A focusing method and device of glasses, smart glasses and a storage medium

Abstract

The present disclosure relates to a focusing method and device of glasses, smart glasses and a storage medium, the method comprising: acquiring vision distance detection data; inputting the vision distance data into a pre-trained vision distance convolutional neural network model to obtain a vision distance judgment result; and controlling the focusing of the glasses based on the vision distance judgment result. In view of the fact that users frequently replace glasses in different eye use scenarios, that zoom glasses have poor adaptability and even safety hazards, and that automatic focusing technology is complex, the present application can accurately determine the current vision distance according to the real vision distance of the user through a convolutional neural network, reduce errors, optimize the automatic focusing function of the glasses, and improve the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of automatic focusing technology, and in particular to a focusing method, device, smart glasses, and storage medium for eyeglasses. Background Technology

[0002] With the increasing aging of the population, the number of elderly people is also rapidly increasing, and the prospects for age-friendly products are becoming increasingly broad. By combining the needs of ease of use, safety, health support, adaptability, and comfort, and making full use of advanced technologies, age-friendly products can significantly improve the quality of life for the elderly, bringing a win-win situation for businesses and society.

[0003] On the other hand, people's lifestyles have also changed due to the development of electronic products. For example, outdoor activities have decreased, while the demand for visual stimulation has increased. Prolonged use of smartphones, tablets, computers, and televisions has increased the burden on the eyes. Some elderly people have both myopia and presbyopia (farsightedness), often requiring multiple pairs of glasses. They wear reading glasses for reading and myopia glasses for outdoor activities, causing inconvenience in daily life. Current bifocal or progressive lenses can easily lead to unnatural vision at different viewing distances and require an adaptation period, potentially causing dizziness or other discomfort. For older users, this can even increase the risk of falls. Furthermore, current autofocus glasses are technically complex and their focusing effect is not ideal. Summary of the Invention

[0004] This disclosure provides a focusing method, device, smart glasses, and storage medium for eyeglasses, to improve the reliability and convenience of automatic focusing of eyeglasses and enhance the user experience.

[0005] In a first aspect, this disclosure provides a method for focusing eyeglasses, comprising:

[0006] Acquire view distance detection data, input the view distance data into a pre-trained view distance convolutional neural network model, and obtain view distance judgment results;

[0007] The eyeglasses are focused based on the distance determination result.

[0008] In some embodiments, acquiring the line-of-sight detection data includes:

[0009] The raw view distance detection data is obtained, and the raw view distance detection data is input into a pre-stored 3D vision model for preprocessing to obtain the view distance detection data.

[0010] In some embodiments, an original training dataset is obtained, which includes at least one of an original distance dataset, an original environment dataset, and an original stress dataset.

[0011] A distance vector set is constructed based on the original distance dataset; the original distance dataset includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye-tracking sensor data;

[0012] The distance vector set is mapped to three-dimensional coordinates to form distance three-dimensional coordinate data;

[0013] An environmental vector set is constructed based on the original environmental dataset; the original environmental dataset includes at least one of image sensor data and ambient light sensor data.

[0014] The environmental vector set is mapped to three-dimensional coordinates to form environmental three-dimensional coordinate data;

[0015] A pressure vector set is constructed based on the original pressure dataset; the original pressure dataset includes at least one of pressure sensor data and contact sensor data.

[0016] The pressure vector set is mapped to three-dimensional coordinates to form pressure three-dimensional coordinate data;

[0017] The three-dimensional visual model is constructed based on the distance three-dimensional coordinate data, the environmental three-dimensional coordinate data, and the pressure three-dimensional coordinate data.

[0018] In some embodiments, the method further includes:

[0019] Obtain a line-of-sight training dataset; the line-of-sight training dataset includes line-of-sight judgment results and corresponding line-of-sight detection data; the line-of-sight detection data includes at least one of a distance dataset, an environment dataset, and a stress dataset.

[0020] The convolutional neural network is trained based on the aforementioned distance training dataset to obtain the distance-based convolutional neural network model.

[0021] In some embodiments, after controlling the focusing of the glasses based on the viewing distance determination result, the method further includes:

[0022] The line-of-sight convolutional neural network is modified based on user feedback.

