Volume control method and system adaptive to user information

Abstract

The invention discloses a volume control method and system adaptive to user information, and the method comprises the steps: collecting a plurality of two-dimensional user images of all users in an activity region through a first camera and a second camera, obtaining a plurality of groups of user image pairs, carrying out the head image region screening of the plurality of groups of user image pairs, obtaining a plurality of groups of head region images, and carrying out the recognition of the head region images. Performing feature point processing on the plurality of groups of head area images to obtain feature point pair information of the plurality of groups of head images, restoring a plurality of groups of three-dimensional point coordinate data of the head area of the user from the plurality of two-dimensional user images through preset parameters and the feature point pair information of the head images, and determining the head area of the user according to the plurality of groups of three-dimensional point coordinate data. And calculating a first distance value and a second distance value, respectively calculating a first volume value and a second volume value according to a preset calculation formula, pre-acquired age information of the user, the first distance value and the second distance value, controlling the first loudspeaker to output the first volume value, and controlling the second loudspeaker to output the second volume value.

Description

Technical Field

[0001] The present application relates to the technical field of volume control, and more specifically, to a volume control method and system adaptive to user information. Background Art

[0002] Bank counters are responsible for handling various bank branch businesses and are one of the core platforms for bank branch business interaction. Therefore, the user experience of bank counters is crucial.

[0003] However, existing bank counters have the following problems: First, most bank counters have only one loudspeaker on one side, which causes the sound heard by the user's ear on the same side as the loudspeaker to be too loud, while the sound heard by the ear on the other side is too soft, causing discomfort to the user. Second, a small number of bank counters are equipped with multiple loudspeakers with fixed positions and consistent volume, but the user's position relative to the counter will change due to the user's personal habits, which may be to the left or right, too far or too close. At this time, the loudspeaker that is too close to the user will sound too loud, while the loudspeaker that is too far from the user will sound too soft, causing discomfort to the user. Third, users of different age groups have different auditory experiences. Elderly users have weaker hearing, so the loudspeaker volume should be louder, but a louder volume will be too harsh for young users.

[0004] Therefore, how to improve the user's auditory experience at the bank counter is an urgent problem to be solved in this application. Summary of the invention

[0005] In view of this, the present application discloses a volume control method and system that is adaptive to user information, aiming to achieve automatic volume control based on different user ages and location information, and effectively improve the user's auditory experience at the bank counter.

[0006] In order to achieve the above purpose, the disclosed technical solution is as follows:

[0007] The first aspect of the present application discloses a volume control method that is adaptive to user information, the method comprising:

[0008] Collecting multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of user image pairs;

[0009] Performing head image region screening on the multiple groups of user image pairs to obtain multiple groups of head region images;

[0010] Performing feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images;

[0011] Restore multiple sets of three-dimensional point coordinate data of the user's head area from the multiple two-dimensional user images by using preset parameters and feature point pair information of the head image;

[0012] Calculate a first distance value and a second distance value according to the multiple sets of three-dimensional point coordinate data; wherein the first distance value is the distance value between the center point of the user's head area and the first speaker; and the second distance value is the distance value between the center point of the user's head area and the second speaker;

[0013] Calculate a first volume value and a second volume value respectively according to a preset calculation formula, the pre-acquired user age information, the first distance value and the second distance value;

[0014] The first speaker is controlled to output the first volume value, and the second speaker is controlled to output the second volume value.

[0015] Preferably, before collecting a plurality of two-dimensional user images of all users in the activity area by the first camera and the second camera to obtain a plurality of groups of user image pairs, the method further includes:

[0016] Start system initialization;

[0017] The system initialization process includes:

[0018] Collecting multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of image pairs;

[0019] Input the plurality of image pairs into a calculation control unit, and calculate the camera posture change information between the first camera and the second camera by calling the image feature matching algorithm and the related functions of the eight-point algorithm built into the cross-platform computer vision library through the calculation control unit; wherein the camera posture change information includes at least a rotation matrix and a translation vector;

[0020] The actual length value of the baseline distance between the installation positions of the first camera and the second camera is obtained, and the actual length value is input into the calculation control unit to complete the system initialization process.

[0021] Preferably, the preset parameters at least include the camera posture change information, the baseline distance value and the camera intrinsic parameter matrix information, and the method of restoring multiple sets of three-dimensional point coordinate data of the user head area from the multiple two-dimensional user images by using the preset parameters and the feature point pair information of the head image includes:

[0022] Acquire an actual distance between the first camera and the second camera, and determine a value corresponding to the actual distance as the baseline distance value;

[0023] According to the camera posture change information, the baseline distance value, the camera intrinsic parameter matrix information and the feature point pair information of the head image, the actual position information of each feature point in the user's head area in the three-dimensional space is restored from the multiple two-dimensional user images to obtain multiple sets of three-dimensional point coordinate data.

