Intelligent blind-assisting glasses system and method for stereoscopic perception of environment

Abstract

The application discloses a kind of stereoscopic perception environment's intelligent assistive glasses system and method, it is related to voice prompt field, it solves the problem that current intelligent assistive glasses voice prompt lacks accuracy, comprising: data acquisition module: radar scanning is carried out to external environment, and environment data is obtained;Model construction module: environment data is handled, and environment data is mapped in three-dimensional space, mapping value is obtained, according to mapping value, model construction is carried out to external environment, and environment model is obtained;Intelligent judgment module: the action information of the user of intelligent assistive glasses is collected, according to the action information of user, obstacle judgment is carried out in combination with environment model, and audio feedback is carried out to user;Voice interaction module: audio feedback is independently set, and different audio feedback is obtained according to the setting result of user;The application can effectively improve the accuracy of intelligent assistive glasses voice prompt, guarantee the travel safety of visually impaired people.

Description

A smart assistive glasses system and method for stereoscopic environmental perception Technical Field

[0001] This invention pertains to intelligent assistive glasses for the blind, and more specifically to the field of voice prompts. Specifically, it relates to an intelligent assistive glasses system and method for three-dimensional environmental perception. Background Technology

[0002] Smart glasses for the blind are key devices to help visually impaired people walk. They are also voice prompt devices that guide visually impaired people to explore an accessible world, help them pursue their dreams in the new era, and ensure the safety of people with low vision when they go out.

[0003] Existing smart assistive glasses for the blind have the following specific drawbacks when in use:

[0004] 1. Existing smart glasses for the blind have limited functionality and cannot be customized to meet user needs. They are not widely applicable to users with different preferences and are difficult to promote in the market. For example, smart glasses for the blind may alert you to objects within one meter, but some visually impaired people may not need to alert you to all objects at close range, or they may want more detailed descriptions or different prompts for objects in certain specific scenarios.

[0005] 2. Existing smart assistive glasses for the blind also have shortcomings in the three-dimensionality and accuracy of environmental perception, making it difficult to accurately determine the specific location, size and shape of obstacles, thus affecting the convenience and safety of use; and making it difficult to guarantee the quality of life and travel safety of visually impaired people.

[0006] To this end, we propose an intelligent assistive glasses system and method for stereoscopic environmental perception. Summary of the Invention

[0007] In view of the shortcomings of the existing technology, the purpose of this invention is to provide an intelligent assistive glasses system and method for stereoscopic perception of the environment.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: a smart assistive glasses system and method for stereoscopic environmental perception, the specific working process of each module is as follows:

[0009] Data acquisition module: The system uses smart glasses for the blind to perform radar scans of the external environment, records the radar scan data, and obtains environmental data.

[0010] Model building module: Processes environmental data, maps the environmental data into three-dimensional space with the smart assistive glasses as the origin, obtains the mapping value, and builds a model of the external environment based on the mapping value to obtain the environmental model;

[0011] Intelligent judgment module: Collects the action information of the user of the smart assistive glasses, judges obstacles based on the user's action information and the environmental model, and provides audio feedback to the user based on the obstacle judgment result;

[0012] Voice interaction module: Users of smart assistive glasses can customize the audio feedback, and receive different audio feedback based on the user's settings.

[0013] Furthermore, environmental data is acquired, specifically as follows:

[0014] The system transmits radio waves through smart glasses for the blind, recording the transmission time and angle. When the radio waves touch an object, they are reflected to obtain a reflected wave. The power and reception time of the reflected wave are obtained from the reflected wave. The reflection time difference of the reflected wave is obtained from the reception time and the transmission time of the radio wave. Environmental data is constructed based on the reflection time difference, the transmission angle of the radio wave, and the power of the reflected wave.

[0015] Furthermore, a model of the external environment is constructed, as follows:

[0016] A three-dimensional coordinate system is constructed with the smart assistive glasses as the origin, with the vertical upward direction as the z-axis, the horizontal forward direction of the glasses as the y-axis, and the direction perpendicular to both the y-axis and z-axis as the x-axis; environmental data is then processed based on this three-dimensional coordinate system.

[0017] Based on environmental data, the reflection time difference of the reflected wave, the transmission angle of the radio wave, and the power of the reflected wave are obtained. The reflection time difference of the reflected wave is denoted as fsc, the transmission angle of the radio wave is denoted as fsj, and the power of the reflected wave is denoted as fgl.