[0023] In some embodiments, controlling the focusing of the glasses based on the distance determination result includes:

[0024] If the viewing distance determination result indicates that the target object is not within the current viewing distance range, a focusing prompt is issued, and the glasses are controlled to focus.

[0025] If the viewing distance determination result indicates that the target object is within the current viewing distance range, a prompt indicating that no focusing is required will be issued.

[0026] Secondly, this disclosure provides a focusing device for eyeglasses, comprising:

[0027] The view distance determination module is used to acquire view distance detection data, input the view distance data into a pre-trained view distance convolutional neural network model, and obtain the view distance determination result.

[0028] The focusing control module is used to control the focusing of the glasses based on the viewing distance judgment result.

[0029] In some embodiments, the apparatus further includes a preprocessing module for:

[0030] The raw view distance detection data is obtained, and the raw view distance detection data is input into a pre-stored 3D vision model for preprocessing to obtain the view distance detection data.

[0031] In some embodiments, the apparatus further includes a three-dimensional visual model building module, comprising:

[0032] The original training dataset acquisition unit is used to acquire the original training dataset, which includes at least one of the original distance dataset, the original environment dataset, and the original stress dataset.

[0033] A distance vector set construction unit is used to construct a distance vector set based on the original distance dataset; the original distance dataset includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye-tracking sensor data;

[0034] A distance 3D coordinate construction unit is used to map the distance vector set to 3D coordinates to form distance 3D coordinate data;

[0035] An environment vector set construction unit is used to construct an environment vector set based on the original environment dataset; the original environment dataset includes at least one of image sensor data and ambient light sensor data.

[0036] An environment 3D coordinate construction unit is used to map the environment vector set to 3D coordinates to form environment 3D coordinate data;

[0037] A pressure vector set construction unit is used to construct a pressure vector set based on the original pressure dataset; the original pressure dataset includes at least one of pressure sensor data and contact sensor data.

[0038] A pressure three-dimensional coordinate construction unit is used to map the pressure vector set to three-dimensional coordinates to form pressure three-dimensional coordinate data;

[0039] A three-dimensional visual model construction unit is used to construct the three-dimensional visual model based on the distance three-dimensional coordinate data, the environment three-dimensional coordinate data, and the pressure three-dimensional coordinate data.

[0040] In some embodiments, the apparatus further includes a view-range convolutional neural network model building module, comprising:

[0041] A line-of-sight training dataset acquisition unit is used to acquire a line-of-sight training dataset; the line-of-sight training dataset includes line-of-sight judgment results and corresponding line-of-sight detection data; the line-of-sight detection data includes at least one of a distance dataset, an environment dataset, and a stress dataset.

[0042] The convolutional neural network training unit is used to train the convolutional neural network based on the line-of-sight training dataset to obtain the line-of-sight convolutional neural network model.

[0043] In some embodiments, the apparatus further includes a line-of-sight convolutional neural network correction module, configured to correct the line-of-sight convolutional neural network based on user feedback.

[0044] In some embodiments, the focusing control module is specifically used for:

[0045] If the viewing distance determination result indicates that the target object is not within the current viewing distance range, a focusing prompt is issued, and the glasses are controlled to focus.

[0046] If the viewing distance determination result indicates that the target object is within the current viewing distance range, a prompt indicating that no focusing is required will be issued.

[0047] Thirdly, this disclosure provides a smart glasses, including a sensor, a focusing device, a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the method described above.

[0048] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the methods described in the above aspects.

[0049] Fifthly, this disclosure provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the methods described in the foregoing aspects.

[0050] This disclosure provides a focusing method, device, smart glasses, and storage medium for eyeglasses. The method includes acquiring viewing distance detection data, inputting the viewing distance data into a pre-trained viewing distance convolutional neural network model to obtain a viewing distance judgment result, and controlling the eyeglasses to focus based on the viewing distance judgment result. Addressing the issues of frequent eyeglass replacements in different visual scenarios, poor adaptability of zoom glasses leading to discomfort or even safety hazards, and the complexity of autofocus technology, this application utilizes a convolutional neural network to accurately determine the current viewing distance based on the user's actual viewing distance, reducing errors, optimizing the autofocus function of the eyeglasses, and improving the user experience. Attached Figure Description

[0051] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0052] Figure 1 A schematic flowchart illustrating a focusing method for eyeglasses provided in an embodiment of this disclosure;

[0053] Figure 2 This is a flowchart illustrating the method for constructing a three-dimensional visual model in a focusing method for eyeglasses provided in this embodiment of the present disclosure.