[0024] Preferably, the first volume value and the second volume value are calculated respectively according to a preset calculation formula, the pre-acquired user age information, the first distance value and the second distance value, including:

[0025] The expression of the preset calculation formula is as follows:

[0026]

[0027] Where, f(dist, age) is the volume value; dist is the distance between the center point of the user's head area and the speaker; age is the user's age information; e is a natural constant; dB is decibel;

[0028] The user's age information, the first distance value, and the second distance value are input into the preset calculation formula to obtain a first volume value and a second volume value.

[0029] Preferably, the performing head image region screening on the plurality of groups of user image pairs to obtain a plurality of groups of head region images comprises:

[0030] The head image regions of the plurality of groups of user image pairs are screened by a head screening algorithm to obtain a plurality of groups of head region image information.

[0031] Preferably, the performing feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images includes:

[0032] The plurality of groups of head region images are processed by an image feature point extraction and matching algorithm to obtain feature point pair information of the head images.

[0033] The second aspect of the present application discloses a volume control system that is adaptive to user information, the system comprising:

[0034] A collection unit, configured to collect multiple two-dimensional user images of all users in the activity area through a first camera and a second camera to obtain multiple groups of user image pairs;

[0035] A screening unit, configured to screen the plurality of groups of user image pairs for head image regions to obtain a plurality of groups of head region images;

[0036] A processing unit, configured to perform feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images;

[0037] A restoration unit, configured to restore multiple sets of three-dimensional point coordinate data of the user's head region from the multiple two-dimensional user images by using preset parameters and feature point pair information of the head image;

[0038] A first calculation unit is used to calculate a first distance value and a second distance value according to the multiple sets of three-dimensional point coordinate data; wherein the first distance value is the distance value between the center point of the user's head area and the first speaker; and the second distance value is the distance value between the center point of the user's head area and the second speaker;

[0039] a second calculation unit, configured to calculate a first volume value and a second volume value respectively according to a preset calculation formula, the pre-acquired age information of the user, the first distance value and the second distance value;

[0040] A control unit is used to control the first speaker to output the first volume value, and control the second speaker to output the second volume value.

[0041] Preferably, it also includes:

[0042] Start initialization unit, used to start system initialization;

[0043] The startup initialization unit comprises:

[0044] A collection module, used to collect multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of image pairs;

[0045] A calculation module, used for inputting the plurality of image pairs into a calculation control unit, and calculating the camera posture change information between the first camera and the second camera by calling the image feature matching algorithm and the related functions of the eight-point algorithm built into the cross-platform computer vision library through the calculation control unit; wherein the camera posture change information includes at least a rotation matrix and a translation vector;

[0046] The first acquisition module is used to obtain the actual length value of the baseline distance between the installation positions of the first camera and the second camera, and input the actual length value into the calculation control unit to complete the system initialization process.

[0047] Preferably, the preset parameters at least include the camera posture change information, the baseline distance value and the camera intrinsic parameter matrix information, and the restoration unit includes:

[0048] A second acquisition module is used to acquire an actual distance between the first camera and the second camera, and determine a value corresponding to the actual distance as the baseline distance value;

[0049] A restoration module is used to restore the actual position information of each feature point in the user's head area in the three-dimensional space from the multiple two-dimensional user images according to the camera posture change information, the baseline distance value, the camera internal parameter matrix information and the feature point pair information of the head image, so as to obtain multiple groups of three-dimensional point coordinate data.

[0050] Preferably, the second computing unit is specifically used for:

[0051] The expression of the preset calculation formula is as follows:

[0052]

[0053] Where, f(dist, age) is the volume value; dist is the distance between the center point of the user's head area and the speaker; age is the user's age information; e is a natural constant; dB is decibel;

[0054] The user's age information, the first distance value, and the second distance value are input into the preset calculation formula to obtain a first volume value and a second volume value.

