Sound localization system and method

Abstract

The present invention provides a sound positioning system and method, which includes: a mounting part for containing a magnetic fluid; a plurality of sound pickup modules arranged around the magnetic fluid for converting the picked-up sound into a voltage signal; a plurality of magnetic parts arranged around the magnetic fluid, each of which is connected to a sound pickup module for generating a magnetic force under the action of the voltage signal to deform the magnetic fluid; a first image acquisition module arranged relative to the magnetic fluid for acquiring an image of the magnetic fluid; and a controller connected to the first image acquisition module for determining the direction of the sound according to the image. The present invention deforms the magnetic fluid through magnetic force, and finally determines the direction of the sound through the deformed magnetic fluid. The direction of the sound can be determined without a processor, which reduces the configuration requirements of the device and the cost of determining the direction of the sound.

Description

Technical Field

[0001] The present invention relates to the technical field of sound positioning, and in particular to a sound positioning system and method. Background Art

[0002] Online video conferencing systems have been welcomed by various institutions in recent years. Whether it is distance learning or business meetings, they can be accessed through various terminals anytime and anywhere, saving transportation costs and improving work efficiency.

[0003] In some conferences where real-time tracking and filming of the host and speaker is required, the camera needs to track the current speaker in real time. To achieve the effect of automatic tracking, some devices use microphone matrices and high-speed signal processors to process the audio signals in the microphone array. The phase difference technology is used to determine the order in which the same audio reaches multiple microphones, thereby estimating the distance from the point of occurrence to the microphone, and then fitting the distance between the two microphones to calculate the direction of the sound, and then film the speaker in that direction.

[0004] However, sound signals are high-speed and high-frequency signals, and a processor with a relatively fast processing speed is required to process the sound signals to determine the direction of the sound. It can be seen that the existing method for determining the direction of sound has relatively high requirements on the configuration of the device. Summary of the invention

[0005] The present invention provides a sound positioning system and method, which are used to solve the problem that the existing sound direction determination method has high requirements on device configuration.

[0006] In one aspect, the present invention provides a sound localization system, comprising:

[0007] A mounting part for containing magnetic fluid;

[0008] A plurality of sound pickup modules are arranged around the magnetic fluid and are used to convert the picked-up sound into a voltage signal;

[0009] A plurality of magnetic members are arranged around the magnetic fluid, each of the magnetic members is connected to one of the sound pickup modules, and is used to generate magnetic force under the action of the voltage signal to cause the magnetic fluid to deform;

[0010] A first image acquisition module, arranged relative to the magnetic fluid, and used for acquiring an image of the magnetic fluid;

[0011] A controller is connected to the first image acquisition module and is used to determine the direction of the sound according to the image.

[0012] In one embodiment, the mounting member is provided with a groove for containing the magnetic fluid, each of the sound pickup modules and each of the magnetic members is arranged on the mounting member around the groove, and the cross-sectional area of ​​the groove is set to be larger than the cross-sectional area of ​​the magnetic fluid.

[0013] In one embodiment, the bottom of the groove is made of a transparent material, and the first image acquisition module is disposed relative to the bottom.

[0014] In one embodiment, the sound pickup module is provided with a microphone matrix and a cylindrical structure, an opening of the cylindrical structure is arranged relative to the sound collection surface of the microphone matrix, and another opening of the cylindrical structure is provided with one or more sound refraction components, and the microphone matrix is ​​used to collect sound that is not refracted by the sound refraction components.

[0015] In one embodiment, the sound positioning system further includes a shell, wherein the shell and the mounting member together form a closed space, and the first image acquisition module and the controller are disposed in the closed space.

[0016] In one embodiment, the sound positioning system further includes a second image acquisition module connected to the controller, and the controller controls the second image acquisition module to acquire an image of the area corresponding to the direction.