[0054] Figure 3 This is another schematic diagram of the training method of the convolutional neural network model in a focusing method for eyeglasses provided in this embodiment of the present disclosure;

[0055] Figure 4 This is another flowchart illustrating the training method of a convolutional neural network model in a focusing method for eyeglasses provided in this embodiment of the present disclosure.

[0056] Figure 5 This is yet another schematic flowchart illustrating a focusing method for eyeglasses provided in an embodiment of the present disclosure;

[0057] Figure 6 This is a schematic diagram of the focusing device for eyeglasses provided in an embodiment of the present disclosure. Detailed Implementation

[0058] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0059] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0060] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0061] This disclosure provides a focusing method, device, smart glasses, and storage medium for eyeglasses, which can accurately determine the current viewing distance based on the user's actual viewing distance through a convolutional neural network, reduce errors, optimize the automatic focusing function of the eyeglasses, and improve the user experience.

[0062] Example 1

[0063] Figure 1 This is a schematic flowchart illustrating a focusing method for eyeglasses provided in an embodiment of the present disclosure.

[0064] Reference Figure 1 As shown, the focusing method for eyeglasses provided in this embodiment of the invention includes steps 101 to 102.

[0065] Step 101: Obtain the view distance detection data, input the view distance data into the pre-trained view distance convolutional neural network model, and obtain the view distance judgment result.

[0066] In a specific example, the line-of-sight detection data consists of data from the external environment and the user themselves detected by various sensors, including but not limited to data collected by distance sensors, image sensors, accelerometers, gyroscopes, eye-tracking sensors, ambient light sensors, pressure and contact sensors, etc.

[0067] In a specific example, the position and distance of the user's target object are determined based on data acquired by a distance sensor combined with a gyroscope, accelerometer, and eye-tracking sensor. Data from an image sensor combined with an ambient light sensor is used to determine information such as the brightness of the target object and the surrounding environment. Data from pressure and contact sensors is used to determine information such as the user's eye condition. Based on the angle and distance of the target object, the external environment, and the user's eye condition, the current viewing distance of the target object is determined to fully meet the user's actual needs.

[0068] In some embodiments, step 101, acquiring line-of-sight detection data, includes:

[0069] The raw view distance detection data is obtained, and the raw view distance detection data is input into a pre-stored 3D vision model for preprocessing to obtain the view distance detection data.

[0070] Due to interference from external factors, such as excessively bright light sources in the environment, the original detection data may contain a certain amount of abnormal data. Preprocessing with a pre-stored 3D vision model can filter and screen the original detection data, avoiding interference from abnormal data in distance judgment.

[0071] Step 102: Control the focus of the glasses based on the distance judgment result.

[0072] In some embodiments, step 102 includes:

[0073] If the viewing distance determination result indicates that the target object is not within the current viewing distance range, a focusing prompt is issued, and the glasses are controlled to focus.

[0074] If the viewing distance determination result indicates that the target object is within the current viewing distance range, a prompt indicating that no focusing is required will be issued.

[0075] In some embodiments, when a user moves, turns around, turns their head, or rotates their eyes, the target object changes, and refocusing may be necessary. Prompting the user during the refocusing process can remind them to close their eyes temporarily to avoid dizziness or other discomfort, or to prevent the user from becoming dissatisfied because they cannot see the target clearly during the refocusing process, thereby further improving the user experience.

[0076] On the other hand, if a prompt indicating that focusing is not needed or focusing is finished is issued, but the user feels that the distance judgment is incorrect, they can issue a focusing command themselves to meet the current needs and provide feedback to the smart glasses, thus promoting further training of the distance-based convolutional neural network.

[0077] In a specific example, the focus adjustment indicator is a red light to remind the user that the current viewing distance is not within the current viewing distance range of the glasses, and to automatically control the focus adjustment.

[0078] In a specific example, the no-focus indicator light is green to indicate that the current viewing distance is within the glasses' current viewing distance range and no refocusing is required.

[0079] In practical applications, a pre-trained convolutional neural network model is used to monitor the viewing distance seen by the user. If the object is within the normal viewing distance, no autofocus is performed. If the object is outside the normal viewing distance, autofocus is performed, and the result is fed back to the 3D vision model for further training.