[0055] Through the above technical solution, it can be known that the present application discloses a volume control method and system for adaptive user information, which collects multiple two-dimensional user images of all users in the active area through a first camera and a second camera to obtain multiple groups of user image pairs, performs head image area screening on the multiple groups of user image pairs to obtain multiple groups of head area images, performs feature point processing on the multiple groups of head area images to obtain feature point pair information of the multiple groups of head images, restores multiple groups of three-dimensional point coordinate data of the user head area from the multiple two-dimensional user images through preset parameters and the feature point pair information of the head images, calculates a first distance value and a second distance value according to the multiple groups of three-dimensional point coordinate data, wherein the first distance value is the distance value between the center point of the user head area and the first speaker, and the second distance value is the distance value between the center point of the user head area and the second speaker, and calculates a first volume value and a second volume value according to a preset calculation formula, the user's age information obtained in advance, the first distance value and the second distance value, respectively, controls the first speaker to output the first volume value, and controls the second speaker to output the second volume value.

[0056] Through the above scheme, the position of the user in the three-dimensional space is calculated slowly and in real time through computer vision technology, which overcomes the shortcomings of the traditional method of using sensors for distance perception, can accurately identify the user's head area, and automatically adjust the volume of the first loudspeaker and the second loudspeaker according to the distance between the user's head and the first loudspeaker and the second loudspeaker, thereby realizing automatic volume control based on different user ages and location information, and effectively improving the user's auditory experience at the bank counter. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0058] Figure 1 A schematic diagram of the overall structure of a volume control device that is adaptive to user information disclosed in an embodiment of the present application;

[0059] Figure 2 A schematic diagram of the overall structure of another volume control device that is adaptive to user information disclosed in an embodiment of the present application;

[0060] Figure 3 A schematic diagram of the working process of the volume control device for adaptive user information disclosed in an embodiment of the present application;

[0061] Figure 4 A flow chart of a volume control method for adaptive user information disclosed in an embodiment of the present application;

[0062] Figure 5 A schematic diagram of a volume control system that is adaptive to user information disclosed in an embodiment of the present application;

[0063] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0066] As can be seen from the background technology, the existing bank counters have the following problems: First, most bank counters have only one unilateral loudspeaker, which causes the sound heard by the user's ear on the same side as the loudspeaker to be too loud, while the sound heard by the ear on the other side is too small, causing discomfort to the user. Second, a small number of bank counters are equipped with multiple fixed loudspeakers with the same volume, but the position of the user relative to the counter will change due to the user's personal habits, which may be to the left or to the right, or too far or too close. At this time, the loudspeaker that is too close to the user will appear to be too loud, while the loudspeaker that is too far from the user will appear to be too small, causing discomfort to the user. Third, the auditory experience of users of different age groups is different. The hearing of elderly users is weak, and the loudspeaker volume should be louder, but a louder volume will appear too harsh to young users. Therefore, how to improve the auditory experience of users at bank counters is a problem that this application urgently needs to solve.

[0067] In order to solve the above problems, the present application discloses a volume control method and system for adaptive user information, which uses computer vision technology to slowly and in real time calculate the position of the user in the three-dimensional space, overcomes the shortcomings of the traditional method of using sensors for distance perception, can accurately identify the user's head area, and automatically adjust the volume of the first loudspeaker and the second loudspeaker according to the distance between the user's head and the first loudspeaker and the second loudspeaker, thereby realizing automatic volume control based on different user ages and location information, and effectively improving the user's auditory experience at the bank counter. The specific implementation method is specifically described through the following embodiments.

[0068] refer to Figure 1 As shown, it is a schematic diagram of the overall structure of a volume control device for adaptive user information disclosed in an embodiment of the present application. The volume control device for adaptive user information is composed of two cameras (a first camera and a second camera), two speakers (a first camera and a second camera), and a computing control unit.

[0069] Among them, the first camera and the second camera are preferably monocular cameras.

[0070] After the first camera and the second camera are installed and fixed, the system is initialized. The two monocular cameras take multiple sets of images and input the multiple sets of images into the calculation control unit. The calculation control unit calls the image feature matching algorithm and the 8-point algorithm related functions built into the image open source code library (openCV) to calculate the posture change information between the two cameras and obtain the specific values ​​of the rotation matrix (R) and the translation vector (t). Figure 1 The value of the actual distance (B0) between the first camera and the second camera in the right figure is input into the calculation control unit to complete the initialization process.

[0071] Among them, the image feature matching algorithm: Feature points refer to the more representative points in the image. When the scene and camera perspective change, these representative points can still be found from the image. Feature points are composed of two parts: key points and descriptors. Key points refer to the position of the feature point in the image. Some feature points also have information such as direction and size. The descriptor is usually a vector that describes the information of the pixels around the key point in a certain artificially designed way. As long as the descriptors of two feature points are close in distance in the vector space, they can be considered to be the same feature points.

[0072] openCV is the most famous open source image code library in the field of computer vision. It encapsulates various mature image processing algorithms in the industry and is a widely used basic code library in the field of image processing.