[0017] On the other hand, the present invention also provides a sound positioning method, which is applied to a sound positioning system, wherein the sound positioning system comprises a mounting member, a plurality of sound pickup modules, a plurality of magnetic members, a first image acquisition module and a controller, wherein the mounting member is used to hold a magnetic fluid, a plurality of the sound pickup modules and a plurality of the magnetic members are arranged around the magnetic fluid, each of the magnetic members is connected to a sound pickup module, and the first image acquisition module is arranged relative to the magnetic fluid; the sound positioning method comprises:

[0018] Acquire a first image of the magnetic fluid acquired by the first image acquisition module;

[0019] Taking the center of the magnetic fluid in the target area as the starting point, a plurality of line segments are set in the target area to divide the target area into a plurality of sub-areas, wherein the target area is the area of ​​the magnetic fluid in the first image, and the angles corresponding to the center of each sub-area are the same;

[0020] Determine a target magnetic energy value of each sub-region according to the pixel points of the sub-region, and determine a target sub-region in each sub-region according to the magnetic energy value of each sub-region, wherein the magnetic energy value of the target sub-region is greater than the magnetic energy value of the sub-region not determined as the target sub-region;

[0021] The direction from which the sound is emitted is determined according to the position of the angle corresponding to the target sub-area.

[0022] In one embodiment, determining the target magnetic energy value of each sub-area according to the pixel points of the sub-area includes:

[0023] Removing the fan-shaped areas of each of the sub-areas to obtain a convex area corresponding to each sub-area, wherein the areas of the fan-shaped areas of each of the sub-areas are the same;

[0024] The target magnetic energy value of the sub-area corresponding to the protruding area is determined according to the number of pixel points corresponding to the protruding area, and the number is positively correlated with the target magnetic energy value.

[0025] In one embodiment, determining the target magnetic energy value of the sub-area corresponding to the protruding area according to the number of pixels corresponding to the protruding area includes:

[0026] Determining the magnetic energy value to be determined of the sub-area corresponding to the protruding area according to the number of pixels corresponding to the protruding area;

[0027] If the sub-region is a historical target sub-region and the current time is in the protection time period of the sub-region, the target magnetic energy value of the sub-region is determined according to the magnetic energy value to be determined and the set multiple.

[0028] In one embodiment, there are two target sub-areas, and determining the direction of the sound according to the positions of the angles corresponding to the target sub-areas includes:

[0029] Obtaining the angle between the two target sub-areas;

[0030] The direction from which the sound is emitted is determined according to the angle.

[0031] In one embodiment, the sound positioning system further includes a second image acquisition module, and after determining the direction of the sound according to the position of the angle corresponding to the target sub-area, further includes:

[0032] Control the second image acquisition module to acquire a second image of the area corresponding to the direction.

[0033] In one embodiment, after controlling the second image acquisition module to acquire the second image of the area corresponding to the direction, the method further includes:

[0034] If the second image does not contain the user, removing the target sub-region from each of the sub-regions;

[0035] Re-determining the target sub-region in each of the sub-regions except the target sub-region;

[0036] Re-determining the direction of the sound according to the position of the angle corresponding to the re-determined target sub-area;

[0037] The second image acquisition module is controlled to acquire an image of the area corresponding to the re-determined direction.

[0038] The sound positioning system and method provided by the present invention are characterized in that a plurality of sound pickup modules and a plurality of magnetic parts are arranged around a magnetic fluid. The sound pickup modules pick up sound to cause the magnetic parts to generate magnetic force, which causes the magnetic fluid to deform. Finally, the direction of the sound is determined by the deformed magnetic fluid. The direction of the sound can be determined without using a processor, thereby reducing the configuration requirements of the device and the cost of determining the sound direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0040] Figure 1 A schematic diagram of the structure of the sound localization system of the present invention;

[0041] Figure 2 Another structural schematic diagram of the sound positioning system of the present invention;

[0042] Figure 3 A schematic diagram of a cylindrical structure in a sound pickup assembly in a sound localization system of the present invention;

[0043] Figure 4 It is another structural schematic diagram of the sound positioning system of the present invention;

[0044] Figure 5 It is another structural schematic diagram of the sound positioning system of the present invention;

[0045] Figure 6 It is a flowchart of a first embodiment of a sound localization method of the present invention;

[0046] Figure 7 FIG. 5 is a schematic diagram of a detailed flow chart of step S603 in the second embodiment of the sound localization method of the present invention.