[0080] In some embodiments, when the location is a measured view distance, the convolutional neural network model detects the measured view distance and outputs a detection result set S = {R1, R2...R...} n}, thus obtaining the measured line-of-sight data.

[0081] In a specific example, the pre-trained convolutional neural network model includes the mapping relationship between the detected viewing distance data and the measured viewing distance, and the mapping relationship between the measured viewing distance and the smart indicator light.

[0082] If the current viewing distance R n Within the normal viewing distance range, the intelligent indicator light will display a green light according to the pre-stored viewing distance mapping relationship, indicating that the measured viewing distance is within the normal viewing distance range and automatic focusing is not required.

[0083] If the current viewing distance R n If the distance is outside the normal viewing distance range, the intelligent indicator light will be turned red according to the pre-stored viewing distance mapping relationship, indicating that the measured viewing distance is outside the normal viewing distance range, and automatic focusing will be performed.

[0084] The focusing method for glasses provided in this invention uses a convolutional neural network to accurately determine the current viewing distance based on the user's actual viewing distance, reducing errors, optimizing the automatic focusing function of the glasses, and improving the user experience.

[0085] Example 2

[0086] Based on the above embodiments, the focusing method for glasses provided by the present invention further includes a three-dimensional visual model construction step.

[0087] In some embodiments, such as Figure 2 As shown, the method for constructing the three-dimensional visual model includes:

[0088] Step 201: Obtain the original training dataset, which includes at least one of the original distance dataset, the original environment dataset, and the original stress dataset.

[0089] In some embodiments, data collected by distance sensors, image sensors, accelerometers, gyroscopes, eye-tracking sensors, ambient light sensors, pressure and contact sensors are mapped onto the three-dimensional coordinates of distance vector, ambient light vector, and pressure vector, respectively, to form three-dimensional coordinate data of distance vector, ambient light vector, and pressure vector.

[0090] Step 202: Construct a distance vector set based on the original distance dataset; the original distance dataset includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye-tracking sensor data;

[0091] Step 203: Map the distance vector set to three-dimensional coordinates to form distance three-dimensional coordinate data;

[0092] In a specific example, a distance vector set M[a1,a2...a3] is constructed using line-of-sight data collected from distance sensors, image sensors, accelerometers, gyroscopes, eye-tracking sensors, etc. n ], where a n This represents the nth distance vector. Mapping the set of distance vectors onto three-dimensional coordinates forms the three-dimensional coordinate data (X) representing the line-of-sight distance vectors. M Y M Z M ).

[0093] Step 204: Construct an environment vector set based on the original environment dataset; the original environment dataset includes at least one of image sensor data and ambient light sensor data;

[0094] Step 205: Map the environment vector set to three-dimensional coordinates to form three-dimensional environment coordinate data.

[0095] In a specific example, an environment vector set K[b1,b2...b] is constructed using ambient lighting data collected by an image sensor and an ambient light sensor.n ], where b n This represents the nth acquired environment vector. Mapping the environment vector set onto three-dimensional coordinates forms the three-dimensional coordinate data of the environment vectors (X). K Y K Z K ).

[0096] Step 206: Construct a pressure vector set based on the original pressure dataset; the original pressure dataset includes at least one of pressure sensor data and contact sensor data;

[0097] Step 207: Map the pressure vector set to three-dimensional coordinates to form pressure three-dimensional coordinate data;

[0098] In a specific example, a pressure vector set F[c1,c2...c] is constructed using pressure data collected from pressure and contact sensors. n ], where c n This represents the nth collected pressure vector. Mapping the pressure vector set onto three-dimensional coordinates forms the three-dimensional coordinate data of the pressure vectors (X). F Y F Z F ).

[0099] Step 208: Construct the three-dimensional visual model based on the distance three-dimensional coordinate data, the environment three-dimensional coordinate data, and the pressure three-dimensional coordinate data.

[0100] A 3D visual model is established based on the above distance vector 3D coordinate data, environment vector 3D coordinate data, and pressure vector 3D coordinate data. Based on the 3D visual model, the raw data are preprocessed through screening and filtering to output preprocessed distance, illumination, and pressure data, thereby improving the reliability and accuracy of the collected data and effectively reducing the final line-of-sight error.