[0073] The 8-point method is an algorithm that uses 8 pairs of feature point information to calculate the essential matrix E=t∧R, and then calculates the specific values ​​of R and t.

[0074] When in use, the calculation control unit reads the user's age information (age) in the counter system, and the unit of age is year (year). The reference value of the volume is set according to the user's age. The older the user is, the larger the reference value is, and the younger the user is, the smaller the reference value is.

[0075] At the same time, the first camera and the second camera are responsible for capturing user images and transmitting the user images to the computing control unit, which calculates the specific position of the user's head in three-dimensional space, thereby calculating the distance (dist) between the user's head and the first speaker, as well as the distance between the user's head and the second speaker, where the unit of dist is centimeters (cm).

[0076] To calculate the distance between the user's head and the first speaker, and the distance between the user's head and the second speaker, refer to Figure 2 shown.

[0077] Figure 2 , if the user is at user position one, then according to the user being at user position one, a first specific position of the user's head in the three-dimensional space is obtained, a distance (L1) between the first specific position of the user's head in the three-dimensional space and the first speaker is calculated, and a value of a distance (R1) between the first specific position of the user's head in the three-dimensional space and the second speaker is calculated;

[0078] If the user is at user position 2, then according to the user being at user position 2, the second specific position of the user's head in the three-dimensional space is obtained, and the distance (L2) between the second specific position of the user's head in the three-dimensional space and the first speaker is calculated. And the value of the distance (R2) between the second specific position of the user's head in the three-dimensional space and the second speaker is calculated;

[0079] Then, the volume of the speaker is controlled according to the specific values ​​of L1, R1, L2, and R2. The farther the distance, the higher the corresponding volume should be set, and the closer the distance, the lower the corresponding volume should be set. The distance between the user's head and the first speaker and the distance between the user and the second speaker can be calculated according to the above calculation method at different positions of the user's head in three-dimensional space.

[0080] Regarding the problem of calculating the corresponding volume value according to the preset calculation formula, the user's age and the user's location, the preset calculation formula is specifically shown in formula (1).

[0081]

[0082] Among them, f(dist, age) is the volume value; dist is the distance between the center point of the user's head area and the speaker; age is the user's age information; e is a natural constant; dB is decibel.

[0083] The age range of users who handle business at the counter is basically between [10, 120], and due to the limited range of counter activities, the distance between the center of the user's head area and each speaker is basically only between [30, 150] cm. According to the information, in a low-noise scene such as a bank branch, the sound of people talking is generally about 40-60dB (decibels), while talking to people with hearing loss requires 60-80dB or even higher decibels to have a normal conversation. In addition, human hearing will decline faster and faster with age, and the attenuation of point sound sources with the increase of propagation distance also shows a logarithmic attenuation trend.

[0084] Therefore, considering various factors, this solution proposes the calculation method of formula (1) to accurately calculate the volume that the speaker should set according to different user information. Based on the 40dB volume, the algorithm generates a volume scaling range of [1.057, 1.948] within the user age range [10, 120], which is consistent with the trend that the volume enhancement becomes stronger with age; at the same time, within the distance range [30, 120] between the user and each speaker, the volume scaling range is [0.699, 1.301], which is basically consistent with the attenuation trend of point source propagation with distance.

[0085] This application uses computer vision technology to calculate the user's position in three-dimensional space in slow real-time, thereby calculating the distance from the user's position to each speaker, and automatically adjusting the volume according to the distance and user age information, thereby effectively improving the user experience. The slow real-time in this application scenario specifically refers to: the shooting frequency is very low, controlled at once per second, and there is no need to restore the three-dimensional information of all point clouds in the entire scene. Only the three-dimensional information of a few feature points is needed to estimate the approximate user position, which greatly reduces the amount of calculation and has sufficient calculation time.

[0086] In order to facilitate the understanding of the overall workflow and structure of each module of the adaptive user information volume control of this solution, please refer to Figure 3 content. Figure 3 A schematic diagram of the working process of the volume control device adapted to user information disclosed in an embodiment of the present application is shown.

[0087] Figure 3 In the device initialization module:

[0088] First, the device initialization module collects images through the camera to generate multiple sets of image pairs;

[0089] The plurality of image pairs are transmitted to a computing control unit, and the computing control unit calls an image feature point extraction and matching algorithm to process the plurality of image pairs, and outputs image feature point pair information;

[0090] The calculation control unit continues to use the 8-point method to solve the posture change information between the two cameras, which is represented by the rotation matrix R and the translation vector t. At the same time, the actual length value of the baseline distance between the installation positions of the two cameras is measured and input into the calculation control unit to complete the initialization.