[0018] The wave velocity of the reflected wave is obtained and denoted as bsv; the reflection distance of the reflected wave is calculated based on the wave velocity and the reflection time difference of the reflected wave to obtain the reflection distance fjl.

[0019] By mapping the radio wave transmission angle fsj to the three-dimensional coordinate system, we can obtain the angle fsjx between the radio wave transmission angle and the x-axis, the angle fsjy between the radio wave transmission angle and the y-axis, and the angle fsjz between the radio wave transmission angle and the z-axis.

[0020] Based on the angle fsjx between the radio wave emission angle and the x-axis and the reflection distance fjl, the distance component of the reflecting object on the x-axis is obtained, denoted as flx;

[0021] Based on the angle fsjy between the radio wave emission angle and the y-axis and the reflection distance fjl, the distance component of the reflecting object on the y-axis is obtained, denoted as fly;

[0022] Based on the angle fsjz between the radio wave emission angle and the z-axis and the reflection distance fjl, the distance component of the reflecting object on the z-axis is obtained, denoted as flz;

[0023] Map the coordinate system based on the distance component.

[0024] Furthermore, the coordinate system is mapped according to the distance components, as follows:

[0025] Based on the distance components of the reflecting object on the x-axis, y-axis, and z-axis, the mapping value fzb of the reflection point is obtained, where fzb = (flx, fly, flz).

[0026] The number of radio waves transmitted is obtained; the reflected radio waves of each radio wave are obtained according to the number of radio waves transmitted, and the mapping value of the reflected radio waves to the reflection point is calculated to obtain fzb(1) to fzb(fs); the reflected radio wave power of each reflected radio wave is recorded as fgl(1) to fgl(fs); where: fs represents the number of reflected radio waves;

[0027] Based on the mapping values ​​fzb(1) to fzb(fs) of the reflection points, the three-dimensional coordinate system is mapped, and each reflection point is represented in the three-dimensional coordinate system according to its mapping value to obtain the mapping point; combined with the reflected wave power fgl(1) to fgl(fs) of each reflected wave, each mapping point is labeled to obtain the labeled value; the mapping point is analyzed through the labeled value.

[0028] Furthermore, the mapping points are analyzed as follows:

[0029] Extract mapping points with the same labeled value, determine the continuity of the mapping points, extract continuous mapping points, and obtain the spatial model of the object based on the space enclosed by the continuous mapping points.

[0030] All labeled values ​​and mapping points are processed to obtain spatial models of all objects scanned by the smart assistive glasses. Based on the spatial models of all objects scanned by the smart assistive glasses, an environmental model is constructed.

[0031] Furthermore, obstacle identification is performed using an environmental model, as detailed below:

[0032] Based on the user's action information, obtain the user's leg lift height, denoted as tgd; obtain the user's stride length, denoted as kcd; obtain the user's minimum standing area, denoted as zxl;

[0033] Based on the environmental model, the spatial model of the object is obtained. The object is judged by the user's leg lift height, stride length and minimum standing area. If the user can stand on the object or straddle the object, the object is judged as a non-obstacle. If the user cannot pass through the object, it is judged as an obstacle.

[0034] Furthermore, the object is judged as follows:

[0035] Based on the spatial model of the object, obtain the height of the object; denote the height of the object as wgd; obtain the plane area of ​​the highest point of the object to obtain the object plane wpm; obtain the cross-domain distance kjl of the object based on the length of the object in the y-axis direction.

[0036] The standing value zlz is obtained by calculating the height of the object, the user's leg lift height, the plane area of ​​the highest point of the object, and the user's minimum standing area.

[0037] The standing value is used to determine whether a user can pass over an object by standing on top of it. If the standing value is less than 0, it means that the user cannot pass over the object by standing on top of it.

[0038] The stride value kyz is obtained by calculating the height of the object and the user's leg lift, as well as the stride distance of the object and the user's stride length.

[0039] Based on the standing value zlz and the crossing value kyz, it is determined whether the object is an obstacle.

[0040] Furthermore, the determination of whether an object is an obstacle is as follows:

[0041] If zlz < 0 and kyz < 0, it means that the user cannot pass through the object without changing the path forward, and therefore it is an obstacle.

[0042] If zlz≥0 or kyz≥0, it means that the user can pass through the object without changing the path forward, and therefore it is not an obstacle.

