AR glasses and safety auxiliary method based on AR glasses

Abstract

The invention discloses AR glasses and a safety auxiliary method based on the AR glasses, and the method comprises the steps: carrying out the light supplementation of an environment through a light supplementation device, facilitating the video collection of a video collection device, carrying out the recognition processing of the video information collected by the video collection device through an auxiliary recognition module, and carrying out the recognition processing of the video information. When the upper computer or the auxiliary recognition module recognizes the stop identifier on the glove, the projection module stops projection, so that the sight of the operator is not influenced. The video information is subjected to dual identification through the auxiliary identification module and the upper computer of the background system, so that the interference of AR glasses on a user can be effectively reduced when the user operates in an uninterrupted power environment, and the safety of the user during operation is improved. Through mutual cooperation of the auxiliary identification module and the background upper computer, real-time monitoring and data processing of a working site are realized, and the reliability and practicability of the system are further enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of AR glasses and relates to an AR glasses and a safety assistance method based on the AR glasses. Background Art

[0002] As a cutting-edge augmented reality device, AR glasses integrate the real environment with digital information, and can provide users with real-time feedback of pictures, videos, etc. through lenses, bringing users an immersive interactive experience. With the continuous advancement of technology, AR glasses are increasingly favored by users and have shown their wide application potential in many fields such as industrial manufacturing and medical health. The quality of its materials directly affects the user's comfort and efficiency, so durability, comfort and practicality must be taken into consideration during design to ensure reliable performance even in harsh industrial environments.

[0003] Current AR glasses technology has made certain progress, but still faces some challenges in practical applications: AR glasses on the market are generally heavy and may cause discomfort when worn for a long time; the functions of existing AR glasses are still relatively limited, and it is difficult to meet the needs of complex working environments, such as safety assistance functions in special scenarios such as non-stop power supply operations; in some specific working environments, existing AR glasses cannot provide users with sufficient safety protection and cannot remind users of safety hazards in the external environment. Summary of the invention

[0004] The purpose of the present invention is to solve the problem in the prior art that AR glasses cannot provide sufficient safety protection for users and cannot remind users of potential safety hazards in the external environment, and to provide an AR glass and a safety assistance method based on the AR glass.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] AR glasses, comprising: a frame, a frame, a video acquisition device, an auxiliary recognition module, an optical display element, a fill light device, a microphone and a nose bridge;

[0007] The frame is connected to the eyeglass frame; the video acquisition device is arranged on both sides of the eyeglass frame, and the auxiliary recognition module is arranged below the video acquisition device; the auxiliary recognition module is connected to the video acquisition device, the auxiliary recognition module is connected to the projection module, the projection module is arranged on the eyeglass frame, and the projection module is externally connected to the host computer; the projection module projects the information sent by the host computer onto the optical display element; the optical display element is arranged on the eyeglass frame, the fill light device is arranged on one side of the video acquisition device, and the fill light device is used to fill light to the environment, so as to facilitate the video acquisition device to perform video acquisition; the nose bridge is arranged between the optical display elements; the microphone is arranged in the nose bridge, and the microphone is used for the background monitoring personnel to communicate with the glasses wearer.

[0008] A further improvement of the present invention is:

[0009] Furthermore, the auxiliary recognition module is connected to the video acquisition device via a connection circuit; the connection circuit is externally connected to a control circuit; and the control circuit controls the connection circuit to send the video acquired by the video acquisition device to the auxiliary recognition module.

[0010] Furthermore, the video acquisition device and the auxiliary recognition module are electrically connected to a host computer at the same time, and the host computer stores the video information acquired by the video acquisition device; the auxiliary recognition module sends the real-time recognition result to the host computer for storage, and the host computer is connected to an alarm device and a microphone. The host computer identifies the stop identifier on the gloves in the video based on the stored video information. If the stop sign is identified, the host computer sends an instruction to the projection module to stop the projection. The alarm device is used to sound an alarm when the recognition result is a stop sign, so as to remind the monitoring personnel to force the power on the AR glasses to be cut off.

[0011] Furthermore, the auxiliary recognition module includes a video segmentation module, an image preprocessing module, an image recognition module and a judgment module; the video segmentation module is used to segment the video into images of different frames; the image preprocessing module performs image denoising, feature enhancement, edge detection, morphological operations and image segmentation on the segmented images; the image recognition module is used to recognize the preprocessed images; the judgment module determines whether the recognized image is a stop identifier on the glove, and if so, the judgment module instructs the projection module below to stop projecting to the optical display element to prevent affecting the user's operation; if not, the recognition continues until a stop sign is obtained.