[0091] The device's formal working module:

[0092] When the formal working module of the device is working, the user image information is collected through the first camera and the second camera to generate multiple groups of user image pairs;

[0093] The calculation control unit calls the head screening algorithm to process the multiple groups of image pairs and outputs the information of the head image area;

[0094] The calculation control unit calls the image feature point extraction and matching algorithm to output feature point pair information of the head image;

[0095] The image feature point three-dimensionalization module combines the posture change information between the two cameras, the baseline distance value, the internal parameter matrix information of the first camera (i.e., the value of the internal parameter matrix K1) and the internal parameter matrix information of the second camera (i.e., the value of the internal parameter matrix K2), and the feature point pair information of the head image, and restores multiple sets of three-dimensional point coordinate data of the user's head area (i.e., the actual position information of each feature point in the user's head area in the three-dimensional space) from the two-dimensional image information;

[0096] The distance calculation module calculates a first distance value between the center point of the user's head area and the first speaker, and a second distance value between the center point of the user's head area and the second speaker according to the multiple sets of three-dimensional point coordinate data of the user's head area;

[0097] The volume calculation module combines the user age information and dist data (i.e., the distance value between the center point of the user's head area and the first speaker, and the distance value between the center point of the user's head area and the second speaker) read from the counter, calls formula (1) to calculate the first volume value and the second volume value, respectively, and controls the first speaker to output the first volume value, and controls the second speaker to output the second volume value.

[0098] In the embodiment of the present application, two monocular cameras are used to identify the specific spatial position of the user's head area near the counter, which overcomes the shortcomings of the traditional method of using sensors for distance perception, can accurately identify the user's head area, and calculate the spatial position of the user's head area in the entire scene, and has the advantage of low cost.

[0099] At the same time, the device innovatively proposes an algorithm to quantitatively calculate the volume that should be set for the loudspeaker at the bank branch counter based on two pieces of information: the distance between the user's head and the loudspeaker and the user's age.

[0100] At present, there is no relevant research on "volume control device for adaptive user information in bank counter scenarios". This application fills the gap in this field and effectively improves the auditory experience of bank counter users.

[0101] The main points protected in this application are the innovative combination of product structure and technology used, as follows:

[0102] 1. The structure of the bank counter volume control device that adapts to user information realizes intelligent volume control of the bank counter by adding two monocular cameras, two speakers and a computing control unit to the ordinary bank counter.

[0103] 2. The method of adaptively controlling the volume of a bank counter based on user information is as follows: first, a volume baseline value is set according to the user's age; then, by shooting the user from multiple angles, the distance between the user's head area and the speaker is calculated; and the volume of the speaker is adjusted again based on the baseline value according to the distance.

[0104] 3. A quantitative algorithm is designed to calculate the volume that should be set based on two variables: user age and the distance dist between the user's head area and the speaker.

[0105] Beneficial effects of the embodiments of the present application:

[0106] The computer vision technology is used to calculate the user's position in three-dimensional space in real time, overcoming the shortcomings of the traditional method of using sensors for distance perception. The system can accurately identify the user's head area and automatically adjust the volume of the first loudspeaker and the second loudspeaker according to the distance between the user's head and the first loudspeaker and the second loudspeaker, thereby realizing automatic volume control based on different user ages and location information, effectively improving the user's auditory experience at the bank counter.

[0107] refer to Figure 4 FIG. 1 is a flow chart of a volume control method for adaptive user information disclosed in an embodiment of the present application. The volume control method for adaptive user information is applicable to the above-mentioned embodiment. Figure 1 and Figure 2 The volume control method based on adaptive user information mainly includes the following steps:

[0108] S401: Start system initialization.

[0109] The system initialization process includes:

[0110] Collecting multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of image pairs;

[0111] Input the plurality of image pairs into a calculation control unit, and calculate the camera posture change information between the first camera and the second camera by calling the image feature matching algorithm and the related functions of the eight-point algorithm built in the cross-platform computer vision library (openCV) through the calculation control unit; wherein the camera posture change information at least includes a rotation matrix (R) and a translation vector (t);

[0112] The actual length value of the baseline distance between the installation positions of the first camera and the second camera is obtained, and the actual length value is input into the calculation control unit to complete the system initialization process.

[0113] S402: Collect multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of user image pairs.

[0114] S403: Perform head image region screening on the multiple groups of user image pairs to obtain multiple groups of head region images.

[0115] In S403, head image regions are screened for the plurality of groups of user image pairs using a head screening algorithm to obtain a plurality of groups of head region image information.