[0043] When a user of smart assistive glasses approaches an object that is an obstacle, the smart assistive glasses will issue a warning to the user;

[0044] When a user of smart assistive glasses approaches a non-obstacle object, the glasses alert the user to the object and guide them on how to pass it.

[0045] Furthermore, users of smart assistive glasses can customize their audio feedback settings, as follows:

[0046] Users of smart assistive glasses can customize the audio feedback settings, which can be set to high-frequency radar sensing target audio, mid-frequency radar sensing target audio, or low-frequency radar sensing target audio.

[0047] Set the target audio of low-frequency radar to level 1, the target audio of medium-frequency radar to level 2, and the target audio of high-frequency radar to level 3; denote the set level as dj; that is, the level of the target audio of low-frequency radar, dj=1;

[0048] When the setting level is the first level, obtain its alarm distance bj (1); when the setting level is the second level, obtain its alarm distance bj (2); when the setting level is the third level, obtain its alarm distance bj (3).

[0049] Based on the environmental model, the distance between the user and the obstacle is obtained and denoted as zjl; the warning value jgz is calculated based on the distance zjl between the user and the obstacle, the setting level dj, and the alarm distance.

[0050] When jgz≤1, a warning is issued to the user;

[0051] When 1 < jgz ≤ 2, a rapid alarm will be sounded for the user;

[0052] When 2 < jgz, a long beep warning will be issued to the user;

[0053] When a user triggers a warning, the smart assistive glasses simultaneously provide a location alert to the user.

[0054] A method for providing intelligent assistive glasses for the blind that enables stereoscopic environmental perception, the assistive method including:

[0055] Step S1: Use smart assistive glasses to perform radar scanning on the external environment, record the radar scan data, and obtain environmental data;

[0056] Step S2: Process the environmental data. Using the smart assistive glasses as the origin, map the environmental data into three-dimensional space to obtain the mapping value. Based on the mapping value, construct a model of the external environment to obtain the environmental model.

[0057] Step S3: Collect the motion information of the user of the smart assistive glasses, judge the obstacles based on the user's motion information and the environmental model, and provide audio feedback to the user based on the obstacle judgment results.

[0058] Step S4: Users of smart assistive glasses can customize the audio feedback settings, and different audio feedback will be obtained based on the user's settings.

[0059] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0060] 1. Provides multiple customizable settings options, allowing users to select different modes according to their needs. Different warnings are also given to users based on the different modes, which enhances the scope of use of smart assistive glasses, meets the needs of more visually impaired people, and improves the applicability of smart assistive glasses.

[0061] 2. By using data modeling, the surrounding environment of smart assistive glasses is analyzed in detail. Combined with multi-dimensional data calculations, obstacles can be judged more accurately, improving the accuracy of the prompts provided by smart assistive glasses and enhancing their safety and practicality; thus ensuring the quality of life and travel safety of visually impaired people. Attached Figure Description

[0062] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0063] Figure 1 is an overall system block diagram of the present invention;

[0064] Figure 2 is a schematic diagram of the model of the present invention;

[0065] Figure 3 is a schematic diagram of the method of the present invention; Detailed Implementation

[0066] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0067] Example 1

[0068] Please refer to Figure 1. The present invention provides a smart assistive glasses system for the blind with a stereoscopic perception environment, which belongs to the category of voice prompt devices. The system includes a data acquisition module, a model building module, an intelligent judgment module, a voice interaction module, and a server. The data acquisition module, model building module, intelligent judgment module, and voice interaction module are respectively connected to the server, and the server controls the data acquisition module, model building module, intelligent judgment module, and voice interaction module respectively.

[0069] Data acquisition module: The system uses smart glasses for the blind to perform radar scans of the external environment, records the radar scan data, and obtains environmental data.

[0070] The specific workflow of the data acquisition module is as follows:

[0071] The system transmits radio waves through smart assistive glasses, recording the transmission time and angle. When the radio waves touch an object, they are reflected to obtain a reflected wave. The power and reception time of the reflected wave are then obtained. The reflection time difference of the reflected wave is calculated from the reception time and the transmission time of the radio wave. Environmental data is then constructed based on the reflection time difference, the transmission angle of the radio wave, and the power of the reflected wave.