[0047] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the preferred embodiments of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar parts or parts with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of them. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limitations on the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The embodiments of the present invention are described in detail below in conjunction with the drawings.

[0049] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, or it can be an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] In the description of the present invention, it is necessary to understand that the terms "upper", "lower", "front", "back", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. indicate orientations or positional relationships based on the orientations or positional relationships in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0051] The terms "first", "second", "third" (if any) in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example.

[0052] In addition, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or display comprising a series of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, product, or display.

[0053] The invention provides a sound localization system.

[0054] Reference Figure 1The sound positioning system 100 includes a mounting member 110 , a plurality of sound pickup modules 120 , a plurality of magnetic members 130 , a first image acquisition module 140 and a controller 150 .

[0055] The mounting member 110 is used to hold a magnetic fluid 111. The magnetic fluid 111 refers to a liquid substance with magnetism. The magnetic fluid 111 has both the fluidity of a liquid and the magnetism of a solid magnetic material. The magnetic fluid 111 is circular when there is no magnetic attraction. The mounting member 110 may be made of plastic and may be in the shape of a circular plate. Preferably, the magnetic fluid 111 is held in the center of the mounting member 110.

[0056] The sound pickup module 120 includes a microphone matrix. Each sound pickup module 120 is disposed around the magnetic fluid 111. Exemplarily, each sound pickup module 120 is arranged in a ring, and the center of the ring is the magnetic fluid 111. Each sound pickup module 120 is used to pick up sounds from different directions.

[0057] The magnetic member 130 includes an electromagnet coil and a permanent magnet, and the electromagnet coil is arranged around the permanent magnet. Each magnetic member 130 is connected to a sound pickup module 120, and each magnetic member 130 is arranged around the magnetic fluid 111. Specifically, the sound pickup module 120 is connected to the electromagnet coil of the magnetic member 130. Exemplarily, each magnetic member 130 is arranged in a ring, and the center of the ring is the magnetic fluid 111. The magnetic member 130 and the sound pickup module 120 connected to the magnetic member 130 are arranged to form a straight line with the magnetic fluid 111. In addition, the magnetic member 130 and the sound pickup module 120 connected thereto can be used as a whole. After picking up the sound, the sound pickup module 120 converts the sound into a voltage signal, so that the magnetic member 130 generates a magnetic force through the voltage signal, and then the magnetic fluid is deformed by the magnetic force generated by the magnetic member 130.

[0058] The first image acquisition module 140 may be a camera. The first image acquisition module 140 is disposed relative to the magnetic fluid 111 and is used to acquire an image of the magnetic fluid 111 ( Figure 1 The middle dotted line is used to indicate that the first image acquisition module acquires an image of the magnetic fluid 111).

[0059] The controller 150 is connected to the first image acquisition module 140 , and the controller 150 can determine the direction of the sound based on the image acquired by the first image acquisition module 140 .

[0060] Specifically, a target area is first determined in the image, and the target area is the area of ​​the magnetic fluid in the image, that is, the target area only includes the magnetic fluid. Then, the target area is binarized, and the center of the magnetic fluid in the target area is determined. Since the magnetic fluid collected by the first image acquisition module is circular when the magnetic fluid is not subjected to the effect of magnetic force, the coordinates of the center of the magnetic fluid can be determined in advance and stored. The center of the magnetic fluid in the target area can be determined by the stored coordinates.