[0116] S404: Perform feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images.

[0117] In S404, the plurality of groups of head region images are processed by an image feature point extraction and matching algorithm to obtain feature point pair information of the head images.

[0118] S405: Restore multiple groups of three-dimensional point coordinate data of the user's head area from multiple two-dimensional user images using preset parameters and feature point pair information of the head image.

[0119] The preset parameters include at least camera posture change information, baseline distance value and camera intrinsic parameter matrix information.

[0120] The matrix composed of the four variables in the middle is called the camera intrinsic parameter matrix information K. Through the camera intrinsic parameter matrix information K, the mapping relationship between a point P (X, Y, Z) in the three-dimensional space and its pixel coordinates (u, v) in the camera pixel plane can be described. The intrinsic parameters of the camera are fixed after leaving the factory and will not change during use. The intrinsic parameter information of the monocular camera used in this solution is specifically shown in formula (2).

[0121]

[0122] Among them, f x is the horizontal component of the focal length in the pixel coordinate system; f y is the vertical component of the distance in the pixel coordinate system; c x c is the horizontal component of the coordinates of the principal point (optical center) in the pixel coordinate system; y It is the vertical component of the coordinates of the principal point (optical center) in the pixel coordinate system; X, Y and Z are the coordinates of a point P in three-dimensional space.

[0123] Acquire an actual distance between the first camera and the second camera, and determine a value corresponding to the actual distance as a baseline distance value;

[0124] According to the camera pose change information, baseline distance value, camera intrinsic parameter matrix information and feature point pair information of the head image, the actual position information of each feature point in the user's head area in the three-dimensional space is restored from multiple two-dimensional user images to obtain multiple sets of three-dimensional point coordinate data.

[0125] Among them, the camera pose change information is used to describe how to change from one camera coordinate system to another camera coordinate system, which can be divided into a rotation change and a translation change. The rotation change can be represented by the rotation matrix R, and the translation change of the origin can be represented by the translation vector t.

[0126] S406: Calculate a first distance value and a second distance value based on multiple sets of three-dimensional point coordinate data; wherein the first distance value is the distance value between the center point of the user's head area and the first speaker; and the second distance value is the distance value between the center point of the user's head area and the second speaker.

[0127] S407: Calculate a first volume value and a second volume value respectively according to a preset calculation formula, the pre-acquired user age information, the first distance value and the second distance value.

[0128] The expression of the preset calculation formula is shown in the above formula (1).

[0129] The user's age information, the first distance value, and the second distance value are input into a preset calculation formula to obtain a first volume value and a second volume value.

[0130] S408: Control the first speaker to output a first volume value, and control the second speaker to output a second volume value.

[0131] The execution process and execution principle of S401-S408 are similar to those of the above embodiment. Figure 3 The execution process and execution principle are consistent, which can be used as a reference and will not be repeated here.

[0132] The beneficial effects of the embodiments of the present application are as follows: the position of the user in the three-dimensional space is calculated slowly and in real time through computer vision technology, which overcomes the shortcomings of the traditional method of using sensors for distance perception, can accurately identify the user's head area, and automatically adjust the volume of the first loudspeaker and the second loudspeaker according to the distance between the user's head and the first loudspeaker and the second loudspeaker, thereby realizing automatic volume control based on different user ages and position information, and effectively improving the user's auditory experience at the bank counter.

[0133] Based on the above embodiments Figure 4 A volume control method for adaptive user information is disclosed, and an embodiment of the present application also discloses a volume control system for adaptive user information, such as Figure 5 As shown, the volume control system adapted to user information includes:

[0134] The acquisition unit 501 is used to acquire multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of user image pairs;

[0135] A screening unit 502 is used to screen the head image regions of the plurality of user image pairs to obtain a plurality of head region images;

[0136] A processing unit 503 is used to perform feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images;

[0137] The restoration unit 504 is used to restore multiple sets of three-dimensional point coordinate data of the user's head area from multiple two-dimensional user images by using preset parameters and feature point pair information of the head image;

[0138] The first calculation unit 505 is used to calculate a first distance value and a second distance value according to the multiple sets of three-dimensional point coordinate data; wherein the first distance value is the distance value between the center point of the user's head area and the first speaker; and the second distance value is the distance value between the center point of the user's head area and the second speaker;

[0139] A second calculation unit 506, configured to calculate a first volume value and a second volume value respectively according to a preset calculation formula, the pre-acquired user age information, the first distance value and the second distance value;

[0140] The control unit 507 is used to control the first speaker to output a first volume value, and control the second speaker to output a second volume value.