[0101] Example 3

[0102] Based on the above embodiments, the focusing method for glasses provided by the present invention further includes a training step of a convolutional neural network model.

[0103] like Figure 3 As shown, the training methods for convolutional neural network models include:

[0104] Step 301: Obtain the line-of-sight training dataset; the line-of-sight training dataset includes line-of-sight judgment results and corresponding line-of-sight detection data; the line-of-sight detection data includes at least one of distance dataset, environment dataset and stress dataset.

[0105] In a specific example, the line-of-sight training dataset is data that has been preprocessed by a 3D vision model to improve the reliability and stability of the line-of-sight convolutional neural network model and avoid abnormal data from interfering with the training of the neural network.

[0106] Step 302: Train the convolutional neural network based on the line-of-sight training dataset to obtain the line-of-sight convolutional neural network model.

[0107] In some embodiments, a convolutional neural network model is obtained by training the convolutional neural network with distance, illumination, and pressure data from the 3D vision model. Optionally, the convolutional neural network model records the mapping relationship between the 3D vision model and the smart indicator light.

[0108] In a specific example, the convolutional neural network is trained using data from a 3D vision model to obtain a convolutional neural network model. Given a measured viewing distance, the convolutional neural network model determines the measured viewing distance and outputs the determination result.

[0109] Furthermore, in some embodiments, the method may use pre-trained convolutions, and the method further includes:

[0110] Step 303: Correct the line-of-sight convolutional neural network based on user feedback.

[0111] As users age, their nearsightedness or farsightedness may change. The method provided in this invention can continuously train the convolutional neural network model according to the actual viewing distance to meet the user's actual needs.

[0112] The convolutional neural network model is trained using data from a 3D vision model to obtain a convolutional network model that more closely approximates the user's actual viewing distance. For example, when the user is an elderly person who is both nearsighted and farsighted, the focusing method provided in this embodiment of the invention can provide a viewing distance convolutional network model that is closer to actual needs.

[0113] Example 4

[0114] Based on the above embodiments, Figure 4 This diagram illustrates another implementation flow of the training method for the convolutional neural network model in the eyeglass focusing method provided in this embodiment of the invention.

[0115] Reference Figure 4 In a specific example, the training method of the convolutional neural network model is implemented as follows.

[0116] First, a 3D vision model is built based on the collected data. Then, a convolutional neural network model is built using the data output from the 3D vision model.

[0117] Select a batch of data from the training dataset, train the parameters of the convolutional neural network, and monitor the error on the test dataset.

[0118] Determine if the error of the test dataset meets the requirements. If it does, the convolutional neural network training is considered complete. If not, repeat the step of selecting data from the training dataset to train the convolutional neural network parameters until the error of the test dataset meets the requirements.

[0119] Figure 5 This diagram illustrates another implementation flow of the focusing method for eyeglasses provided in an embodiment of the present invention.

[0120] Reference Figure 5 In a specific example, the implementation process of the training method includes the following steps.

[0121] First, data such as distance, illumination, and pressure are collected using various sensors, and a 3D visual model is built based on this data. Then, data from the 3D visual model is used to train a convolutional neural network, resulting in a convolutional neural network model.

[0122] When the measured viewing distance is unknown, the convolutional neural network model makes a judgment on the viewing distance, obtains the measured viewing distance, and outputs the judgment result.

[0123] The system determines whether the viewing distance is within the normal range. If the current viewing distance is within the normal range, the smart light will display green, indicating that the object can be viewed normally without automatic focusing. If the current viewing distance is not within the normal range, the smart light will display red, indicating that the object cannot be viewed normally, and the system will automatically focus based on the viewing distance result.

[0124] Furthermore, the measured viewing distance is fed back after automatic focusing.

[0125] Example 5

[0126] Figure 6 This invention illustrates a focusing device for eyeglasses according to an embodiment of the present invention, comprising:

[0127] The view distance determination module is used to acquire view distance detection data, input the view distance data into a pre-trained view distance convolutional neural network model, and obtain the view distance determination result.

[0128] The focusing control module is used to control the focusing of the glasses based on the viewing distance judgment result.

[0129] In some embodiments, the apparatus further includes a preprocessing module for:

[0130] The raw view distance detection data is obtained, and the raw view distance detection data is input into a pre-stored 3D vision model for preprocessing to obtain the view distance detection data.