[0012] Furthermore, the video acquisition device is connected to the host computer based on the WebRTC technology of the UDP communication protocol, and the auxiliary recognition module uploads the recognition result to the host computer through WebRTC; the video acquisition device includes a first camera 3 and a second camera; the optical display element includes a first AR lens and a second AR lens; the first camera is arranged on one side of the first AR lens; the second camera is arranged on the other side of the second AR lens; the auxiliary recognition module includes a first auxiliary recognition module and a second auxiliary recognition module; the first auxiliary recognition module is connected to the first camera; the second auxiliary recognition module is connected to the second camera.

[0013] Furthermore, the connection circuit and the control circuit are both arranged on the frame; a front top cover is arranged on the frame; the front top cover is buckled on the frame to seal the connection circuit and the control circuit.

[0014] A safety assistance method based on AR glasses comprises: when the environment is dim, turning on a fill light device to fill light for the environment; a video acquisition device transmits the acquired video information to an auxiliary recognition module for auxiliary recognition, and when the image recognized by the auxiliary recognition module is a stop sign, a projection module stops projecting to an optical display element to prevent affecting user operations; if not, the recognition continues until a stop sign is obtained; a host computer recognizes a stop identifier on a glove in the video based on the stored video information, and if a stop identifier is recognized, the host computer sends an instruction to the projection module to stop projection, and a background alarm device sounds an alarm to remind monitoring personnel to forcibly power off the AR glasses.

[0015] Furthermore, the video acquisition device transmits the acquired video information to the auxiliary recognition module for auxiliary recognition, specifically:

[0016] Segmenting the video captured by the video capture device into images of different frames;

[0017] Preprocessing the segmented image;

[0018] Input the preprocessed image into the trained support vector machine machine learning model to obtain the recognized image;

[0019] It is determined whether the recognized image is a stop sign. If so, the projection module stops projecting to the optical display element to prevent affecting the user's operation; if not, the recognition continues until a stop sign is obtained.

[0020] Furthermore, the segmented images are preprocessed, specifically: image denoising, feature enhancement, edge detection, morphological operations and image segmentation are performed on the segmented images; bilateral filtering technology is used for denoising, and the image contrast is enhanced through a histogram equalization algorithm, so as to extract the most relevant information from the original image data; the Canny algorithm is used for edge detection, the morphological operations include dilation and erosion steps, and the image segmentation is achieved through a watershed algorithm to eliminate irrelevant details and background noise.

[0021] Furthermore, the trained support vector machine machine learning model is specifically as follows: the image data set is divided into a training set and a test set; the training set is used to learn model parameters, and the test set is used to evaluate the generalization performance of the model; the training set is input into the support vector machine machine learning model for training, and the training results are evaluated based on the test set until the support vector machine machine learning model reaches the convergence condition, thereby obtaining the trained support vector machine machine learning model; the image data set is obtained by segmenting the video pre-collected by the video acquisition device;

[0022] The training of the support vector machine machine learning model is represented as:

[0023]

[0024] Among them, w is the weight vector, b is the bias term, and X i is the i-th eigenvector, Y i is the corresponding category label;

[0025] During the training process, the hinge loss function is used as the optimization target, and the loss function is minimized through an iterative optimization algorithm until the preset convergence condition is met, and the trained support vector machine machine learning model is obtained.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention uses a fill-light device to fill in the environment, which is convenient for the video acquisition device to perform video acquisition. The auxiliary recognition module recognizes and processes the video information collected by the video acquisition device. When the host computer or the auxiliary recognition module recognizes the stop sign on the gloves, the projection module stops projecting to avoid affecting the line of sight of the operator. The present invention uses the auxiliary recognition module and the host computer of the background system to perform dual recognition of video information, which can effectively reduce the interference of AR glasses on users when users are working in an environment without power outages, thereby improving the safety of users when working. The present invention realizes real-time monitoring and data processing of the work site through the mutual cooperation of the auxiliary recognition module and the background host computer. Through wireless network communication, the AR support device and the AR field device can achieve efficient and stable data transmission, further enhancing the reliability and practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 It is a schematic diagram of the structure of the AR glasses of the present invention;

[0030] Figure 2 A schematic diagram of a method for performing auxiliary identification by an auxiliary identification module of the present invention;

[0031] Figure 3 It is a schematic diagram of the process of the safety assistance method based on AR glasses of the present invention;

[0032] Figure 4 Stop sign illustration.