[0061] After determining the center of the magnetic fluid, multiple line segments are set in the target area with the center as the starting point, so as to divide the target area into multiple sub-areas, and the angle of each sub-area at the center is the same. For example, the center is O, and four line segments are set in the target area, namely AO, BO, CO and DO, and A, B, C, and D are all points on the boundary of the target area, that is, the target area is divided into four sub-areas AOB, BOC, COD and DOA, and ∠AOB=∠BOC=∠COD=∠DOA.

[0062] Since sound diffuses, and when sound diffuses, the energy of sound decays. Therefore, the energy corresponding to the direction of the sound is the largest, while the energy corresponding to the sound in other directions is smaller. The energy of sound is converted into the magnitude of magnetic force. The greater the magnetic force, the greater the deformation of the magnetic fluid. In this regard, the number of pixels in each sub-area can be determined. The sub-area with the largest number of pixels is the area with the largest deformation of the magnetic fluid. This area is defined as the target sub-area. The direction of the angle corresponding to the target sub-area can be determined as the direction of the sound.

[0063] Furthermore, the number of pixels can be converted into the magnetic capability value of the sub-area. The more pixels there are, the greater the magnetic capability value of the sub-area, and the greater the deformation of the sub-area. Sort the sub-areas in descending order of magnetic capability value, and then use the sub-area with the highest order as the target sub-area. The direction of the angle corresponding to the target sub-area can be determined as the direction of the sound. In addition, the first and second sub-areas can be selected as target sub-areas, and the direction of the angle between the two target sub-areas can be determined as the direction of the sound.

[0064] In this embodiment, a plurality of sound pickup modules and a plurality of magnetic parts are arranged around the magnetic fluid. The sound pickup modules pick up the sound to make the magnetic parts generate magnetic force, which causes the magnetic fluid to deform through the magnetic force. Finally, the direction of the sound is determined by the deformed magnetic fluid. The direction of the sound can be determined without going through a processor, which reduces the configuration requirements of the device and the cost of determining the direction of the sound.

[0065] Reference Figure 2The mounting member 110 is provided with a groove 112, and each sound pickup module 120 and each magnetic member 130 are arranged on the mounting member 110 around the groove. Exemplarily, the sound pickup module 120 and the connected magnetic member 130 are arranged on the mounting member 110 as a whole magnetic assembly 121.

[0066] Since the magnetic fluid 111 will deform, the groove 112 needs to leave space to allow the magnetic fluid 111 to deform. Therefore, the cross-sectional area of ​​the groove 112 is set to be larger than the cross-sectional area of ​​the magnetic fluid 111, so that the first image acquisition module can capture the image of the deformed magnetic fluid 111.

[0067] Further, when the target area is divided into sub-areas, one sub-area corresponds to one sound pickup module 120, that is, the line connecting the sound pickup module 120 with respect to the center of the magnetic fluid 111 is located in the sub-area corresponding to the sound pickup module 120. Preferably, the line is the center line of the sub-area corresponding to the sound pickup module 120, and the center line divides the angle of the sub-area at the center into two equal angles. Since the angle corresponding to each sub-area is the same, the distance between two adjacent sound pickup modules 120 is the same. In addition, the distance between each magnetic member 130 and the center is the same, and the distance between each sound pickup module 120 and the center is also the same, that is, the magnetic capacity value of each sub-area is determined at the same distance.

[0068] In addition, the bottom of the groove 112 is made of transparent material, and the first image acquisition module 140 is disposed relative to the bottom. Since the bottom of the groove 112 is transparent, the first image acquisition module 140 can acquire the image of the magnetic fluid 111 through the transparent bottom.

[0069] In this embodiment, the magnetic fluid is contained in the groove of the mounting member, and each sound pickup module and each magnetic member are arranged on the mounting member around the groove, so that the magnetic fluid, the sound pickup module and the magnetic member are fixed to prevent the movement of the components from reducing the accuracy of determining the sound direction.

