Intelligent aiming system of electronic aiming mirror

Abstract

The invention discloses an electronic sight intelligent aiming system, and particularly relates to the technical field of eye movement tracking, the electronic sight intelligent aiming system comprises a data acquisition module, a target identification module, an eye movement tracking module and a man-machine interaction module, the data acquisition module comprises an image acquisition unit and a distance measurement unit, and is used for acquiring images and distance data in a target area; the image data and the distance data are collected and transmitted to the target recognition module for processing, the target recognition module comprises a state evaluation unit and is used for extracting features by analyzing the image data and the distance data and recognizing and predicting the motion trail of a target, and the eye movement tracking module comprises a sight capturing unit and an attention analysis unit. The infrared camera and the optical sensor are used for detecting eyeball movement, analyzing sight change in real time and dynamically adjusting an aiming point according to sight data, the man-machine interaction module comprises a user input interface and a feedback display unit, and a user inputs an instruction, adjusts an aiming mode and displays the aiming point through a display screen. And feeding back the target identification result and the distance information to the user.

Description

Technical Field

[0001] The present invention relates to the field of eye tracking technology, and more specifically, to an electronic sighting mirror intelligent aiming system. Background Art

[0002] In traditional mechanical aiming systems, shooters need to rely on vision and experience to judge the position, distance and direction of the target, and manually adjust the sight to correct the deviation. However, due to the external environment, physiological differences of shooters and dynamic changes of targets, the accuracy and reliability of traditional systems have certain limitations. Especially in long-range shooting, low-light environment or complex weather conditions, the effectiveness of traditional aiming systems is greatly reduced.

[0003] In order to improve aiming accuracy and reaction speed, an electronic sight intelligent aiming system uses built-in sensors to accurately measure the distance to the target, and uses image recognition technology to analyze the target's position and movement trajectory in real time, providing the shooter with more accurate aiming data. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an electronic sighting scope intelligent aiming system to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an electronic sighting scope intelligent aiming system, comprising a data acquisition module, a target recognition module, an eye tracking module, and a human-computer interaction module;

[0006] The data acquisition module includes an image acquisition unit and a distance measurement unit, which are used to acquire images and distance data within the target area and transmit them to the target recognition module for processing;

[0007] The target recognition module includes a state evaluation unit, which extracts features and performs recognition by analyzing image data and distance data to predict the movement trajectory of the target;

[0008] The eye tracking module includes a sight line capture unit and an attention analysis unit, which uses an infrared camera and an optical sensor to detect eye movements, analyze sight line changes in real time, and dynamically adjust the aiming point based on the sight line data;

[0009] The human-computer interaction module includes a user input interface and a feedback display unit. The user adjusts the aiming mode by inputting instructions, and the target recognition result and distance information are fed back to the user through the display screen.

[0010] In a preferred embodiment, the data acquisition module includes an image acquisition unit and a distance measurement unit, which are used to acquire images and distance data within the target area and transmit them to the target recognition module for processing. The specific steps are as follows:

[0011] Step A1, data acquisition: the image acquisition unit acquires the image of the target area in real time through a high-resolution camera, the resolution of the image acquisition is W×H, which means the width is W pixels and the height is H pixels, and the mathematical expression of each frame of the image acquired is: I(t)={I(x,y)|x=1,2,..,W; y=1,2,...,H}, wherein the color information of each pixel is I(x,y), and x and y respectively represent the horizontal and vertical coordinates of the image; the distance measurement unit uses a laser rangefinder to measure the distance from the sight to the target, and the obtained distance is D(t), which represents the distance acquired at time t;

[0012] Step A2, data transmission: Encapsulate the image data I(t) and the distance data D(t) into a data packet, which includes the time point of data acquisition, the image information of the target area and the distance measured at time t, and transmit the data to the target recognition module through a high-speed serial connection.

