Focusing method and device of glasses, intelligent glasses and storage medium

Abstract

The invention relates to a glasses focusing method and device, intelligent glasses and a storage medium, and the method comprises the steps: obtaining sight distance detection data, inputting the sight distance data into a pre-trained sight distance convolutional neural network model, and obtaining a sight distance judgment result; and controlling the glasses to focus on the basis of the sight distance judgment result. Aiming at the situations that glasses of a user are frequently replaced in different eye using scenes, the adaptability of zoom glasses is poor, discomfort and even potential safety hazards exist, and an automatic focusing technology is complex, the current sight distance can be accurately judged according to the real sight distance of the user through the convolutional neural network, errors are reduced, the automatic focusing function of the glasses is optimized, and the user experience is improved. And the user experience is improved.

Description

Technical Field

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

[0002] As the population ages, the number of elderly people is increasing rapidly, and the prospects for elderly-friendly products are becoming more and more promising. By combining ease of use, safety, health support, adaptability and comfort, and making full use of advanced technology, elderly-friendly products can significantly improve the quality of life of the elderly, bringing a win-win situation for enterprises and society.

[0003] On the other hand, people's lifestyles have also changed due to the development of electronic products, such as a decrease in outdoor activities and an increase in eye demand. People use smartphones, tablets, computers, televisions and other devices for a long time, which increases the burden on their eyes. Some elderly people have both myopia and presbyopia, or hyperopia, and usually need to buy multiple pairs of glasses. They wear reading glasses in scenes such as reading, and wear myopia glasses in scenes such as outdoors, which is inconvenient in daily life. Current bifocal or progressive lenses can easily cause the wearer to have unnatural vision at different viewing distances, and there is a certain adaptation period, which may cause dizziness or other discomfort, and even increase the risk of falling when walking for older users. Furthermore, the current automatic focusing glasses are technically complex to implement, and the focusing effect is not good. Summary of the invention

[0004] The present invention provides a focusing method and device for glasses, smart glasses and a storage medium, so as to improve the reliability and convenience of automatic focusing of glasses and improve the user experience.

[0005] In a first aspect, the present disclosure provides a focusing method for glasses, comprising:

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

[0007] The focusing of the glasses is controlled based on the visual distance judgment result.

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

[0009] Original sight distance detection data is obtained, and the original sight distance detection data is input into a pre-stored three-dimensional vision model for preprocessing to obtain the sight distance detection data.

[0010] In some embodiments, an original training data set is obtained, wherein the original training data set includes at least one of an original distance data set, an original environment data set, and an original pressure data set;

[0011] Constructing a distance vector set based on the original distance data set; the original distance data set includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye tracking sensor data;

[0012] Mapping the distance vector set to three-dimensional coordinates to form distance three-dimensional coordinate data;

[0013] Constructing an environment vector set based on the original environment data set; the original environment data set includes at least one of image sensor data and ambient light sensor data;

[0014] Mapping the environmental vector set to three-dimensional coordinates to form environmental three-dimensional coordinate data;

[0015] Constructing a pressure vector set based on the original pressure data set; the original pressure data set includes at least one of pressure sensor data and contact sensor data;

[0016] Mapping the pressure vector set 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 environment three-dimensional coordinate data and the pressure three-dimensional coordinate data.

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

[0019] Acquire a sight distance training data set; the sight distance training data set includes a sight distance judgment result and corresponding sight distance detection data; the sight distance detection data includes at least one of a distance data set, an environment data set, and a pressure data set;

[0020] The convolutional neural network is trained based on the line-of-sight training data set to obtain the line-of-sight convolutional neural network model.

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

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

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

[0024] If the visual distance judgment result is that the target visual object is not within the current visual distance range, a focus adjustment prompt is issued and the glasses are controlled to focus;

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

[0026] In a second aspect, the present disclosure provides a focusing device for glasses, comprising:

[0027] A sight distance judgment module is used to obtain sight distance detection data, input the sight distance data into a pre-trained sight distance convolutional neural network model, and obtain a sight distance judgment result;

[0028] A focus control module is used to control the focus of the glasses based on the visual distance judgment result.