[0070] Reference Figure 3 The sound pickup module 120 includes a microphone matrix (not shown) and a cylindrical structure 122. The first opening 1221 of the cylindrical structure 122 is arranged relative to the sound collection surface of the microphone matrix. The second opening 1222 of the cylindrical structure 122 is provided with one or more sound refraction components 1223, and a gap 1224 is left between each sound refraction component 1223. By providing the sound refraction component 1223 at the second opening 1222, the microphone matrix can only collect sounds that are not refracted by the sound refraction component 1223, that is, the microphone matrix can only collect sounds transmitted through the gap 1224.

[0071] If the magnetic fluid is deformed too much, it will cause the magnetic fluid to occupy the entire groove, that is, the shape of the magnetic fluid captured by the first image acquisition module is the shape of the groove. At this time, the controller cannot determine the direction of the sound through the magnetic fluid. In this embodiment, the intensity of the sound is weakened by the cylindrical structure 122 to avoid excessive deformation of the magnetic fluid due to excessive sound, that is, to avoid being unable to determine the direction of the sound.

[0072] Reference Figure 4 The sound positioning system 100 further includes a housing 160, which together with the mounting member 110 forms a closed space, and the first image acquisition module 140 and the controller 150 are disposed in the closed space. Exemplarily, the groove of the mounting member 110 contains the magnetic fluid 111, each sound pickup module 120 and each magnetic member 130 are disposed on the mounting member 110 around the groove, and the camera of the first image acquisition module 140 is disposed relative to the bottom of the groove.

[0073] Further, see Figure 5 The sound positioning system 100 further includes a second image acquisition module 170 connected to the controller 150. The second image acquisition module 170 is used to acquire an image of the area corresponding to the direction in which the sound is emitted. Exemplarily, the second image acquisition module 170 is mounted on the mounting member 110, and the second image acquisition module 170 is a rotatable camera. The controller 150 controls the second image acquisition module 170 to rotate, thereby acquiring an image of the area corresponding to the direction in which the sound is emitted.

[0074] In this embodiment, the various components of the sound positioning system are protected by providing a housing, thereby increasing the service life of the sound positioning system.

[0075] The invention also provides a sound positioning method.

[0076] Reference Figure 6 , Figure 6 This is a flow chart of a first embodiment of a sound localization method according to the present invention. The sound localization method comprises the following steps:

[0077] Step S601, acquiring a first image of the magnetic fluid acquired by a first image acquisition module.

[0078] In this embodiment, the execution subject is a sound positioning system, which includes a mounting member, a sound pickup module, a magnetic member, and a first image acquisition module. The connection relationship between the mounting member, the sound pickup module, the magnetic member, and the first image acquisition module is specifically referred to in the above description, and will not be repeated here. For the convenience of description, the system is used below to refer to the sound positioning system.

[0079] The system acquires an image of the magnetic fluid collected by the first image stimulation module, and the image is defined as a first image.

[0080] Step S602, taking the center of the magnetic fluid in the target area as the starting point, setting multiple line segments in the target area to divide the target area into multiple sub-areas, wherein the target area is the area of ​​the magnetic fluid in the first image, and the angles corresponding to the centers of the sub-areas are the same.

[0081] After acquiring the first image, the system first determines the target area in the first image. The target area is the area of ​​the magnetic fluid in the first image, that is, the target area only includes the magnetic fluid. The system then performs a binary process on the target area and determines the center of the magnetic fluid in the target area. Since the magnetic fluid collected by the first image acquisition module is circular when the magnetic fluid is not affected by the magnetic force, the system can first determine the coordinates of the center of the magnetic fluid and store the coordinates. The center of the magnetic fluid in the target area in the first image can be determined by the stored coordinates.

[0082] After determining the center of the magnetic fluid, the system sets multiple line segments in the target area with the center as the starting point, thereby dividing the target area into multiple sub-areas, and the angle of each sub-area at the center is the same. For example, the center is O, and four line segments are set in the target area, namely AO, BO, CO and DO, and A, B, C, and D are all points on the boundary of the target area, that is, the target area is divided into four sub-areas AOB, BOC, COD and DOA, and ∠AOB=∠BOC=∠COD=∠DOA.