[0013] In a preferred embodiment, the target recognition module includes a state evaluation unit, which extracts features and performs recognition by analyzing image data and distance data to predict the motion trajectory of the target. The specific steps are as follows:

[0014] Step B1, feature extraction: receiving a data packet from the data acquisition module and initializing it, extracting image data I(t) and distance data D(t) from the data packet, using Gaussian filtering to smooth the distance data and reduce the impact of noise, and extracting image features through a convolutional neural network, further comprising the following steps:

[0015] Step B101, the convolutional neural network is composed of multiple convolutional layers, pooling layers, and fully connected layers. For a convolutional layer, the input is an image I(t), the convolution kernel is K, and the output is a feature map F(t)=I(t)*K, where * represents a convolution operation, and F(t) is the output feature map of the layer;

[0016] Step B102, the pooling layer performs dimensionality reduction processing on the feature F(t) output by the convolutional layer, and outputs the pooling result R(t)=MaxPooling(F(t)) to reduce the amount of calculation, where R(t) is the feature map after pooling and MaxPooling is the pooling operation;

[0017] Step B103, the fully connected layer is used to linearly combine the features extracted by the convolution layer and the pooling layer, and output the final class probability pooled feature vector as R(t), the first weight matrix is ​​represented as ω, the first bias is represented as b, the output of the fully connected layer is: Y(t) = ωR(t) + b, and the output is converted into the probability of the target category through the activation function Among them, Y(t)i is the value of the i-th class in the output vector Y(t) of the fully connected layer, Y(t) j is the original output value of the jth class among all categories, is the probability of the i-th category, M is the total number of categories;

[0018] Step B2: Target motion trajectory prediction: Concatenate the extracted image features with the smoothed distance data to form a joint feature vector F fused , through the analysis and comparison of continuous image frames, the target's motion trajectory is predicted. The specific steps are as follows:

[0019] Step B201, by analyzing the changes of two consecutive frames of images and distance data, the movement trend of the target in time is obtained, and the dynamic changes of the target are predicted by processing the time series data;

[0020] Step B202: Set the historical data of the target location at different times as Joint eigenvector F fused As input features, the target position Z(t) is used as the target output for linear regression training. The specific formula is: in, is the second weight, λ is the second bias, and the predicted position of the target at the future time t+τt is Repeat the above steps to continuously acquire new features and update the prediction to form a complete motion trajectory.

[0021] In a preferred embodiment, the sight capture unit calculates the sight direction and aiming point through pupil positioning, and performs dynamic adjustment to achieve accurate detection of eye movement. The specific steps are as follows:

[0022] Step C1, pupil location: Use an infrared camera to emit infrared light to illuminate the eyeball. The infrared light is received by the camera after being reflected on the surface of the eyeball. Image processing technology is used to identify the pupil and corneal reflection points to obtain the pupil center coordinates (x p ,y p ) and the coordinates of the corneal reflection point (x c ,y c );

[0023] Step C2, sight direction: Calculate the sight vector according to the position coordinates of the pupil and corneal reflection point. The specific calculation formula is: Where V is the sight vector, (x p ,y p ) and (x c ,y c ) are the coordinates of the pupil and corneal reflection points respectively. The sight vector is normalized and mapped to the screen coordinate system. The aiming point P is calculated by setting the screen center as the origin. aim =Cscreen +η·V norm , where P aim is the aiming point, C screen is the screen center coordinate, η is the magnification factor of the sight vector, is the normalized sight line vector;

[0024] Step C3, real-time tracking and feedback: The eyeball image is captured in real time by an infrared camera, and steps C1 and C2 are continued to update the coordinates of the pupil and corneal reflection points according to the calculated aiming point P. aim Dynamically adjust aiming.

[0025] In a preferred embodiment, the attention analysis unit calculates the user's gaze time on each area based on the aiming point coordinates obtained by the sight capture unit, constructs a heat map of the focus area, marks the dynamic area that the user is paying attention to, and detects whether the user's attention is shifted by analyzing the eye movement trajectory. The specific steps are as follows:

[0026] Step D1, focus area analysis: divide the screen into multiple areas, and determine the area R where the current aiming point is located according to the aiming point obtained from the sight capture unit. aim , count users in area R aim The gaze time of each area is converted into a heat map to show the hot spots that the user pays attention to, where the color depth represents the gaze time. aim The total fixation time formula is: The fixation time T of each area is focus Converted into heat map value, the specific formula is: Among them, t δ is the duration of the δth aiming point, T focus is the total fixation time, L is the number of aiming points, T max is the maximum fixation time of all regions, H aim is the heatmap value;

[0027] Step D2, attention shift detection: For each frame of eye movement data, record the coordinates of the current gaze point and the previous gaze point, and calculate the moving distance between the gaze points as Among them, (x α ,y α ) and (x β ,y β ) are the coordinates of the αth and βth fixation points, D move is the distance the user moves between the two gaze points; set a deviation threshold D threshold , when D move Exceeding the deviation threshold D threshold , indicating that attention has shifted.