[0029] In some embodiments, the device further comprises a pre-processing module for:

[0030] Original sight distance detection data is obtained, and the original sight distance detection data is input into a pre-stored three-dimensional vision model for preprocessing to obtain the sight distance detection data.

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

[0032] An original training data set acquisition unit, used to acquire an original training data set, wherein the original training data set includes at least one of an original distance data set, an original environment data set, and an original pressure data set;

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

[0034] A distance three-dimensional coordinate construction unit, used for mapping the distance vector set to three-dimensional coordinates to form distance three-dimensional coordinate data;

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

[0036] An environment three-dimensional coordinate construction unit, used for mapping the environment vector set to three-dimensional coordinates to form environment three-dimensional coordinate data;

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

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

[0039] A three-dimensional visual model building unit is used to build 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 comprises a line-of-sight convolutional neural network model building module, comprising:

[0041] A sight distance training data set acquisition unit, used to acquire a sight distance training data set; the sight distance training data set includes a sight distance judgment result and corresponding sight distance detection data; the sight distance detection data includes at least one of a distance data set, an environment data set and a pressure data set;

[0042] A convolutional neural network training unit is used to train a convolutional neural network based on the line-of-sight training data set to obtain the line-of-sight convolutional neural network model.

[0043] In some embodiments, the device 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 focus control module is specifically used to:

[0045] If the visual distance judgment result is that the target visual object is not within the current visual distance range, a focus adjustment prompt is issued and the glasses are controlled to focus;

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

[0047] In a third aspect, the present disclosure provides a pair of 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] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0049] In a fifth aspect, the present disclosure provides a computer program product, including a computer program / instructions, which implements the steps of the method described in the above aspects when the computer program is executed by a processor.

[0050] The present disclosure provides a method and device for adjusting the focus of glasses, smart glasses and storage medium, the method comprising obtaining visual distance detection data, inputting the visual distance data into a pre-trained visual distance convolutional neural network model, obtaining a visual distance judgment result; and controlling the focusing of glasses based on the visual distance judgment result. In view of the fact that users frequently change glasses in different eye use scenarios, the poor adaptability of zoom glasses causes discomfort and even safety hazards, and the complex automatic focusing technology, the present application can accurately judge the current visual distance according to the user's actual visual distance through a convolutional neural network, reduce errors, optimize the automatic focusing function of glasses, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[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 diagram of a flow chart of a focusing method for glasses provided in an embodiment of the present disclosure;

[0053] Figure 2 A schematic flow chart of a method for constructing a three-dimensional visual model in a method for adjusting the focus of glasses provided in an embodiment of the present disclosure;

[0054] Figure 3 A further flow chart of a method for training a convolutional neural network model in a method for adjusting the focus of glasses provided in an embodiment of the present disclosure;

[0055] Figure 4 Another schematic flow chart of a method for training a convolutional neural network model in a method for adjusting the focus of glasses provided in an embodiment of the present disclosure;

[0056] Figure 5 Another schematic diagram of a flow chart of a focusing method of glasses provided in an embodiment of the present disclosure;

[0057] Figure 6 A schematic structural diagram of a focusing device for glasses provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0059] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

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

[0061] The present invention provides a focusing method and device for glasses, smart glasses and a storage medium, which can accurately judge the current viewing distance according to the user's actual viewing distance through a convolutional neural network, reduce errors, optimize the automatic focusing function of the glasses, and improve the user experience.

[0062] Embodiment 1

[0063] Figure 1 A schematic flow chart of a focusing method for glasses provided in an embodiment of the present disclosure.

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

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

[0066] In a specific example, the line of sight detection data is data of the external environment and the user himself detected by multiple sensors, including but not limited to data collected by distance sensors, image sensors, accelerometers, gyroscope sensors, 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 the data obtained by the distance sensor combined with the gyroscope sensor, accelerometer, and eye tracking sensor. The brightness of the user's target object and the surrounding environment are determined based on the data obtained by the image sensor combined with the ambient light sensor. The user's own eye state and other information are determined based on the data obtained by the pressure and contact sensors. Based on the angle, distance, external environment and user's eye condition of the above target object, the viewing distance of the user's current target object is determined to fully meet the user's actual needs.