[0083] Step S603, determining the target magnetic energy value of each sub-region based on the pixel points of the sub-region, and determining the target sub-region in each sub-region based on the magnetic energy value of each sub-region, the magnetic energy value of the target sub-region is greater than the magnetic energy value of the sub-region not determined as the target sub-region.

[0084] Step S604: determine the direction from which the sound is emitted according to the position of the corresponding angle of the target sub-area.

[0085] Since sound diffuses, and when sound diffuses, the energy of sound decays. Therefore, the energy corresponding to the direction of the sound is the largest, while the energy corresponding to the sound in other directions is smaller. The energy of sound is converted into the magnitude of magnetic force. The greater the magnetic force, the greater the deformation of the magnetic fluid. In this regard, the number of pixels in each sub-area can be determined. The sub-area with the largest number of pixels is the area with the largest deformation of the magnetic fluid. This area is defined as the target sub-area. The direction of the angle corresponding to the target sub-area can be determined as the direction of the sound.

[0086] Furthermore, the system can convert the number of pixels into the target magnetic capability value of the sub-area. The more pixels there are, the greater the target magnetic capability value of the sub-area, and the greater the deformation of the sub-area. The sub-areas are sorted in descending order of the target magnetic capability value, and then the sub-area with the highest sorting is used as the target sub-area. The direction of the angle corresponding to the target sub-area can be determined as the direction of the sound.

[0087] In this embodiment, a plurality of sound pickup modules and a plurality of magnetic parts are arranged around the magnetic fluid. The sound pickup modules pick up sound to cause the magnetic parts to generate magnetic force, which causes the magnetic fluid to deform. Finally, the direction of the sound is determined by collecting an image of the deformed magnetic fluid. The direction of the sound can be determined without going through a processor, thereby reducing the configuration requirements of the device and the cost of determining the direction of the sound.

[0088] Reference Figure 7 , Figure 7 This is a flow chart of a second embodiment of the sound localization method of the present invention. Based on the first embodiment, step S603 includes:

[0089] Step S701 , removing the fan-shaped regions of each sub-region to obtain a protruding region corresponding to each sub-region, wherein the fan-shaped regions of each sub-region have the same area.

[0090] In this embodiment, after the system determines the center of the magnetic fluid in the target area, it sets a circle based on the center. Specifically, the system sets the first circle in the target area with the center O as the center and R=1 as the radius. 1 can be the length of a pixel. If the boundary of the first circle does not intersect with the boundary of the target area, the system sets the second circle in the target area with O as the center and R=2 as the radius. In this way, the system sets various concentric circles in the target area, and the boundaries of each concentric circle do not intersect with the boundary of the target area, and the concentric circle with the largest radius is used as the target circle. Since the angles corresponding to each sub-area are the same, the target circle is divided into multiple sector areas by each sub-area, that is, the area of ​​each sector area is the same. It should be noted that each concentric circle can be used as a target circle.

[0091] The system removes the fan-shaped area corresponding to each sub-area to obtain the convex area corresponding to each sub-area. The convex area can be regarded as the deformation of the magnetic fluid at the angle corresponding to the sub-area.

[0092] Step S702, determining the target magnetic energy value of the sub-area corresponding to the protruding area according to the number of pixel points corresponding to the protruding area, and the number is positively correlated with the target magnetic energy value.

[0093] Compared with the sub-area, the protruding area has fewer pixels, which means it is easier to calculate the target magnetic energy value. The system can determine the target magnetic energy value of the protruding area by the number of pixels corresponding to the protruding area. It should be noted that the more pixels there are in the protruding area, the greater the target magnetic energy value of the protruding area, that is, the number is positively correlated with the target magnetic energy value.