[0131] In some embodiments, the apparatus further includes a three-dimensional visual model building module, comprising:

[0132] The original training dataset acquisition unit is used to acquire the original training dataset, which includes at least one of the original distance dataset, the original environment dataset, and the original stress dataset.

[0133] A distance vector set construction unit is used to construct a distance vector set based on the original distance dataset; the original distance dataset includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye-tracking sensor data;

[0134] A distance 3D coordinate construction unit is used to map the distance vector set to 3D coordinates to form distance 3D coordinate data;

[0135] An environment vector set construction unit is used to construct an environment vector set based on the original environment dataset; the original environment dataset includes at least one of image sensor data and ambient light sensor data.

[0136] An environment 3D coordinate construction unit is used to map the environment vector set to 3D coordinates to form environment 3D coordinate data;

[0137] A pressure vector set construction unit is used to construct a pressure vector set based on the original pressure dataset; the original pressure dataset includes at least one of pressure sensor data and contact sensor data.

[0138] A pressure three-dimensional coordinate construction unit is used to map the pressure vector set to three-dimensional coordinates to form pressure three-dimensional coordinate data;

[0139] A three-dimensional visual model construction unit is used to construct the three-dimensional visual model based on the distance three-dimensional coordinate data, the environment three-dimensional coordinate data, and the pressure three-dimensional coordinate data.

[0140] In some embodiments, the apparatus further includes a view-range convolutional neural network model building module, comprising:

[0141] A line-of-sight training dataset acquisition unit is used to acquire a line-of-sight training dataset; the line-of-sight training dataset includes line-of-sight judgment results and corresponding line-of-sight detection data; the line-of-sight detection data includes at least one of a distance dataset, an environment dataset, and a stress dataset.

[0142] The convolutional neural network training unit is used to train the convolutional neural network based on the line-of-sight training dataset to obtain the line-of-sight convolutional neural network model.

[0143] In some embodiments, the apparatus further includes a line-of-sight convolutional neural network correction module, configured to correct the line-of-sight convolutional neural network based on user feedback.

[0144] In some embodiments, the focusing control module is specifically used for:

[0145] If the viewing distance determination result indicates that the target object is not within the current viewing distance range, a focusing prompt is issued, and the glasses are controlled to focus.

[0146] If the viewing distance determination result indicates that the target object is within the current viewing distance range, a prompt indicating that no focusing is required will be issued.

[0147] The focusing device for glasses provided in this embodiment of the invention is used to acquire visual distance detection data, input the visual distance data into a pre-trained visual distance convolutional neural network model, and obtain a visual distance judgment result; based on the visual distance judgment result, the focusing of the glasses is controlled. Addressing the issues of frequent glasses replacement in different visual scenarios, poor adaptability of zoom glasses leading to discomfort or even safety hazards, and the complexity of autofocus technology, the focusing device provided in this embodiment of the invention can accurately determine the current visual distance according to the user's actual visual distance through a convolutional neural network, reducing errors, optimizing the autofocus function of the glasses, and improving the user experience.

[0148] Example 6

[0149] Based on the above embodiments, this embodiment provides smart glasses, including a sensor, a focusing device, a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the method described above.

[0150] In some embodiments of this example, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the method described in the above embodiments.

[0151] In some embodiments of this example, a computer program product is provided, including a computer program / instructions, characterized in that the computer program, when executed by a processor, implements the steps of the method described in the above embodiments.

[0152] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic component, for executing the methods described in the above embodiments.

[0153] Computer-readable storage media can be implemented by any type of volatile or non-volatile storage device or a combination thereof. Computer-readable storage media may include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, and computer storage media (e.g., hard disks, floppy disks, solid-state drives, removable disks, CD-ROMs, DVD-ROMs, Blu-ray discs, etc.).

[0154] Computer-readable storage media may also store at least one computer-executable program / instruction, such as computer-readable instructions. Computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Computer-readable storage media may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions stored on the computer-readable storage medium, the various methods described above can be performed.

[0155] In addition, the computer device may include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (e.g., keyboard, mouse, speakers, etc.).

[0156] The processor can communicate with external devices via the I / O bus through wired or wireless networks.