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

[0069] Original sight distance detection data is obtained, and the original sight distance detection data is input into a pre-stored three-dimensional vision model for preprocessing to obtain the sight distance detection data.

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

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

[0072] In some embodiments, step 102 includes:

[0073] If the visual distance judgment result is that the target visual object is not within the current visual distance range, a focus adjustment prompt is issued and the glasses are controlled to focus;

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

[0075] In some embodiments, when the user moves, turns around, turns his head, or rotates his eyes, the target visual object changes, and focusing may be required. During the focusing process, the user is prompted to remind the user to temporarily close his eyes and wait, so as to avoid dizziness and other discomfort, or to avoid dissatisfaction caused by the user not being able to see the target clearly during the focusing process, thereby further improving the user experience.

[0076] On the other hand, if a prompt is given that no focusing is required or that focusing is completed, but the user feels that the viewing distance judgment is incorrect, they can issue a focusing command on their own to meet current needs and provide feedback to the smart glasses to promote further training of the viewing distance convolutional neural network.

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

[0078] In a specific example, the prompt that no focusing is required is a green indicator light to prompt the user that the current viewing distance judgment result is within the current viewing distance range of the glasses and no focusing is required.

[0079] In actual 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, automatic focusing is not performed. If the object is not within the normal distance, automatic focusing is performed and the results are fed back to the 3D vision model for further training.

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

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

[0082] If the current line of sight R n If it is within the normal viewing distance range, the intelligent indicator light is controlled to 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 no automatic focusing is required.

[0083] If the current line of sight R n If it is not within the normal viewing distance range, the intelligent indicator light is controlled to display a red light according to the pre-stored viewing distance mapping relationship, indicating that the measured viewing distance is not within the normal viewing distance range, and automatic focusing is performed.

[0084] The focusing method of glasses provided in the embodiment of the present invention can accurately judge the current viewing distance according to the user's actual viewing distance through a convolutional neural network, reduce errors, optimize the automatic focusing function of the glasses, and improve the user experience.

[0085] Embodiment 2

[0086] On the basis of the above-mentioned embodiments, the focusing method of glasses provided by the present invention further includes a step of constructing a three-dimensional visual model.

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

[0088] Step 201: Acquire an original training data set, where the original training data set includes at least one of an original distance data set, an original environment data set, and an original pressure data set.

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

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

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

[0092] In a specific example, the distance vector set M[a1, a2...a n ], where a n Represents the nth distance vector. Map the distance vector set to three-dimensional coordinates to form the three-dimensional coordinate data of the distance vector of the viewing distance (X M , Y M , Z M ).

[0093] Step 204: constructing an environment vector set based on the original environment data set; the original environment data set 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 environment three-dimensional coordinate data.

[0095] In a specific example, the ambient light data collected by the image sensor and the ambient light sensor are used to construct the ambient vector set K[b1,b2...bn ], where b n Represents the nth environmental vector collected. The environmental vector set is mapped to three-dimensional coordinates to form the three-dimensional coordinate data of the environmental vector (X K , Y K , Z K ).

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

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

[0098] In a specific example, the pressure vector set F[c1,c2...c n ], where c n Represents the nth pressure vector collected. The pressure vector set is mapped to three-dimensional coordinates to form the pressure vector three-dimensional coordinate data (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, each raw data is pre-processed by screening and filtering, and the pre-processed distance, illumination, and pressure data are output to improve the reliability and accuracy of the collected data and effectively reduce the final line of sight error.

[0101] Embodiment 3

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

[0103] like Figure 3 As shown, the training method of the convolutional neural network model includes:

[0104] Step 301: Acquire a sight distance training data set; the sight distance training data set includes a sight distance judgment result and corresponding sight distance detection data; the sight distance detection data includes at least one of a distance data set, an environment data set, and a pressure data set.