[0033] Among them, 1-frame; 2-frame; 3-first camera; 4-first auxiliary recognition module; 5-first AR lens; 6-microphone; 7-nose bridge; 8-second AR lens; 9-second auxiliary recognition module; 10-second camera; 12-front top cover; 13-control circuit; 14-connection circuit. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0035] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0037] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0038] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0039] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0041] See also Figure 1 The present invention discloses an AR glasses, including: a frame 1, a frame 2, a video acquisition device, an auxiliary recognition module, an optical display element, a fill light device, a microphone 6 and a nose bridge 7;

[0042] The frame 2 is connected to the frame 1; the video acquisition device is arranged on both sides of the frame 1, and the auxiliary recognition module is arranged below the video acquisition device; the auxiliary recognition module is connected to the video acquisition device, the auxiliary recognition module is connected to the projection module, the projection module is arranged on the frame 1, and the projection module is externally connected to the host computer; the projection module projects the information sent by the host computer onto the optical display element; the optical display element is arranged on the frame 1, the fill light device is arranged on one side of the video acquisition device, and the fill light device is used to fill light to the environment, so as to facilitate the video acquisition device to collect video; the nose bridge 7 is arranged between the optical display elements; the microphone 6 is arranged in the nose bridge 7, and the microphone 6 is used for the background monitoring personnel to communicate with the glasses wearer. .

[0043] The auxiliary recognition module is connected to the video acquisition device via a connection circuit 14; the connection circuit 14 is externally connected to a control circuit 13; the control circuit 13 controls the connection circuit 14 to send the video acquired by the video acquisition device to the auxiliary recognition module.

[0044] The video acquisition device and the auxiliary recognition module are electrically connected to the host computer at the same time, and the host computer stores the video information collected by the video acquisition device; the auxiliary recognition module sends the real-time recognition result to the host computer for storage, and the host computer is connected to the alarm device and the microphone. The host computer identifies the stop identifier on the gloves in the video based on the stored video information. If the stop sign is recognized, the host computer sends an instruction to the projection module to stop projection. The alarm device is used to alarm when the recognition result is a stop sign, and remind the monitoring personnel to force the power off of the AR glasses.

[0045] The auxiliary recognition module includes a video segmentation module, an image preprocessing module, an image recognition module and a judgment module; the video segmentation module is used to segment the video into images of different frames; the image preprocessing module performs image denoising, feature enhancement, edge detection, morphological operations and image segmentation on the segmented images; the image recognition module is used to recognize the preprocessed images; the judgment module determines whether the recognized image is a stop identifier on the glove. If so, the judgment module instructs the projection module below to stop projecting to the optical display element to prevent affecting the user's operation; if not, the recognition continues until a stop sign is obtained.

[0046] The video acquisition device is connected to the host computer based on the WebRTC technology of the UDP communication protocol, and the auxiliary recognition module uploads the recognition results to the host computer through WebRTC; the video acquisition device includes a first camera 3 and a second camera 10; the optical display element includes a first AR lens 5 and a second AR lens 8; the first camera 3 is arranged on one side of the first AR lens 5; the second camera 10 is arranged on the other side of the second AR lens 8; the auxiliary recognition module includes a first auxiliary recognition module 4 and a second auxiliary recognition module 9; the first auxiliary recognition module 4 is connected to the first camera 3; the second auxiliary recognition module 9 is connected to the second camera 10.

[0047] The connecting circuit 14 and the control circuit 13 are both arranged on the lens frame 1 ; a front top cover 12 is arranged on the lens frame 1 ; the front top cover 12 is buckled on the lens frame 1 to seal the connecting circuit 14 and the control circuit 13 .

[0048] A safety assistance method based on AR glasses comprises: when the environment is dim, turning on a fill light device to fill light for the environment; a video acquisition device transmits the acquired video information to an auxiliary recognition module for auxiliary recognition, and when the image recognized by the auxiliary recognition module is a stop sign, a projection module stops projecting to an optical display element to prevent affecting user operations; if not, the recognition continues until a stop sign is obtained; a host computer recognizes a stop identifier on a glove in the video based on the stored video information, and if a stop identifier is recognized, the host computer sends an instruction to the projection module to stop projection, and a background alarm device sounds an alarm to remind monitoring personnel to forcibly power off the AR glasses.