[0141] Furthermore, the volume control system adapted to user information further includes:

[0142] Start initialization unit, used to start system initialization;

[0143] Start the initialization unit, including:

[0144] A collection module, used to collect multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of image pairs;

[0145] A calculation module is used to input multiple sets of image pairs into a calculation control unit, and the calculation control unit calls the image feature matching algorithm and the related functions of the eight-point algorithm built into the cross-platform computer vision library to calculate the camera posture change information between the first camera and the second camera; wherein the camera posture change information at least includes a rotation matrix and a translation vector;

[0146] The first acquisition module is used to obtain the actual length value of the baseline distance between the installation positions of the first camera and the second camera, and input the actual length value into the calculation control unit to complete the system initialization process.

[0147] Furthermore, the restoring unit 504 includes:

[0148] A second acquisition module is used to acquire an actual distance between the first camera and the second camera, and determine a value corresponding to the actual distance as a baseline distance value;

[0149] The restoration module is used to restore the actual position information of each feature point in the user's head area in three-dimensional space from multiple two-dimensional user images according to the camera posture change information, baseline distance value, camera internal parameter matrix information and feature point pair information of the head image, and obtain multiple sets of three-dimensional point coordinate data.

[0150] Furthermore, the second calculation unit 506 is specifically configured to:

[0151] The expression of the preset calculation formula is as follows:

[0152]

[0153] Where, f(dist, age) is the volume value; dist is the distance between the center point of the user's head area and the speaker; age is the user's age information; e is a natural constant; dB is decibel;

[0154] The user's age information, the first distance value, and the second distance value are input into a preset calculation formula to obtain a first volume value and a second volume value.

[0155] Furthermore, the screening unit 502 is specifically configured to screen the head image regions of the plurality of groups of user image pairs by using a head screening algorithm to obtain a plurality of groups of head region image information.

[0156] Furthermore, the processing unit 503 is specifically configured to process the plurality of groups of head region images through an image feature point extraction and matching algorithm to obtain feature point pair information of the head images.

[0157] The beneficial effects of the embodiments of the present application are as follows: the position of the user in the three-dimensional space is calculated slowly and in real time through computer vision technology, which overcomes the shortcomings of the traditional method of using sensors for distance perception, can accurately identify the user's head area, and automatically adjust the volume of the first loudspeaker and the second loudspeaker according to the distance between the user's head and the first loudspeaker and the second loudspeaker, thereby realizing automatic volume control based on different user ages and position information, and effectively improving the user's auditory experience at the bank counter.

[0158] An embodiment of the present application further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the volume control method for adaptive user information as described above.

[0159] The present application also provides an electronic device, whose structural diagram is as follows: Figure 6As shown, it specifically includes a memory 601 and one or more instructions 602, wherein the one or more instructions 602 are stored in the memory 601 and are configured to be executed by one or more processors 603 to execute the one or more instructions 602 to perform the above-mentioned volume control method of adaptive user information.

[0160] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0161] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0162] The steps in the methods of the embodiments of the present application can be adjusted in order, combined, and deleted according to actual needs.

[0163] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0164] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0165] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A volume control method adapted to user information, characterized in that: The method comprises: Collecting multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of user image pairs; Performing head image region screening on the multiple groups of user image pairs to obtain multiple groups of head region images; Performing feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images; Restore multiple sets of three-dimensional point coordinate data of the user's head area from the multiple two-dimensional user images by using preset parameters and feature point pair information of the head image; Calculate a first distance value and a second distance value according to the multiple sets of three-dimensional point coordinate data; wherein the first distance value is the distance value between the center point of the user's head area and the first speaker; and the second distance value is the distance value between the center point of the user's head area and the second speaker; Calculate a first volume value and a second volume value respectively according to a preset calculation formula, the pre-acquired user age information, the first distance value and the second distance value; The first speaker is controlled to output the first volume value, and the second speaker is controlled to output the second volume value.

2. The method according to claim 1, characterized in that Before collecting a plurality of two-dimensional user images of all users in the activity area by the first camera and the second camera to obtain a plurality of groups of user image pairs, the method further includes: Start system initialization; The system initialization process includes: Collecting multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of image pairs; Input the plurality of image pairs into a calculation control unit, and calculate the camera posture change information between the first camera and the second camera by calling the image feature matching algorithm and the related functions of the eight-point algorithm built into the cross-platform computer vision library through the calculation control unit; wherein the camera posture change information includes at least a rotation matrix and a translation vector; The actual length value of the baseline distance between the installation positions of the first camera and the second camera is obtained, and the actual length value is input into the calculation control unit to complete the system initialization process.