[0072] Model building module: Processes environmental data, maps the environmental data into three-dimensional space with the smart assistive glasses as the origin, obtains the mapping value, and builds a model of the external environment based on the mapping value to obtain the environmental model;

[0073] The specific workflow of the model building module is as follows:

[0074] Please refer to Figure 2: A three-dimensional coordinate system is constructed with the smart assistive glasses as the origin. The z-axis is the direction perpendicular to the ground upwards, the y-axis is the direction horizontally forward of the glasses, and the x-axis is the direction perpendicular to both the y-axis and z-axis. The environmental data is processed according to the three-dimensional coordinate system as follows:

[0075] Based on environmental data, the reflection time difference of the reflected wave, the transmission angle of the radio wave, and the power of the reflected wave are obtained. The reflection time difference of the reflected wave is denoted as fsc, the transmission angle of the radio wave is denoted as fsj, and the power of the reflected wave is denoted as fgl.

[0076] The wave velocity of the reflected wave is obtained and denoted as bsv; the reflection distance of the reflected wave is calculated based on the wave velocity and the reflection time difference of the reflected wave to obtain the reflection distance fjl.

[0077] ;

[0078] It should be noted that the wave speed of a reflected wave refers to its propagation speed in the atmosphere. For example, the speed of ultrasound is v = 331.4 + 0.6T (where T is temperature in °C). Example: When the temperature T = 30 °C, v ≈ 349.4 m / s.

[0079] By mapping the radio wave transmission angle fsj to the three-dimensional coordinate system, we can obtain the angle fsjx between the radio wave transmission angle and the x-axis, the angle fsjy between the radio wave transmission angle and the y-axis, and the angle fsjz between the radio wave transmission angle and the z-axis.

[0080] Based on the angle fsjx between the radio wave emission angle and the x-axis and the reflection distance fjl, the distance component of the reflecting object on the x-axis is obtained, denoted as flx;

[0081] ;

[0082] Based on the angle fsjy between the radio wave emission angle and the y-axis and the reflection distance fjl, the distance component of the reflecting object on the y-axis is obtained, denoted as fly;

[0083] ;

[0084] Based on the angle fsjz between the radio wave emission angle and the z-axis and the reflection distance fjl, the distance component of the reflecting object on the z-axis is obtained, denoted as flz;

[0085] ;

[0086] The coordinate system is mapped based on the distance components, as follows:

[0087] Based on the distance components of the reflecting object on the x-axis, y-axis, and z-axis, the mapping value fzb of the reflection point is obtained, where fzb = (flx, fly, flz).

[0088] The number of radio waves transmitted is obtained; the reflected radio waves of each radio wave are obtained according to the number of radio waves transmitted, and the mapping value of the reflected radio waves to the reflection point is calculated to obtain fzb(1) to fzb(fs); the reflected radio wave power of each reflected radio wave is recorded as fgl(1) to fgl(fs); where: fs represents the number of reflected radio waves;

[0089] Based on the mapping values ​​fzb(1) to fzb(fs) of the reflection points, the three-dimensional coordinate system is mapped, and each reflection point is represented in the three-dimensional coordinate system according to its mapping value to obtain the mapping point; combined with the reflected wave power fgl(1) to fgl(fs) of each reflected wave, each mapping point is labeled to obtain the labeled value;

[0090] It should be noted that reflected radio wave power can identify the material of the reflecting object, extract identical objects, and separate different objects.

[0091] Analyze the mapped points based on the labeled values:

[0092] Extract mapping points with the same labeled value, determine the continuity of the mapping points, extract continuous mapping points, and obtain the spatial model of the object based on the space enclosed by the continuous mapping points.

[0093] All labeled values ​​and mapping points are processed to obtain a spatial model of all objects scanned by the smart assistive glasses. An environmental model is then constructed based on the spatial model of all objects scanned by the smart assistive glasses.

[0094] It should be noted that by constructing an environmental model, the user's surrounding environment can be assessed, reducing the difficulty of assessing the surrounding environment and improving the accuracy of smart assistive glasses in judging obstacles.

[0095] Intelligent judgment module: Collects the action information of the user of the smart assistive glasses, judges obstacles based on the user's action information and the environmental model, and provides audio feedback to the user based on the obstacle judgment result;

[0096] The specific workflow of the intelligent judgment module is as follows:

[0097] Based on the user's action information, obtain the user's leg lift height, denoted as tgd; obtain the user's stride length, denoted as kcd; obtain the user's minimum standing area, denoted as zxl;

[0098] Based on the environmental model, the spatial model of the object is obtained. The object is judged by the user's leg height, stride length and minimum standing area. If the user can stand on the object or stride over the object, the object is judged as a non-obstacle. If the user cannot pass through the object, it is judged as an obstacle.