[0157] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product / computer program product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0158] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0159] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0160] While the embodiments disclosed herein are as described above, the foregoing content is merely for the purpose of facilitating understanding of this disclosure and is not intended to limit this disclosure. Any person skilled in the art to which this disclosure pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope of this disclosure; however, the scope of patent protection of this disclosure shall still be determined by the scope defined in the appended claims.

Claims

1. A method for adjusting the focus of eyeglasses, characterized in that, include: Acquire view distance detection data, input the view distance data into a pre-trained view distance convolutional neural network model, and obtain view distance judgment results; Control the focus of the glasses based on the visual distance determination result; Obtain the raw view distance detection data, input the raw view distance detection data into the pre-stored 3D vision model for preprocessing, and obtain the view distance detection data; Obtain the original training dataset, which includes at least one of the original distance dataset, the original environment dataset, and the original stress dataset; A distance vector set is constructed based on the original distance dataset; the original distance dataset includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye-tracking sensor data; The distance vector set is mapped to three-dimensional coordinates to form distance three-dimensional coordinate data; An environmental vector set is constructed based on the original environmental dataset; the original environmental dataset includes at least one of image sensor data and ambient light sensor data. The environmental vector set is mapped to three-dimensional coordinates to form environmental three-dimensional coordinate data; A pressure vector set is constructed based on the original pressure dataset; the original pressure dataset includes at least one of pressure sensor data and contact sensor data. The pressure vector set is mapped to three-dimensional coordinates to form pressure three-dimensional coordinate data; The three-dimensional visual model is constructed based on the distance three-dimensional coordinate data, the environmental three-dimensional coordinate data, and the pressure three-dimensional coordinate data.

2. The method according to claim 1, characterized in that, The method further includes: Obtain a line-of-sight training dataset; the line-of-sight training dataset includes line-of-sight judgment results and corresponding line-of-sight detection data; the line-of-sight detection data includes at least one of a distance dataset, an environment dataset, and a stress dataset. The convolutional neural network is trained based on the aforementioned distance training dataset to obtain the distance-based convolutional neural network model.

3. The method according to claim 2, characterized in that, After controlling the focus of the glasses based on the viewing distance determination result, the method further includes: The line-of-sight convolutional neural network is modified based on user feedback.

4. The method according to any one of claims 1 to 3, characterized in that, The method of controlling the focus of the glasses based on the distance judgment result includes: If the viewing distance determination result indicates that the target object is not within the current viewing distance range, a focusing prompt is issued, and the glasses are controlled to focus. If the viewing distance determination result indicates that the target object is within the current viewing distance range, a prompt indicating that no focusing is required will be issued.

5. A focusing device for eyeglasses, characterized in that, include: The view distance determination module is used to acquire view distance detection data, input the view distance data into a pre-trained view distance convolutional neural network model, and obtain the view distance determination result. The focusing control module is used to control the focusing of the glasses based on the viewing distance judgment result; The preprocessing module is used to acquire the original view distance detection data, input the original view distance detection data into the pre-stored three-dimensional vision model for preprocessing, and obtain the view distance detection data. The 3D visual model building module includes: The original training dataset acquisition unit is used to acquire the original training dataset, which includes at least one of the original distance dataset, the original environment dataset, and the original stress dataset. A distance vector set construction unit is used to construct a distance vector set based on the original distance dataset; the original distance dataset includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye-tracking sensor data; A distance 3D coordinate construction unit is used to map the distance vector set to 3D coordinates to form distance 3D coordinate data; An environment vector set construction unit is used to construct an environment vector set based on the original environment dataset; the original environment dataset includes at least one of image sensor data and ambient light sensor data. An environment 3D coordinate construction unit is used to map the environment vector set to 3D coordinates to form environment 3D coordinate data; A pressure vector set construction unit is used to construct a pressure vector set based on the original pressure dataset; the original pressure dataset includes at least one of pressure sensor data and contact sensor data. A pressure three-dimensional coordinate construction unit is used to map the pressure vector set to three-dimensional coordinates to form pressure three-dimensional coordinate data; A three-dimensional visual model construction unit is used to construct the three-dimensional visual model based on the distance three-dimensional coordinate data, the environment three-dimensional coordinate data, and the pressure three-dimensional coordinate data.

6. A smart pair of glasses, comprising a sensor, a focusing device, a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 4.

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

Images