[0028] In a preferred embodiment, the human-computer interaction module includes a user input interface and a feedback display unit. The user adjusts the aiming mode by inputting instructions, and the target recognition result and distance information are fed back to the user through the display screen. The specific steps are as follows:

[0029] Step S1, monitoring the user's instructions through the input interface, parsing the user's instructions and applying them to the system, adjusting the aiming mode, displaying the target recognition results to the user through the feedback display unit, including the target category, target position, and target distance information, and displaying the aiming point, target outline, and motion trajectory prediction information on the display screen to provide real-time feedback to the user;

[0030] Step S2: When the user continuously inputs new commands, a loop is entered to continuously draw new target data. By continuously updating target recognition, distance measurement, eye movement capture and feedback display, a closed-loop feedback system is formed to provide real-time information to the user.

[0031] The beneficial effects of the present invention are: combining human-computer interaction with perception technology, providing real-time feedback and optimizing the aiming process through sensors and intelligent algorithms, capturing the shooter's line of sight direction using eye tracking technology, determining the shooter's attention focus area by tracking eye movements, and applying this information to the intelligent adjustment of the aiming point. In this way, the present invention can automatically adjust the aiming angle based on the shooter's visual focus to improve shooting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0034] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0035] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0036] Example 1

[0037] This embodiment provides Figure 1 An electronic sighting mirror intelligent aiming system is shown, which specifically includes a data acquisition module, a target recognition module, an eye tracking module, and a human-computer interaction module;

[0038] The data acquisition module includes an image acquisition unit and a distance measurement unit, which are used to acquire images and distance data within the target area and transmit them to the target recognition module for processing;

[0039] The target recognition module includes a state evaluation unit, which extracts features and performs recognition by analyzing image data and distance data to predict the movement trajectory of the target;

[0040] The eye tracking module includes a sight line capture unit and an attention analysis unit, which uses an infrared camera and an optical sensor to detect eye movements, analyze sight line changes in real time, and dynamically adjust the aiming point based on the sight line data;

[0041] The human-computer interaction module includes a user input interface and a feedback display unit. The user adjusts the aiming mode by inputting instructions, and the target recognition result and distance information are fed back to the user through the display screen.

[0042] In this embodiment, the data acquisition module specifically needs to be explained. The data acquisition module includes an image acquisition unit and a distance measurement unit, which are used to collect images and distance data in the target area and transmit them to the target recognition module for processing to improve the accuracy of aiming. The specific steps are as follows:

[0043] Step A1, data acquisition: the image acquisition unit acquires the image of the target area in real time through a high-resolution camera, the resolution of the image acquisition is W×H, which means the width is W pixels and the height is H pixels, and the mathematical expression of each frame of the image acquired is: I(t)={I(x,y)|x=1,2,..,W; y=1,2,...,H}, wherein the color information of each pixel is I(x,y), and x and y respectively represent the horizontal and vertical coordinates of the image; the distance measurement unit uses a laser rangefinder to measure the distance from the sight to the target, and the obtained distance is D(t), which represents the distance acquired at time t;

[0044] Step A2, data transmission: Encapsulate the image data I(t) and the distance data D(t) into a data packet, which includes the time point of data acquisition, the image information of the target area and the distance measured at time t, and transmit the data to the target recognition module through a high-speed serial connection.

[0045] In this embodiment, the target recognition module specifically needs to be explained. The target recognition module includes a state evaluation unit, which extracts features and performs recognition by analyzing image data and distance data to predict the motion trajectory of the target. The specific steps are as follows:

[0046] Step B1, feature extraction: receiving a data packet from the data acquisition module and initializing it, extracting image data I(t) and distance data D(t) from the data packet, using Gaussian filtering to smooth the distance data and reduce the impact of noise, and extracting image features through a convolutional neural network, further comprising the following steps:

[0047] Step B101, the convolutional neural network is composed of multiple convolutional layers, pooling layers, and fully connected layers. For a convolutional layer, the input is an image I(t), the convolution kernel is K, and the output is a feature map F(t)=I(t)*K, where * represents a convolution operation, and F(t) is the output feature map of the layer;

[0048] Step B102, the pooling layer performs dimensionality reduction processing on the feature F(t) output by the convolutional layer, and outputs the pooling result R(t)=MaxPooling(F(t)) to reduce the amount of calculation, where R(t) is the feature map after pooling and MaxPooling is the pooling operation;