3. The method according to claim 2, characterized in that The preset parameters at least include the camera posture change information, the baseline distance value and the camera intrinsic parameter matrix information, and the multiple sets of three-dimensional point coordinate data of the user head area are restored from the multiple two-dimensional user images through the preset parameters and the feature point pair information of the head image, including: Acquire an actual distance between the first camera and the second camera, and determine a value corresponding to the actual distance as the baseline distance value; According to the camera posture change information, the baseline distance value, the camera intrinsic parameter matrix information and the feature point pair information of the head image, the actual position information of each feature point in the user's head area in the three-dimensional space is restored from the multiple two-dimensional user images to obtain multiple sets of three-dimensional point coordinate data.

4. The method according to claim 1, characterized in that: The first volume value and the second volume value are calculated respectively according to a preset calculation formula, the pre-acquired user age information, the first distance value and the second distance value, including: The expression of the preset calculation formula is as follows: 其 In the equation, f(dist, age) is the volume value; dist is the distance between the center of the user's head area and the speaker; age is the user's age information; e is a natural constant; dB is decibel; The user's age information, the first distance value, and the second distance value are input into the preset calculation formula to obtain a first volume value and a second volume value.

5. The method according to claim 1, characterized in that The step of screening the plurality of groups of user image pairs for head image regions to obtain a plurality of groups of head region images comprises: The head image regions of the plurality of groups of user image pairs are screened by a head screening algorithm to obtain a plurality of groups of head region image information.

6. The method according to claim 1, characterized in that The performing feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images includes: The plurality of groups of head region images are processed by an image feature point extraction and matching algorithm to obtain feature point pair information of the head images.

7. A volume control system that is adaptive to user information, characterized in that: The system comprises: A collection unit, configured to collect multiple two-dimensional user images of all users in the activity area through a first camera and a second camera to obtain multiple groups of user image pairs; A screening unit, configured to screen the plurality of groups of user image pairs for head image regions to obtain a plurality of groups of head region images; A processing unit, configured to perform feature point processing on the multiple groups of head region images to obtain feature point pair information of the multiple groups of head images; A restoration unit, configured to restore multiple sets of three-dimensional point coordinate data of the user's head region from the multiple two-dimensional user images by using preset parameters and feature point pair information of the head image; A first calculation unit is used to calculate a first distance value and a second distance value according to the multiple sets of three-dimensional point coordinate data; wherein the first distance value is the distance value between the center point of the user's head area and the first speaker; and the second distance value is the distance value between the center point of the user's head area and the second speaker; a second calculation unit, configured to calculate a first volume value and a second volume value respectively according to a preset calculation formula, the pre-acquired age information of the user, the first distance value and the second distance value; A control unit is used to control the first speaker to output the first volume value, and control the second speaker to output the second volume value.

8. The system according to claim 7, characterized in that Also includes: Start initialization unit, used to start system initialization; The startup initialization unit comprises: A collection module, used to collect multiple two-dimensional user images of all users in the activity area through the first camera and the second camera to obtain multiple groups of image pairs; A calculation module, used for inputting the plurality of image pairs into a calculation control unit, and calculating the camera posture change information between the first camera and the second camera by calling the image feature matching algorithm and the related functions of the eight-point algorithm built into the cross-platform computer vision library through the calculation control unit; wherein the camera posture change information includes at least a rotation matrix and a translation vector; The first acquisition module is used to obtain the actual length value of the baseline distance between the installation positions of the first camera and the second camera, and input the actual length value into the calculation control unit to complete the system initialization process.

9. The system according to claim 8, characterized in that The preset parameters at least include the camera posture change information, the baseline distance value and the camera internal parameter matrix information, and the restoration unit includes: A second acquisition module is used to acquire an actual distance between the first camera and the second camera, and determine a value corresponding to the actual distance as the baseline distance value; A restoration module is used to restore the actual position information of each feature point in the user's head area in the three-dimensional space from the multiple two-dimensional user images according to the camera posture change information, the baseline distance value, the camera internal parameter matrix information and the feature point pair information of the head image, so as to obtain multiple groups of three-dimensional point coordinate data.

10. The system according to claim 7, characterized in that The second computing unit is specifically configured to: The expression of the preset calculation formula is as follows: 其 in, f(dist,age) 为 Volume value; dist 为 The distance between the center of the user's head area and the speaker; age is the user's age information; e is a natural constant; dB is decibel; The user's age information, the first distance value, and the second distance value are input into the preset calculation formula to obtain a first volume value and a second volume value.

Images