[0099] The specific steps for judging an object are as follows:

[0100] Based on the spatial model of the object, obtain the height of the object; denote the height of the object as wgd; obtain the plane area of ​​the highest point of the object to obtain the object plane wpm; obtain the cross-domain distance kjl of the object based on the length of the object in the y-axis direction.

[0101] The standing value zlz is obtained by calculating the height of the object, the user's leg lift height, the plane area of ​​the highest point of the object, and the user's minimum standing area.

[0102] ;

[0103] It should be noted that the difference between the height of the object and the height of the user's raised leg is used to determine whether the user can pass the highest point of the object. The difference between the plane area of ​​the highest point of the object and the user's minimum standing area is used to determine whether the user can stand on the object. The two factors are combined to determine whether the user can pass the object by standing on it.

[0104] The standing value is used to determine whether a user can pass over an object by standing on top of it. If the standing value is less than 0, it means that the user cannot pass over the object by standing on top of it.

[0105] The stride value kyz is obtained by calculating the height of the object and the user's leg lift, as well as the stride distance of the object and the user's stride length.

[0106] ;

[0107] It should be noted that: the ability of a user to directly cross an object is determined by the object's span distance and the user's stride length. The height of the object and the user's leg lift height are combined to constrain the ability to directly cross the object, thereby enhancing the accuracy of the calculation results. For example, if the width of an object is less than the user's span length, but its height is too high for the user to pass through, then the user cannot directly cross the object.

[0108] Based on the standing value zlz and the crossing value kyz, determine whether the object is an obstacle;

[0109] If zlz < 0 and kyz < 0, it means that the user cannot pass through the object without changing the path forward, and therefore it is an obstacle.

[0110] If zlz≥0 or kyz≥0, it means that the user can pass through the object without changing the path forward, and therefore it is not an obstacle.

[0111] When a user of smart assistive glasses approaches an object that is an obstacle, the smart assistive glasses will issue a warning to the user;

[0112] When a user of smart assistive glasses approaches a non-obstacle object, the glasses alert the user to the object and guide them on how to pass it.

[0113] It should be noted that: by using multiple data to evaluate objects, the accuracy of obstacle assessment is ensured; and the warning accuracy of smart assistive glasses for the blind is improved.

[0114] Voice interaction module: Users of smart assistive glasses can customize the audio feedback, and different audio feedback will be obtained based on the user's settings;

[0115] The specific workflow of the voice interaction module is as follows:

[0116] Users of smart assistive glasses can customize the audio feedback settings, which can be set to high-frequency radar sensing target audio, mid-frequency radar sensing target audio, or low-frequency radar sensing target audio.

[0117] Set the target audio of low-frequency radar to level 1, the target audio of medium-frequency radar to level 2, and the target audio of high-frequency radar to level 3; denote the set level as dj; that is, the level of the target audio of low-frequency radar, dj=1;

[0118] When the setting level is the first level, obtain its alarm distance bj (1); when the setting level is the second level, obtain its alarm distance bj (2); when the setting level is the third level, obtain its alarm distance bj (3).

[0119] Based on the environmental model, the distance between the user and the obstacle is obtained and denoted as zjl; the warning value jgz is calculated based on the distance zjl between the user and the obstacle, the setting level dj, and the alarm distance.

[0120] ;

[0121] When jgz≤1, a warning is issued to the user;

[0122] When 1 < jgz ≤ 2, a rapid alarm will be sounded for the user;

[0123] When 2 < jgz, a long beep warning will be issued to the user;

[0124] When a user triggers a warning, the smart assistive glasses simultaneously provide the user's location information.

[0125] It should be noted that different warning levels allow users to better perceive the distance between themselves and obstacles, thereby avoiding obstacles and ensuring user safety.

[0126] Example 2

[0127] Please refer to Figure 3. The present invention provides a method for providing a stereoscopic perception environment-enabled smart assistive glasses for the blind, which pertains to voice prompt devices.

[0128] Step S1: Use smart assistive glasses to perform radar scanning on the external environment, record the radar scan data, and obtain environmental data;

[0129] Step S2: Process the environmental data. Using the smart assistive glasses as the origin, map the environmental data into three-dimensional space to obtain the mapping value. Based on the mapping value, construct a model of the external environment to obtain the environmental model.