[0105] In a specific example, the line-of-sight training data set is data that has been preprocessed by a three-dimensional vision model to improve the reliability and stability of the line-of-sight convolutional neural network model and avoid interference with neural network training caused by abnormal data.

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

[0107] In some embodiments, the convolutional neural network is trained by using the distance, illumination, and pressure data in the three-dimensional visual model to obtain a convolutional neural network model. Optionally, the convolutional neural network model records the mapping relationship between the three-dimensional visual model and the intelligent indicator light.

[0108] In a specific example, a convolutional neural network is trained using data in a three-dimensional vision model to obtain a convolutional neural network model. When the position is measured at a certain viewing distance, the convolutional neural network model judges the measured viewing distance and outputs a judgment result.

[0109] Further, the trained convolution can be used. In some embodiments, the method further includes:

[0110] Step 303: Modify the sight-range convolutional neural network based on user feedback.

[0111] As the user ages, the degree of myopia and hyperopia of the user may change. The method provided in the embodiment of the present invention can continuously train the convolutional neural network model according to the actual viewing distance to meet the actual needs of the user.

[0112] The convolutional neural network model is trained using the data of the three-dimensional visual model to obtain a convolutional network model that is closer to the actual viewing distance seen by the user. For example, when the user is an elderly person with both myopia and hyperopia, the focusing method provided in the embodiment of the present invention can provide a viewing distance convolutional network model that is closer to actual needs.

[0113] Embodiment 4

[0114] Based on the above embodiments, Figure 4 Another implementation flow chart of a convolutional neural network model training method in the glasses focusing method provided in an embodiment of the present invention is shown.

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

[0116] First, a three-dimensional vision model is established based on the collected data, and a convolutional neural network model is established using the data output by the three-dimensional vision model.

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

[0118] Determine whether the error of the test data set meets the requirements. If so, it is determined that the convolutional neural network training is completed. If not, the steps of selecting data from the training data set to train the convolutional neural network parameters are executed repeatedly until the error of the test data set meets the requirements.

[0119] Figure 5 A schematic diagram of another implementation flow of the focusing method for glasses provided in an embodiment of the present invention is shown.

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

[0121] First, various sensors are used to collect data such as distance, light, and pressure, and a 3D visual model is established based on these data. The convolutional neural network is trained using the data in the 3D visual model to produce a convolutional neural network model.

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

[0123] Determine 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, and objects can be viewed normally without automatic focusing. If the current viewing distance is not within the normal range, the smart light will display red, and objects cannot be viewed normally. The viewing distance result will be fed back for automatic focusing.

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

[0125] Embodiment 5

[0126] Figure 6 A focusing device for glasses provided by an embodiment of the present invention is shown, comprising:

[0127] A sight distance judgment module is used to obtain sight distance detection data, input the sight distance data into a pre-trained sight distance convolutional neural network model, and obtain a sight distance judgment result;

[0128] A focus control module is used to control the focus of the glasses based on the visual distance judgment result.

[0129] In some embodiments, the device further comprises a pre-processing module for:

[0130] Original sight distance detection data is obtained, and the original sight distance detection data is input into a pre-stored three-dimensional vision model for preprocessing to obtain the sight distance detection data.

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

[0132] An original training data set acquisition unit, used to acquire an original training data set, wherein the original training data set includes at least one of an original distance data set, an original environment data set, and an original pressure data set;

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

[0134] A distance three-dimensional coordinate construction unit, used for mapping the distance vector set to three-dimensional coordinates to form distance three-dimensional coordinate data;

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

[0136] An environment three-dimensional coordinate construction unit, used for mapping the environment vector set to three-dimensional coordinates to form environment three-dimensional coordinate data;

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

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

[0139] A three-dimensional visual model building unit is used to build 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 comprises a line-of-sight convolutional neural network model building module, comprising:

[0141] A sight distance training data set acquisition unit, used to acquire a sight distance training data set; the sight distance training data set includes a sight distance judgment result and corresponding sight distance detection data; the sight distance detection data includes at least one of a distance data set, an environment data set and a pressure data set;

[0142] A convolutional neural network training unit is used to train a convolutional neural network based on the line-of-sight training data set to obtain the line-of-sight convolutional neural network model.