[0049] Step B103, the fully connected layer is used to linearly combine the features extracted by the convolution layer and the pooling layer, and output the final class probability pooled feature vector as R(t), the first weight matrix is ​​represented as ω, the first bias is represented as b, the output of the fully connected layer is: Y(t) = ωR(t) + b, and the output is converted into the probability of the target category through the activation function Among them, Y(t) iis the value of the i-th class in the output vector Y(t) of the fully connected layer, Y(t) j is the original output value of the jth class among all categories, is the probability of the i-th category, M is the total number of categories;

[0050] Step B2: Target motion trajectory prediction: Concatenate the extracted image features with the smoothed distance data to form a joint feature vector F fused , through the analysis and comparison of continuous image frames, the target's motion trajectory is predicted. The specific steps are as follows:

[0051] Step B201, by analyzing the changes of two consecutive frames of images and distance data, the movement trend of the target in time is obtained, and the dynamic changes of the target are predicted by processing the time series data;

[0052] Step B202: Set the historical data of the target location at different times as Joint eigenvector F fused As input features, the target position Z(t) is used as the target output for linear regression training. The specific formula is: in, is the second weight, λ is the second bias, and the predicted position of the target at the future time t+τt is Repeat the above steps to continuously acquire new features and update the prediction to form a complete motion trajectory.

[0053] In this embodiment, the eye tracking module specifically needs to be explained. The eye tracking module includes a sight capture unit and an attention analysis unit, which uses an infrared camera and an optical sensor to detect eye movements, analyze sight changes in real time, and dynamically adjust the aiming point according to the sight data to ensure that the aiming is always consistent with the user's sight focus, thereby improving the accuracy of the operation;

[0054] Furthermore, the sight capture unit calculates the sight direction and aiming point through pupil positioning and performs dynamic adjustment to achieve accurate detection of eye movement. The specific steps are as follows:

[0055] Step C1, pupil location: Use an infrared camera to emit infrared light to illuminate the eyeball. The infrared light is received by the camera after being reflected on the surface of the eyeball. Image processing technology is used to identify the pupil and corneal reflection points to obtain the pupil center coordinates (x p ,y p ) and the coordinates of the corneal reflection point (x c ,y c );

[0056] Step C2, sight direction: Calculate the sight vector according to the position coordinates of the pupil and corneal reflection point. The specific calculation formula is: Where V is the sight vector, (xp ,y p ) and (x c ,y c ) are the coordinates of the pupil and corneal reflection points respectively. The sight vector is normalized and mapped to the screen coordinate system. The aiming point P is calculated by setting the screen center as the origin. aim =C screen +η·V norm , where P aim is the aiming point, indicating the screen position where the user is currently looking. screen is the screen center coordinate, η is the magnification factor of the sight vector, is the normalized sight line vector;

[0057] Step C3, real-time tracking and feedback: The eyeball image is captured in real time by an infrared camera, and steps C1 and C2 are continued to update the coordinates of the pupil and corneal reflection points according to the calculated aiming point P. aim Dynamically adjust aiming;

[0058] Furthermore, the attention analysis unit calculates the user's gaze time on each area based on the aiming point coordinates obtained by the sight capture unit, constructs a heat map of the focus area, marks the dynamic area that the user is paying attention to, and detects whether the user's attention is shifted by analyzing the eye movement trajectory. The specific steps are as follows:

[0059] Step D1, focus area analysis: divide the screen into multiple areas, and determine the area R where the current aiming point is located according to the aiming point obtained from the sight capture unit. aim , count users in area R aim The gaze time of each area is converted into a heat map to show the hot spots that the user pays attention to, where the color depth represents the gaze time, the darker the color, the longer the gaze time, and the user is in area R. aim The total fixation time formula is: The fixation time T of each area is focus Converted into heat map value, the specific formula is: Among them, t δ is the duration of the δth aiming point, T focus is the total fixation time, L is the number of aiming points, T max is the maximum fixation time of all regions, H aim is the heatmap value;

[0060] Step D2, attention shift detection: For each frame of eye movement data, record the coordinates of the current gaze point and the previous gaze point, and calculate the moving distance between the gaze points as Among them, (x α ,y α ) and (xβ ,y β ) are the coordinates of the αth and βth fixation points, D move is the distance the user moves between the two gaze points; set a deviation threshold D threshold , when D move Exceeding the deviation threshold D threshold , indicating that attention has shifted.

