large number of people can be classified according to the HOG gradient direction histogram feature + SVM support vector machine object detection algorithm and the two-dimensional image feature point extraction algorithm based on Ensemble of Regression Trees multi-level regression tree, and the key point database is established by collecting data in advance. The key point database is used for clustering analysis according to the key point distance and the key point connecting line. According to the key point distribution interval with the largest probability distribution, several corresponding preliminary ear hanging structural members are designed to meet the average shape size and the front and rear sound hole positions in the interval. Finally, the front view image and the side view image collected by photographing the user himself are obtained, and the key points are obtained by image recognition. According to the clustering analysis result of the key points, one of the above-mentioned several preliminary ear hanging structural members that best matches the user's own ear is selected, that is, the specific model of the ear hanging structure is obtained. Meanwhile, the preliminary ear hanging structural member is a detachable structure on the earphone, which can be installed and replaced on the sound emitting main structure of the earphone.

[0089] In one embodiment, a computer device, which can be a server, has an internal structure diagram as shown in Figure 6 The computer device includes a processor, a memory and a network interface connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store ear key point recognition parameters and other data. The network interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement an earphone sound outlet positioning method.

[0090] Those skilled in the art can understand that Figure 6 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. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0091] In one of the embodiments, the present application further provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0092] In one of the embodiments, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0093] A person of ordinary skill in the art can understand that all or part of the above-mentioned method embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the computer program can include the processes of the above-mentioned method embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. The volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, the RAM can be static random access memory (SRAM) or dynamic random access memory (DRAM).

[0094] The above-mentioned embodiments only express several implementation manners of the present application, which are described in detail and specifically, but should not be understood as limitation to the patent scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A method for locating the sound outlet of an earphone, characterized in that, include: Obtain ear key point recognition parameters; The ear key point recognition parameters and the preset target parameters are processed to obtain the key point position difference. The preset target parameters are the ear key point recognition parameters corresponding to the ear shape that the earphone is currently adapted to for suspension. Based on the key point position difference, a positioning signal is sent to the headphone positioning monitoring system to adjust the positioning position of the headphone sound outlet to be aligned with the center of the ear canal. The step of performing point-position processing on the ear key point recognition parameters and preset target parameters to obtain the key point position difference includes: Obtain the single-axis displacement of the distance between at least two ear key points; The difference between the single-axis displacement and the preset orientation value is calculated to obtain the offset difference of the ear outlet corresponding to all key points. The preset orientation value is the standard offset value in the specified direction, which is used to reflect the standard position of the current ear outlet in the specified direction. The step of sending a positioning signal to the headphone positioning monitoring system based on the key point position difference to adjust the positioning position of the headphone outlet to be aligned with the center of the ear canal includes: Detect whether the key point position difference matches the preset point position difference. When the position difference of the key point does not match the position difference of the preset point, a directional adjustment signal is sent to the headphone adjustment monitoring system to adjust the position deviation of the headphone sound-generating main body connecting tube in a specified direction. The position deviation includes at least one of the length, curvature and torsion angle of the headphone sound-generating main body connecting tube.

2. The headphone output port positioning method according to claim 1, characterized in that, The step of performing point-position processing on the ear key point recognition parameters and preset target parameters to obtain the key point position difference includes: Cluster analysis is performed on the distances and connections between key points on the ear to obtain the ear hook model output. The step of sending a positioning signal to the headphone positioning monitoring system based on the key point position difference to adjust the positioning position of the headphone outlet to be aligned with the center of the ear canal includes: Output the corresponding ear hook model based on the output quantity of the ear hook model.

3. The headphone output port positioning method according to claim 1, characterized in that, The step of performing point-position processing on the ear key point recognition parameters and preset target parameters to obtain the key point position difference includes: By performing a uniform positioning operation on the key points of each ear, a universal sound outlet position is obtained; Cluster analysis was performed on the locations of key points in each ear and the locations of common sound outlets to obtain the output of each sound outlet model. The step of sending a positioning signal to the headphone positioning monitoring system based on the key point position difference to adjust the positioning position of the headphone outlet to be aligned with the center of the ear canal includes: Output the corresponding mouthpiece model based on the output volume of the mouthpiece model.

4. The headphone output port positioning method according to claim 1, characterized in that, The step of sending a positioning signal to the headphone positioning monitoring system based on the key point position difference to adjust the positioning position of the headphone outlet to be aligned with the center of the ear canal, and then further includes: The coordinates of the midpoint are then obtained based on the two ear key point recognition parameters; The position of the rear sound outlet of the headphones is determined by extending a preset distance from the coordinates of the midpoint of the positioning and the positioning position of the headphone outlet along the straight line.

5. The headphone output port positioning method according to claim 1, characterized in that, The single-axis displacement includes the vertical projection distance between any two key points on the ear.

6. The headphone output port positioning method according to claim 1, characterized in that, The single-axis displacement includes the horizontal projected distance between any two key points on the ear.

7. A headphone sound outlet positioning device, characterized in that, include: The key point recognition module is used to obtain key point recognition parameters of the ear; The key point processing module is used to perform point processing on the ear key point recognition parameters and the preset target parameters to obtain the key point position difference, wherein the preset target parameters are the ear key point recognition parameters corresponding to the ear shape that the earphone is currently adapted to hang. The sound outlet positioning output module is used to send a positioning signal to the headphone positioning monitoring system based on the key point position difference, so as to adjust the positioning position of the headphone sound outlet to be aligned with the center of the ear canal; wherein, the step of processing the ear key point identification parameters and preset target parameters to obtain the key point position difference includes: obtaining the single-axis displacement of the distance between at least two ear key points; calculating the difference between the single-axis displacement and the preset orientation value to obtain the ear sound outlet offset difference corresponding to all key points, wherein the preset orientation value is a standard position offset value in a specified direction, used to reflect the position difference in the specified direction. The standard position of the current sound outlet corresponding to the headphones; the step of sending a positioning signal to the headphone positioning monitoring system according to the key point position difference to adjust the positioning position of the headphone sound outlet to be aligned with the center of the ear canal includes: detecting whether the key point position difference matches the preset point position difference; when the key point position difference does not match the preset point position difference, sending a directional adjustment signal to the headphone positioning monitoring system to adjust the position deviation of the headphone sound-generating main body connecting tube in a specified direction, wherein the position deviation includes at least one of the length, curvature, and torsion angle of the headphone sound-generating main body connecting tube.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images