[0049] See also Figure 2 The present invention discloses a method for auxiliary identification by an auxiliary identification module, which is specifically:

[0050] S101, dividing the video captured by the video capture device into images of different frames;

[0051] S102, preprocessing the segmented image;

[0052] The segmented images are preprocessed, specifically: image denoising, feature enhancement, edge detection, morphological operations and image segmentation are performed on the segmented images; bilateral filtering technology is used for denoising, and the image contrast is enhanced through the histogram equalization algorithm, so as to extract the most relevant information from the original image data; the Canny algorithm is used for edge detection, the morphological operations include dilation and erosion steps, and the image segmentation is achieved through the watershed algorithm to eliminate irrelevant details and background noise.

[0053] S103, inputting the preprocessed image into a trained support vector machine machine learning model to obtain a recognized image;

[0054] The trained support vector machine machine learning model is specifically as follows: the image data set is divided into a training set and a test set; the training set is used to learn model parameters, and the test set is used to evaluate the generalization performance of the model; the training set is input into the support vector machine machine learning model for training, and the training results are evaluated based on the test set until the support vector machine machine learning model reaches the convergence condition, thereby obtaining the trained support vector machine machine learning model; the image data set is obtained by segmenting the video pre-collected by the video acquisition device;

[0055] The training of the support vector machine machine learning model is represented as:

[0056]

[0057] Among them, w is the weight vector, b is the bias term, and x i is the i-th eigenvector, y i is the corresponding category label;

[0058] During the training process, the hinge loss function is used as the optimization objective, and the loss function is minimized through an iterative optimization algorithm until the preset convergence conditions are met to obtain the trained support vector machine machine learning model.

[0059] S104, determining whether the recognized image is a stop sign, if so, the projection module stops projecting to the optical display element to prevent affecting the user's operation; if not, continue to recognize until a stop sign is obtained.

[0060] Example:

[0061] The present invention provides an AR glasses, including a frame 1, a frame 2, a camera, a video acquisition device, a fill light device, an auxiliary recognition module, an optical display element, a nose bridge, a front top cover 12, a control circuit 13 and a connection circuit 14; the auxiliary recognition module is connected to the video acquisition device through the connection circuit 14; the connection circuit 14 is externally connected to the control circuit 13; the control circuit 13 controls the connection circuit 14 to send the video acquired by the video acquisition device to the auxiliary recognition module. The connection circuit 14 and the control circuit 13 are both arranged on the frame 1; the frame 1 is provided with a front top cover 12; the front top cover 12 is buckled on the frame 1, and the connection circuit 14 and the control circuit 13 are sealed; the fill light device is arranged on one side of the video acquisition device, and the fill light device is used to fill light to the environment, so as to facilitate the video acquisition device to perform video acquisition.

[0062] The outer side of the frame 1 is made of plastic material, the inside of the frame 2 is a metal bracket, and the outer side is wrapped with plastic material to improve the wearing experience of the user. There are function expansion interfaces on both sides of the frame 2 to expand its functions and upgrade related firmware. Sufficient space is reserved on both sides of the frame 1 to place the first camera 3 and the second camera 10; the auxiliary recognition module and the connection circuit 14 can avoid damage caused by related collisions, fully reduce the overall weight, deformation caused by collision and extrusion, and improve the user experience.

[0063] Furthermore, sufficient space is reserved on both sides of the frame 1 to place the first camera 3 and the second camera 10. Through relevant computer network communication protocols and WebRTC technology based on the UDP communication protocol, a connection between the wearer and the host computer can be remotely established to transmit video streaming media, and the scene viewed by the current wearer can be transcribed in real time and sent to the supporting background system. The auxiliary recognition module receives the video information taken by the first camera and the second camera, and when the relevant stop sign is recognized, the transcription mode can be ended.

[0064] Furthermore, the first AR lens 5 and the second AR lens 8 can cooperate with the first camera 3 and the second camera 10 to identify the current scene. At the same time, they can receive the video streaming media processed by auxiliary identification from the background system through WebRTC technology, mark and select specific objects, and help remind the wearer of the points that should be paid attention to during work to prevent misoperation and dangerous behavior.