[0094] Furthermore, each time the system determines the direction of the sound, it will collect images of the area in the direction to determine whether there are users in the direction. If there are users, the target sub-area is marked as a historical target sub-area, and a protection time period is set. The protection time period refers to the user's set speaking time, that is, the system assumes that the user spoke during the protection time period. When subsequently calculating the magnetic capacity value of the sub-area, a set multiple is set for the sub-area, and the product of the magnetic energy value of the sub-area and the set multiple is the target magnetic capacity value of the sub-area.

[0095] In this regard, the system determines the magnetic energy value to be determined of the sub-area corresponding to the protruding area based on the number of pixels corresponding to the protruding area. If the sub-area is a historical target sub-area and the current time is in the protection time period of the sub-area, the target magnetic capacity value is determined based on the set multiple and the magnetic capacity value to be determined, that is, the target magnetic capacity value is the product of the set multiple and the magnetic capacity value to be determined. The set multiple can be an integer of any composite number, for example, the set multiple is 2.

[0096] In this embodiment, each protruding area is obtained by removing the area with the same area from each sub-area, and then the target magnetic energy value is determined by the number of pixels in each protruding area, thereby reducing the amount of calculation of the target magnetic energy value.

[0097] In one embodiment, there may be two target sub-areas. Specifically, the system sorts the sub-areas in descending order of target magnetic energy values, and the system takes the first and second ranked sub-areas as target sub-areas. The system obtains the angle between the two target sub-areas, and thus determines the direction of the sound through the angle.

[0098] In this embodiment, the direction from which the sound is emitted can be accurately determined through the sub-region with the highest magnetic capability value and the sub-region with the second highest magnetic capability value.

[0099] In one embodiment, the system further includes a second image acquisition module. After determining the direction from which the sound is emitted, the system controls the second image acquisition module to acquire a second image of an area corresponding to the direction.

[0100] Furthermore, after acquiring the second image, the system identifies the second image to determine whether the user is included in the second image. If the user is not included, the system removes the target sub-area from each sub-area, and redefines the target sub-area in each sub-area from which the target sub-area is removed. The system then redefines the direction of the sound according to the direction of the angle corresponding to the redetermined target sub-area, and finally controls the second image acquisition module to acquire an image of the area corresponding to the redetermined direction.

[0101] For example, if there is one target sub-region, the system removes the sub-region with the largest magnetic energy value from each sub-region, that is, removes the target sub-region, and redefines the target sub-region, that is, the sub-region with the second largest magnetic energy value is redetermined as the target sub-region. If there are two target sub-regions, when redefining the target sub-region, the sub-regions with the second and third largest magnetic energy values ​​are determined as the target sub-regions.

[0102] In this embodiment, the system controls the second image acquisition module to accurately capture the user who makes the sound.

[0103] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0104] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A sound positioning system, It is characterized in that include: A mounting part for containing magnetic fluid; A plurality of sound pickup modules are arranged around the magnetic fluid and are used to convert the picked-up sound into a voltage signal; A plurality of magnetic members are arranged around the magnetic fluid, each of the magnetic members is connected to one of the sound pickup modules, and is used to generate magnetic force under the action of the voltage signal to cause the magnetic fluid to deform; A first image acquisition module, arranged relative to the magnetic fluid, and used for acquiring an image of the magnetic fluid; A controller is connected to the first image acquisition module and is used to determine the direction of the sound according to the image.

2. The sound localization system according to claim 1, It is characterized in that The mounting member is provided with a groove for containing the magnetic fluid, each of the sound pickup modules and each of the magnetic members is arranged on the mounting member around the groove, and the cross-sectional area of ​​the groove is set to be larger than the cross-sectional area of ​​the magnetic fluid.

3. The sound localization system according to claim 2, It is characterized in that The bottom of the groove is made of a transparent material, and the first image acquisition module is arranged relative to the bottom.