[0061] In this embodiment, the human-computer interaction module specifically needs to be explained. The human-computer interaction module includes a user input interface and a feedback display unit. The user adjusts the aiming mode by inputting instructions, and the target recognition result and distance information are fed back to the user through the display screen. The specific steps are as follows:

[0062] Step S1, monitoring the user's instructions through the input interface, parsing the user's instructions and applying them to the system, adjusting the aiming mode, displaying the target recognition results to the user through the feedback display unit, including the target category, target position, and target distance information, and displaying the aiming point, target outline, and motion trajectory prediction information on the display screen to provide real-time feedback to the user;

[0063] Step S2: When the user continuously inputs new commands, a loop is entered to continuously draw new target data. By continuously updating target recognition, distance measurement, eye movement capture and feedback display, a closed-loop feedback system is formed to provide real-time information to the user.

[0064] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0065] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An electronic sighting scope intelligent aiming system, characterized by: It includes data acquisition module, target recognition module, eye tracking module, and human-computer interaction module; The data acquisition module includes an image acquisition unit and a distance measurement unit, which are used to acquire images and distance data within the target area and transmit them to the target recognition module for processing; The target recognition module includes a state evaluation unit, which extracts features and performs recognition by analyzing image data and distance data to predict the movement trajectory of the target; The eye tracking module includes a sight line capture unit and an attention analysis unit, which uses an infrared camera and an optical sensor to detect eye movements, analyze sight line changes in real time, and dynamically adjust the aiming point based on the sight line data; The human-computer interaction module includes a user input interface and a feedback display unit. The user adjusts the aiming mode by inputting instructions, and the target recognition result and distance information are fed back to the user through the display screen.

2. The electronic sighting scope intelligent aiming system according to claim 1, characterized in that: The data acquisition module includes an image acquisition unit and a distance measurement unit, which are used to collect images and distance data within the target area and transmit them to the target recognition module for processing. The specific steps are as follows: Step A1, data acquisition: the image acquisition unit acquires the image of the target area in real time through a high-resolution camera, the resolution of the image acquisition is W×H, which means the width is W pixels and the height is H pixels, and the mathematical expression of each frame of the image acquired is: I(t)={I(x,y)|x=1,2,..,W; y=1,2,...,H}, wherein the color information of each pixel is I(x,y), and x and y respectively represent the horizontal and vertical coordinates of the image; the distance measurement unit uses a laser rangefinder to measure the distance from the sight to the target, and the obtained distance is D(t), which represents the distance acquired at time t; Step A2, data transmission: Encapsulate the image data I(t) and the distance data D(t) into a data packet, which includes the time point of data acquisition, the image information of the target area and the distance measured at time t, and transmit the data to the target recognition module through a high-speed serial connection.

3. The electronic sighting scope intelligent aiming system according to claim 1, characterized in that: The target recognition module includes a state evaluation unit, which extracts features and performs recognition by analyzing image data and distance data to predict the movement trajectory of the target. The specific steps are as follows: Step B1, feature extraction: receiving data packets from the data acquisition module and initializing, extracting image data I(t) and distance data D(t) from the data packets, using Gaussian filtering to smooth the distance data and reduce the impact of noise, and extracting image features through convolutional neural networks; Step B2: Target motion trajectory prediction: Concatenate the extracted image features with the smoothed distance data to form a joint feature vector F fused , through the analysis and comparison of continuous image frames, the target's motion trajectory is predicted. The specific steps are as follows: Step B201, by analyzing the changes of two consecutive frames of images and distance data, the movement trend of the target in time is obtained, and the dynamic changes of the target are predicted by processing the time series data; Step B202: Set the historical data of the target location at different times as Joint eigenvector F fused As input features, the target position Z(t) is used as the target output for linear regression training. The specific formula is: in, is the second weight, λ is the second bias, and the predicted position of the target at the future time t+τt is Repeat the above steps to continuously acquire new features and update the prediction to form a complete motion trajectory.