[0065] Furthermore, the auxiliary recognition module is embedded with a computer vision processing algorithm, which uses the open source OpenCV library to perform image processing tasks. These tasks include, but are not limited to, image denoising, feature enhancement, edge detection, morphological operations, and image segmentation. In the image preprocessing stage, bilateral filtering technology is used for denoising, while the image contrast is enhanced by the histogram equalization algorithm, thereby extracting the most relevant information from the original image data. Edge detection uses the Canny algorithm, morphological operations include dilation and erosion steps, and image segmentation is achieved through the watershed algorithm to eliminate irrelevant details and background noise, and improve the accuracy and speed of image recognition.

[0066] In order to achieve efficient image classification and recognition, the present invention adopts a support vector machine (SVM) machine learning model, which is implemented through the LIBSVM library and provides an easy-to-use interface for rapid integration into the auxiliary recognition module. During the training process of the SVM model, the image data set is divided into a training set and a test set. The training set is used to learn the model parameters, while the test set is used to evaluate the generalization performance of the model. The training process involves solving a quadratic programming problem by maximizing the interval between two types of data points while minimizing the classification error; specifically, the training of SVM is achieved by solving the following quadratic programming problem:

[0067]

[0068] Among them, w is the weight vector, b is the bias term, and x i is the i-th eigenvector, y i is the corresponding category label.

[0069] During the training process, the hinge loss function is used as the optimization target, and an iterative optimization algorithm, such as the sequential minimum optimization (SMO) algorithm, is used to minimize the loss function until the preset convergence conditions are met; for example, a preset number of iterations is reached or the rate of decrease of the loss function is lower than a predetermined threshold.

[0070] The LIBSVM interface allows system designers to directly call pre-trained SVM models without complex programming, thus simplifying the development process. The SVM model trained in the OpenCV environment can be exported as a text file in XML format, so that it can be reused on different platforms and devices, including resource-constrained embedded systems. In real-time application scenarios, AR glasses can read XML parameter files through the programming interface and use these parameters for real-time image recognition and classification inference, ensuring fast response even in dynamic environments.

[0071] In particular, when the AR glasses detect a STOP sign in the user's field of view based on the above algorithm, the auxiliary recognition module immediately triggers a series of safety measures. These measures may include issuing a warning sound to the user, displaying a stop sign on the display of the AR glasses, or activating an emergency stop command in the remote assistance system. This immediate feedback mechanism can effectively prevent users from continuing potentially harmful operations in potentially dangerous situations. In addition, when a stop sign is recognized and the relevant auxiliary functions are activated, the system can also automatically turn off the display optical elements of the AR glasses to avoid distractions when the user needs to concentrate on the external environment. This safety feature is particularly important in scenarios where users may need to respond immediately to external emergencies, such as avoiding obstacles.

[0072] Furthermore, a microphone 6 is installed in the middle of the frame 1. When the wearer turns on the remote auxiliary recognition function, he can communicate with the backstage staff in real time to prevent the wearer from making dangerous and unnecessary operations.

[0073] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An AR glasses, characterized in that: include: Spectacle frame (1), spectacles frame (2), video acquisition device, auxiliary identification module, optical display element, fill light device, microphone (6) and nose bridge (7); The frame (2) is connected to the frame (1); the video acquisition device is arranged on both sides of the frame (1), and the auxiliary recognition module is arranged below the video acquisition device; the auxiliary recognition module is connected to the video acquisition device, the auxiliary recognition module is connected to the projection module, the projection module is arranged on the frame (1), and the projection module is externally connected to a host computer; the projection module projects information sent by the host computer onto an optical display element; the optical display element is arranged on the frame (1), the fill light device is arranged on one side of the video acquisition device, and the fill light device is used to fill light to the environment, so as to facilitate the video acquisition device to perform video acquisition; the nose bridge (7) is arranged between the optical display elements; the microphone (6) is arranged in the nose bridge (7), and the microphone (6) is used for background monitoring personnel to communicate with the glasses wearer.

2. The AR glasses according to claim 1, characterized in that: The auxiliary recognition module is connected to the video acquisition device via a connection circuit (14); the connection circuit (14) is externally connected to a control circuit (13); the control circuit (13) controls the connection circuit (14) to send the video acquired by the video acquisition device to the auxiliary recognition module.

3. The AR glasses according to claim 2, characterized in that: The video acquisition device and the auxiliary recognition module are electrically connected to a host computer at the same time, and the host computer stores the video information acquired by the video acquisition device; The auxiliary recognition module sends the real-time recognition result to the host computer for storage. The host computer is connected to an alarm device and a microphone. The host computer identifies the stop identifier on the glove in the video based on the stored video information. If the stop identifier is identified, the host computer sends an instruction to the projection module to stop projection. The alarm device is used to sound an alarm when the recognition result is a stop sign, reminding the monitoring personnel to force the AR glasses to power off.