[0130] Step S3: Collect the motion information of the user of the smart assistive glasses, judge the obstacles based on the user's motion information and the environmental model, and provide audio feedback to the user based on the obstacle judgment results.

[0131] Step S4: Users of smart assistive glasses can customize the audio feedback settings, and different audio feedback will be obtained based on the user's settings.

[0132] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart assistive glasses system for the blind that enables stereoscopic environmental perception, characterized in that, include: Data acquisition module: The system uses smart glasses for the blind to perform radar scans of the external environment, records the radar scan data, and obtains environmental data. Model Building Module: Processes environmental data, using the smart assistive glasses as the origin, maps the environmental data into three-dimensional space to obtain mapping values, and builds an environmental model based on these mapping values. Intelligent Judgment Module: Collects the user's action information, judges obstacles based on the user's action information and the environmental model, and provides audio feedback to the user based on the obstacle judgment results. Voice Interaction Module: Allows the user to customize the audio feedback, and provides different audio feedback based on the user's settings. The specific workflow of the intelligent judgment module is as follows: Based on the user's action information, obtains the user's leg lift height (tgd); obtains the user's stride length (kcd); obtains the user's minimum standing area (zxl); based on the environmental model, obtains the spatial model of objects, and judges objects based on the user's leg lift height, stride length, and minimum standing area. If the user can stand on or stride over an object, the object is judged as a non-obstacle; if the user cannot pass through an object, it is judged as an obstacle; based on the object's spatial model, obtains the object's height. The height of the object is denoted as wgd; the area of ​​the plane at the highest point of the object is obtained to get the object plane wpm; the span distance of the object is obtained based on the length of the object in the y-axis direction; the standing value zlz is obtained by calculating the height of the object, the user's leg lift height, the area of ​​the plane at the highest point of the object, and the user's minimum standing area. The system determines whether a user can cross an object by standing on top of it based on the standing value. If the standing value is less than 0, it means that the user cannot cross the object by standing on top of it. The system calculates the crossing value kyz by combining the height of the object with the user's leg lift, the crossing distance of the object with the user's crossing length. Based on the standing value zlz and the crossing value kyz, determine whether the object is an obstacle; If zlz < 0 and kyz < 0, it means that the user cannot pass through the object without changing the path forward, and therefore it is an obstacle; if zlz ≥ 0 or kyz ≥ 0, it means that the user can pass through the object without changing the path forward, and therefore it is not an obstacle.

2. The intelligent assistive glasses system for the blind with stereoscopic environmental perception according to claim 1, characterized in that, The environmental data is acquired as follows: radio waves are emitted through smart assistive glasses for the blind, and the emission time and angle of the radio waves are recorded. When the radio waves touch an object, they are reflected to obtain the reflected wave. The power and reception time of the reflected wave are obtained based on the reflected wave. The reflection time difference of the reflected wave is obtained from the reception time of the reflected wave and the emission time of the radio wave. The environmental data is constructed based on the reflection time difference, the emission angle of the radio wave, and the power of the reflected wave.

3. The intelligent assistive glasses system for the blind with stereoscopic environmental perception according to claim 1, characterized in that, The external environment is modeled as follows: A three-dimensional coordinate system is constructed with the smart assistive glasses as the origin. The z-axis is the direction perpendicular to the ground upwards, the y-axis is the direction horizontally forward of the glasses, and the x-axis is the direction perpendicular to both the y-axis and z-axis. Environmental data is processed based on this three-dimensional coordinate system. The reflection time difference, radio wave transmission angle, and reflected wave power are obtained from the environmental data. The reflection time difference is denoted as fsc, the radio wave transmission angle as fsj, and the reflected wave power as fgl. The wave speed of the reflected wave is obtained and denoted as bsv. The reflection distance is calculated based on the wave speed and reflection time difference, yielding the reflection distance fjl. The radio wave transmission angle fjl is calculated as fsjl. Mapping sj ​​to the three-dimensional coordinate system yields the angles fsjx (radio wave emission angle) with the x-axis, fsjy (radio wave emission angle) with the y-axis, and fsjz (radio wave emission angle) with the z-axis. Using the angles fsjx and fjl (radio wave emission angle) and the reflection distance fjl, the distance component of the reflecting object on the x-axis is obtained, denoted as flx. Using the angles fsjy and fjl (radio wave emission angle) and the reflection distance fjl, the distance component of the reflecting object on the y-axis is obtained, denoted as fly. Using the angles fsjz and fjl (radio wave emission angle) and the reflection distance fjl, the distance component of the reflecting object on the z-axis is obtained, denoted as flz. The coordinate system is then mapped based on these distance components.