4. The electronic sighting scope intelligent aiming system according to claim 3 is characterized in that: In the feature extraction of step B1, a data packet from a data acquisition module is received and initialized, image data I(t) and distance data D(t) are extracted from the data packet, Gaussian filtering is used to smooth the distance data to reduce the influence of noise, and image features are extracted through a convolutional neural network, further comprising the following steps: Step B101, the convolutional neural network is composed of multiple convolutional layers, pooling layers, and fully connected layers. For a convolutional layer, the input is an image I(t), the convolution kernel is K, and the output is a feature map F(t)=I(t)*K, where * represents a convolution operation, and F(t) is the output feature map of the layer; Step B102, the pooling layer performs dimensionality reduction processing on the feature F(t) output by the convolutional layer, and outputs the pooling result R(t)=MaxPooling(F(t)) to reduce the amount of calculation, where R(t) is the feature map after pooling and MaxPooling is the pooling operation; Step B103, the fully connected layer is used to linearly combine the features extracted by the convolution layer and the pooling layer, and output the final class probability pooled feature vector as R(t), the first weight matrix is ​​represented as ω, the first bias is represented as b, the output of the fully connected layer is: Y(t) = ωR(t) + b, and the output is converted into the probability of the target category through the activation function Among them, Y(t) i is the value of the i-th class in the output vector Y(t) of the fully connected layer, Y(t) j is the original output value of the jth class among all categories, is the probability of the i-th class, and M is the total number of classes.

5. The electronic sighting scope intelligent aiming system according to claim 1, characterized in that: The sight capture unit calculates the sight direction and aiming point through pupil positioning and makes dynamic adjustments to achieve accurate detection of eye movement. The specific steps are as follows: Step C1, pupil location: Use an infrared camera to emit infrared light to illuminate the eyeball. The infrared light is received by the camera after being reflected on the surface of the eyeball. Image processing technology is used to identify the pupil and corneal reflection points to obtain the pupil center coordinates (x p ,y p ) and the coordinates of the corneal reflection point (x c ,y c ); Step C2, sight direction: Calculate the sight vector according to the position coordinates of the pupil and corneal reflection point. The specific calculation formula is: Where V is the sight vector, (x p ,y p ) and (x c ,y c ) are the coordinates of the pupil and corneal reflection points respectively. The sight vector is normalized and mapped to the screen coordinate system. The aiming point P is calculated by setting the screen center as the origin. aim =C screen +η·V norm , where P aim is the aiming point, C screen is the screen center coordinate, η is the magnification factor of the sight vector, is the normalized sight line vector; Step C3, real-time tracking and feedback: The eyeball image is captured in real time by an infrared camera, and steps C1 and C2 are continued to update the coordinates of the pupil and corneal reflection points according to the calculated aiming point P. aim Dynamically adjust aiming.

6. The electronic sight intelligent aiming system according to claim 1, characterized in that: The attention analysis unit calculates the user's gaze time on each area based on the aiming point coordinates obtained by the sight capture unit, constructs a heat map of the focus area, marks the dynamic area that the user is paying attention to, and detects whether the user's attention is shifted by analyzing the eye movement trajectory. The specific steps are as follows: Step D1, focus area analysis: divide the screen into multiple areas, and determine the area R where the current aiming point is located according to the aiming point obtained from the sight capture unit. aim , count users in area R aim The gaze time of each area is converted into a heat map to show the hot spots that the user pays attention to, where the color depth represents the gaze time. aim The total fixation time formula is: The fixation time T of each area is focus Converted into heat map value, the specific formula is: Among them, t δ is the duration of the δth aiming point, T focus is the total fixation time, L is the number of aiming points, T max is the maximum fixation time of all regions, H aim is the heatmap value; Step D2, attention shift detection: For each frame of eye movement data, record the coordinates of the current gaze point and the previous gaze point, and calculate the moving distance between the gaze points as Among them, (x α ,y α ) and (x β ,y β ) are the coordinates of the αth and βth fixation points, D move is the distance the user moves between the two gaze points; set a deviation threshold D threshold , when D move Exceeding the deviation threshold D threshold , indicating that attention has shifted.

7. The electronic sighting scope intelligent aiming system according to claim 1, characterized in that: The human-computer interaction module includes a user input interface and a feedback display unit. The user adjusts the aiming mode by inputting instructions, and the target recognition result and distance information are fed back to the user through the display screen. The specific steps are as follows: Step S1, monitoring the user's instructions through the input interface, parsing the user's instructions and applying them to the system, adjusting the aiming mode, displaying the target recognition results to the user through the feedback display unit, including the target category, target position, and target distance information, and displaying the aiming point, target outline, and motion trajectory prediction information on the display screen to provide real-time feedback to the user; Step S2: When the user continuously inputs new commands, a loop is entered to continuously draw new target data. By continuously updating target recognition, distance measurement, eye movement capture and feedback display, a closed-loop feedback system is formed to provide real-time information to the user.

Images