[0143] In some embodiments, the device 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 focus control module is specifically used to:

[0145] If the visual distance judgment result is that the target visual object is not within the current visual distance range, a focus adjustment prompt is issued and the glasses are controlled to focus;

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

[0147] The focusing device of glasses provided in the embodiment of the present invention is used to obtain visual distance detection data, input the visual distance data into a pre-trained visual distance convolutional neural network model, obtain a visual distance judgment result; and control the focusing of glasses based on the visual distance judgment result. In view of the fact that users frequently change glasses in different eye use scenarios, the poor adaptability of zoom glasses causes discomfort and even safety hazards, and the complex automatic focusing technology, the focusing device provided in the embodiment of the present invention can accurately judge the current visual distance according to the user's actual visual distance through a convolutional neural network, reduce errors, optimize the automatic focusing function of glasses, and improve the user experience.

[0148] Embodiment 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 implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

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

[0152] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0153] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof. The computer-readable storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CDROM, DVDROM, Blu-ray disc, etc.).

[0154] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a 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 runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

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

[0156] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

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

[0158] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including 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 limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0160] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A method for adjusting the focus of glasses, characterized in that: include: Acquire sight distance detection data, input the sight distance data into a pre-trained sight distance convolutional neural network model, and obtain a sight distance judgment result; The focusing of the glasses is controlled based on the visual distance judgment result.

2. The method according to claim 1, characterized in that The obtaining of sight distance detection data comprises: Original sight distance detection data is obtained, and the original sight distance detection data is input into a pre-stored three-dimensional vision model for preprocessing to obtain the sight distance detection data.

3. The method according to claim 2, characterized in that The method further comprises: Acquire an original training data set, where the original training data set includes at least one of an original distance data set, an original environment data set, and an original pressure data set; Constructing a distance vector set based on the original distance data set; the original distance data set includes at least one of distance sensor data, image sensor data, accelerometer data, gyroscope sensor data, and eye tracking sensor data; Mapping the distance vector set to three-dimensional coordinates to form distance three-dimensional coordinate data; Constructing an environment vector set based on the original environment data set; the original environment data set includes at least one of image sensor data and ambient light sensor data; Mapping the environmental vector set to three-dimensional coordinates to form environmental three-dimensional coordinate data; Constructing a pressure vector set based on the original pressure data set; the original pressure data set includes at least one of pressure sensor data and contact sensor data; Mapping the pressure vector set 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 environment three-dimensional coordinate data and the pressure three-dimensional coordinate data.

4. The method according to claim 1, characterized in that The method further comprises: Acquire a sight distance training data set; the sight distance training data set includes a sight distance judgment result and corresponding sight distance detection data; the sight distance detection data includes at least one of a distance data set, an environment data set, and a pressure data set; The convolutional neural network is trained based on the line-of-sight training data set to obtain the line-of-sight convolutional neural network model.

5. The method according to claim 4, characterized in that After controlling the focusing of the glasses based on the visual distance judgment result, the method further includes: The sight-range convolutional neural network is modified based on user feedback.

6. The method according to any one of claims 1 to 5, characterized in that: The controlling the focusing of the glasses based on the visual distance judgment result comprises: If the visual distance judgment result is that the target visual object is not within the current visual distance range, a focus adjustment prompt is issued and the glasses are controlled to focus; If the viewing distance judgment result is that the target visual object is within the current viewing distance range, a prompt is issued indicating that no focusing is required.

7. A focusing device for glasses, characterized in that: include: A sight distance judgment module is used to obtain sight distance detection data, input the sight distance data into a pre-trained sight distance convolutional neural network model, and obtain a sight distance judgment result; A focus control module is used to control the focus of the glasses based on the visual distance judgment result.

8. A pair of smart 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 6.

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

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images