4. The intelligent assistive glasses system for the blind with stereoscopic perception of the environment according to claim 3, characterized in that, The coordinate system is mapped according to the distance components, as follows: Based on the distance components of the reflecting object on the x-axis, the distance components of the reflecting object on the y-axis, and the distance components of the reflecting object on the z-axis, the mapping value of the reflection point fzb is obtained, fzb = (flx, fly, flz); the number of radio waves transmitted is obtained; the reflected radio waves of each radio wave are obtained according to the number of radio waves transmitted, and the mapping value of the reflection point is calculated according to the reflected radio waves to obtain fzb(1) to fzb(fs); the reflected radio wave power of each reflected radio wave is recorded as fgl(1) to fgl(fs); where: fs represents the number of reflected radio waves; the three-dimensional coordinate system is mapped according to the mapping value of the reflection point fzb(1) to fzb(fs), and each reflection point is represented in the three-dimensional coordinate system according to its mapping value to obtain the mapping point; combined with the reflected radio wave power fgl(1) to fgl(fs) of each reflected radio wave, each mapping point is labeled to obtain the label value; the mapping point is analyzed through the label value.

5. The intelligent assistive glasses system for the blind with stereoscopic environmental perception according to claim 4, characterized in that, The mapping points are analyzed as follows: mapping points with the same labeled value are extracted; the continuity of the mapping points is judged; continuous mapping points are extracted; and the spatial model of the object is obtained based on the space enclosed by the continuous mapping points. All labeled values ​​and mapping points are processed to obtain the spatial model of all objects scanned by the smart assistive glasses. Based on the spatial model of all objects scanned by the smart assistive glasses, an environmental model is constructed.

6. The intelligent assistive glasses system for the blind with stereoscopic environmental perception according to claim 1, characterized in that, The system determines whether an object is an obstacle as follows: when the user of the smart assistive glasses approaches an object that is an obstacle, the smart assistive glasses issue a warning to the user; when the user approaches an object that is not an obstacle, the smart assistive glasses remind the user of the object ahead and inform the user to pass through the object.

7. The intelligent assistive glasses system for the blind with stereoscopic environmental perception according to claim 1, characterized in that, Users of smart assistive glasses can customize the audio feedback settings as follows: Users of smart assistive glasses can customize the audio feedback settings, which can be set to high-frequency radar sensing target audio, mid-frequency radar sensing target audio, or low-frequency radar sensing target audio. Set the target audio of the low-frequency radar to the first level, the target audio of the medium-frequency radar to the second level, and the target audio of the high-frequency radar to the third level; denot the setting level as dj; that is, the level of the target audio of the low-frequency radar, dj=1; when the setting level is the first level, obtain its alarm distance bj (1); when the setting level is the second level, obtain its alarm distance bj (2); when the setting level is the third level, obtain its alarm distance bj (3); according to the environmental model, obtain the distance between the user and the obstacle, denoted as zjl; calculate the warning value jgz based on the distance zjl between the user and the obstacle, the setting level dj, and the alarm distance; when jgz≤1, warn the user; when 1<jgz≤2, give the user a quick alarm warning; when 2<jgz, give the user a long alarm warning; when the user triggers the warning, the smart assistive glasses simultaneously remind the user of the location.

8. A method for providing intelligent assistive glasses for the blind with stereoscopic environmental perception, applicable to the intelligent assistive glasses system for the blind with stereoscopic environmental perception as described in any one of claims 1-7, characterized in that, The assistive method for the blind includes: Step S1: Using smart assistive glasses to perform radar scanning of the external environment, recording the radar scan data to obtain environmental data; Step S2: Processing the environmental data, using the smart assistive glasses as the origin, mapping the environmental data in three-dimensional space to obtain mapping values, and constructing an environmental model based on the mapping values; Step S3: Collecting the user's action information, judging obstacles based on the user's action information and the environmental model, and providing audio feedback to the user based on the obstacle judgment results; Step S4: The user of the smart assistive glasses can independently set the audio feedback, and different audio feedback is obtained based on the user's settings.

Images