4. The sound localization system according to claim 1, It is characterized in that The sound pickup module is provided with a microphone matrix and a cylindrical structure, an opening of the cylindrical structure is arranged relative to the sound collection surface of the microphone matrix, and another opening of the cylindrical structure is provided with one or more sound refraction components, and the microphone matrix is ​​used to collect sound that is not refracted by the sound refraction components.

5. The sound positioning system according to any one of claims 1 to 4, It is characterized in that The sound positioning system further includes a shell, which together with the mounting member forms a closed space, and the first image acquisition module and the controller are arranged in the closed space.

6. The sound positioning system according to any one of claims 1 to 4, It is characterized in that The sound positioning system further comprises a second image acquisition module connected to the controller, and the controller controls the second image acquisition module to acquire an image of the area corresponding to the direction.

7. A sound positioning method, applied to a sound positioning system, It is characterized in that The sound positioning system comprises a mounting member, a plurality of sound pickup modules, a plurality of magnetic members, a first image acquisition module and a controller, wherein the mounting member is used to contain magnetic fluid, a plurality of the sound pickup modules and a plurality of the magnetic members are arranged around the magnetic fluid, each of the magnetic members is connected to a sound pickup module, and the first image acquisition module is arranged relative to the magnetic fluid; The sound localization method comprises: Acquire a first image of the magnetic fluid acquired by the first image acquisition module; Taking the center of the magnetic fluid in the target area as the starting point, a plurality of line segments are set in the target area to divide the target area into a plurality of sub-areas, wherein the target area is the area of ​​the magnetic fluid in the first image, and the angles corresponding to the center of each sub-area are the same; Determine a target magnetic energy value of each sub-region according to the pixel points of the sub-region, and determine a target sub-region in each sub-region according to the magnetic energy value of each sub-region, wherein the magnetic energy value of the target sub-region is greater than the magnetic energy value of the sub-region not determined as the target sub-region; The direction from which the sound is emitted is determined according to the position of the angle corresponding to the target sub-area.

8. The sound localization method according to claim 7, It is characterized in that The step of determining the target magnetic energy value of each sub-area according to the pixel points of the sub-area comprises: Removing the fan-shaped areas of each of the sub-areas to obtain a convex area corresponding to each sub-area, wherein the areas of the fan-shaped areas of each of the sub-areas are the same; The target magnetic energy value of the sub-area corresponding to the protruding area is determined according to the number of pixel points corresponding to the protruding area, and the number is positively correlated with the target magnetic energy value.

9. The sound localization method according to claim 8, It is characterized in that The step of determining the target magnetic energy value of the sub-area corresponding to the protruding area according to the number of pixels corresponding to the protruding area includes: Determining the magnetic energy value to be determined of the sub-area corresponding to the protruding area according to the number of pixels corresponding to the protruding area; If the sub-region is a historical target sub-region and the current time is in the protection time period of the sub-region, the target magnetic energy value of the sub-region is determined according to the magnetic energy value to be determined and the set multiple.

10. The sound localization method according to claim 7, It is characterized in that There are two target sub-areas, and determining the direction of the sound according to the directions of the angles corresponding to the target sub-areas includes: Obtaining the angle between the two target sub-areas; The direction from which the sound is emitted is determined according to the angle.

11. The sound localization method according to any one of claims 7 to 10, It is characterized in that The sound positioning system further includes a second image acquisition module, and after determining the direction of the sound according to the position of the angle corresponding to the target sub-area, further includes: Control the second image acquisition module to acquire a second image of the area corresponding to the direction.

12. The sound localization method according to claim 11, It is characterized in that After controlling the second image acquisition module to acquire the second image of the area corresponding to the direction, the method further includes: If the second image does not contain the user, removing the target sub-region from each of the sub-regions; Re-determining the target sub-region in each of the sub-regions except the target sub-region; Re-determining the direction of the sound according to the direction of the angle corresponding to the re-determined target sub-area; The second image acquisition module is controlled to acquire an image of the area corresponding to the re-determined direction.

Images