4. The AR glasses according to claim 3, characterized in that: The auxiliary recognition module includes a video segmentation module, an image preprocessing module, an image recognition module and a judgment module; the video segmentation module is used to segment the video into images of different frames; the image preprocessing module performs image denoising, feature enhancement, edge detection, morphological operations and image segmentation on the segmented images; the image recognition module is used to recognize the preprocessed images; the judgment module determines whether the recognized image is a stop identifier on the glove, and if so, the judgment module instructs the projection module below to stop projecting to the optical display element to prevent affecting the user's operation; if not, the recognition continues until a stop sign is obtained.

5. The AR glasses according to claim 4, characterized in that: The video acquisition device is connected to a host computer based on the WebRTC technology of the UDP communication protocol, and the auxiliary recognition module uploads the recognition result to the host computer through WebRTC; the video acquisition device comprises a first camera (3) and a second camera (10); the optical display element comprises a first AR lens (5) and a second AR lens (8); the first camera (3) is arranged on one side of the first AR lens (5); the second camera (10) is arranged on the other side of the second AR lens (8); the auxiliary recognition module comprises a first auxiliary recognition module (4) and a second auxiliary recognition module (9); the first auxiliary recognition module (4) is connected to the first camera (3); and the second auxiliary recognition module (9) is connected to the second camera (10).

6. The AR glasses according to claim 5, characterized in that: The connecting circuit (14) and the control circuit (13) are both arranged on the spectacles frame (1); a front top cover (12) is arranged on the spectacles frame (1); the front top cover (12) is buckled on the spectacles frame (1) to seal the connecting circuit (14) and the control circuit (13).

7. A safety assistance method based on AR glasses, characterized in that: include: When the environment is dim, turn on the fill light device to fill in the environment; The video acquisition device transmits the acquired video information to the auxiliary recognition module for auxiliary recognition. When the image recognized by the auxiliary recognition module is a stop sign, the projection module stops projecting to the optical display element to prevent affecting the user's operation; if not, it continues to recognize until a stop sign is obtained; the host computer identifies the stop identifier on the glove in the video based on the stored video information. If the stop identifier is recognized, the host computer sends an instruction to the projection module to stop projection, and the background alarm device sounds an alarm to remind the monitoring personnel to force the power on the AR glasses to be cut off.

8. The safety assistance method based on AR glasses according to claim 7, characterized in that: The video acquisition device transmits the acquired video information to the auxiliary recognition module for auxiliary recognition, specifically: Segmenting the video captured by the video capture device into images of different frames; Preprocessing the segmented image; Input the preprocessed image into the trained support vector machine machine learning model to obtain the recognized image; It is determined whether the recognized image is a stop sign. If so, the projection module stops projecting to the optical display element to prevent affecting the user's operation; if not, the recognition continues until a stop sign is obtained.

9. The safety assistance method based on AR glasses according to claim 8, characterized in that: The segmented images are preprocessed, specifically: image denoising, feature enhancement, edge detection, morphological operation and image segmentation are performed on the segmented images; bilateral filtering technology is used for denoising, and image contrast is enhanced by a histogram equalization algorithm, so as to extract the most relevant information from the original image data; edge detection uses the Canny algorithm, the morphological operation includes dilation and erosion steps, and image segmentation is achieved by a watershed algorithm to eliminate irrelevant details and background noise.

10. The safety assistance method based on AR glasses according to claim 9, characterized in that: The trained support vector machine machine learning model is specifically as follows: the image data set is divided into a training set and a test set; the training set is used to learn model parameters, and the test set is used to evaluate the generalization performance of the model; the training set is input into the support vector machine machine learning model for training, and the training results are evaluated based on the test set until the support vector machine machine learning model reaches the convergence condition, thereby obtaining the trained support vector machine machine learning model; the image data set is obtained by segmenting the video pre-collected by the video acquisition device; The training of the support vector machine machine learning model is represented as: Among them, w is the weight vector, b is the bias term, and X i is the i-th eigenvector, Y i is the corresponding category label; During the training process, the hinge loss function is used as the optimization objective, and the loss function is minimized through an iterative optimization algorithm until the preset convergence conditions are met to obtain the trained support vector machine machine learning model.

Images