An adaptive aiming parameter optimization method and system

Abstract

The application discloses a kind of self-adapting parameter optimization method and system of aiming, it is related to aiming control technical field, the method includes: the information base of target sighting telescope is established, reference scene is divided based on the information base, constructs fine adjustment control interval, input environment data is as first matching data, calls integrated in the laser sensor of target sighting telescope, establishes second matching data, carries out target sighting telescope optimization adjustment by target adjustment parameter and fine adjustment control interval, and establishes the electronic imaging data set of objective lens and carries out optimization iterative evaluation, according to aiming parameter optimization result, the control management of target sighting telescope is carried out.The application solves the technical problems that target sighting telescope in the prior art is poor in adaptability to various complex and changeable environments, aiming precision is low, and parameters cannot be dynamically adjusted in time according to actual conditions on site, achieves fast adaptation to environment, improves aiming precision and adaptability, and achieves the technical effects of intelligent management and continuous improvement of sighting telescope.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aiming control, in particular to a self-adaptive aiming parameter optimization method and system. BACKGROUND

[0002] With the continuous development of science and technology, in the field of modern shooting or observation, the accuracy and adaptability of the sighting telescope are increasingly required. The traditional sighting telescope often uses fixed parameter settings, which is difficult to adapt to complex and variable environments and the needs of different users.

[0003] The prior art has the technical problems that the target sighting telescope is poor in adaptability to various complex and variable environments, low in aiming accuracy, and unable to dynamically adjust parameters in time according to the actual situation on site. SUMMARY

[0004] The present application provides a self-adaptive aiming parameter optimization method and system, which is used to solve the technical problems that the target sighting telescope is poor in adaptability to various complex and variable environments, low in aiming accuracy, and unable to dynamically adjust parameters in time according to the actual situation on site in the prior art.

[0005] In view of the above problems, the present application provides a self-adaptive aiming parameter optimization method and system.

[0006] The first aspect of the present application provides a self-adaptive aiming parameter optimization method, which comprises:

[0007] An information library of the target sighting telescope is established, the information library comprises a topological structure information library and a basic lens information database, the information library is constructed by calling a database of the same model data as the target sighting telescope; a benchmark scene is divided based on the information library, and N scene spaces are established, wherein the N scene spaces are mapped with corresponding adjustment parameters; an individual difference evaluation of the corresponding model sighting telescope is performed based on the information library, and a fine-tuning control interval is constructed based on the individual difference evaluation result; input environment data of a user is obtained, the input environment data is taken as first matching data, a laser sensor integrated in the target sighting telescope is called to perform trigger collection, and second matching data is established; N scene spaces are adaptively matched based on the first matching data and the second matching data, and a target adjustment parameter is called according to the matching result; the target sighting telescope is optimized and adjusted through the target adjustment parameter and the fine-tuning control interval, an electronic imaging data set of the ocular lens is established, the optimization iteration evaluation is performed through the electronic imaging data set, and an aiming parameter optimization result is generated according to the evaluation result; and the target sighting telescope is controlled and managed based on the aiming parameter optimization result.

[0008] The second aspect of the present application provides a self-adaptive aiming parameter optimization system, which comprises:

[0009] The sighting telescope information library establishing module is used for establishing an information library of a target sighting telescope, the information library includes a topological structure information library and a basic lens information database, and the information library is constructed by calling a database of the same model as the target sighting telescope; the reference scene division module is used for performing reference scene division based on the information library, and N scene spaces are established, wherein the N scene spaces are mapped with corresponding adjustment parameters; the fine adjustment control interval constructing module is used for performing individual difference evaluation of a corresponding model sighting telescope based on the information library, and a fine adjustment control interval is constructed based on the individual difference evaluation result; the input environment data acquisition module is used for acquiring input environment data of a user, taking the input environment data as first matching data, calling a laser sensor integrated in the target sighting telescope, performing trigger collection, and establishing second matching data; the target adjustment parameter calling module is used for performing adaptive matching of the N scene spaces based on the first matching data and the second matching data, and calling a target adjustment parameter according to a matching result; the sighting parameter optimization result generating module is used for performing optimization adjustment of the target sighting telescope through the target adjustment parameter and the fine adjustment control interval, establishing an electronic imaging data set of an ocular lens, performing optimization iterative evaluation through the electronic imaging data set, and generating a sighting parameter optimization result according to an evaluation result; and the sighting telescope control module is used for performing control management of the target sighting telescope based on the sighting parameter optimization result.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] An information library of a target sighting telescope is established, reference scene division is performed based on the information library, N scene spaces are established, individual difference evaluation of a corresponding model sighting telescope is performed, a fine adjustment control interval is constructed based on the individual difference evaluation result, input environment data of a user is acquired, the input environment data is taken as first matching data, a laser sensor integrated in the target sighting telescope is called, trigger collection is performed, second matching data is established, adaptive matching of the N scene spaces is performed based on the first matching data and the second matching data, a target adjustment parameter is called according to a matching result, optimization adjustment of the target sighting telescope is performed through the target adjustment parameter and the fine adjustment control interval, an electronic imaging data set of an ocular lens is established, optimization iterative evaluation is performed through the electronic imaging data set, a sighting parameter optimization result is generated according to an evaluation result, and control management of the target sighting telescope is performed. The technical effects of quickly adapting to an environment, improving sighting precision and adaptability, realizing intelligent management and continuous improvement of a sighting telescope are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic flowchart of an adaptive aiming parameter optimization method provided in an embodiment of this application;

[0014] Figure 2 This is a flowchart illustrating the process of obtaining user input environment data in an adaptive aiming parameter optimization method provided in this application embodiment;

[0015] Figure 3 This is a schematic diagram of an adaptive aiming parameter optimization system provided in an embodiment of this application.

[0016] Explanation of reference numerals in the attached diagram: 10 for establishing a scope information database, 20 for dividing a baseline scene, 30 for constructing a fine-tuning control range, 40 for acquiring input environment data, 50 for calling target adjustment parameters, 60 for generating aiming parameter optimization results, and 70 for scope control. Detailed Implementation

[0017] This application provides an adaptive aiming parameter optimization method and system to address the technical problems in the prior art, such as poor adaptability of target aiming scopes to various complex and changing environments, low aiming accuracy, and inability to dynamically adjust parameters in a timely manner according to the actual situation on site.

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] Example 1

[0020] like Figure 1 As shown, this application provides an adaptive aiming parameter optimization method, the method comprising:

[0021] Step S100: Establish a database of information for the target sight, which includes a topology database and a basic lens information database. The database is constructed by calling data of the same model as the target sight.

[0022] Specifically, a target sighting information library is constructed, which is subdivided into a topological structure information library and a basic lens information library to ensure the systematicness and orderliness of the information. For the topological structure information library, detailed information about the positional relationship, connection mode, spatial layout, etc. of each component inside the sighting scope is collected and sorted, which involves disassembling and in-depth analyzing the sighting scope, using professional measuring tools and technical means to accurately record every detail, such as the position of screws, the wiring of circuit boards, the structure of mechanical transmission components, etc., which helps to deeply understand the working principle and mechanical characteristics of the sighting scope; the basic lens information database collects various key parameters of the lens, including the material properties of the lens, optical performance indicators (such as refractive index, light transmittance, Abbe number, etc.), surface treatment conditions (such as the type and thickness of coating), etc., and through various testing means and data collection methods, such as optical transmittance test, refractive index measurement, spectral analysis, etc. testing means, comprehensive and accurate information is obtained and entered into the database. In the process of establishing the information library, the accuracy and reliability of the data need to be ensured, and the quality of the data is guaranteed through multiple measurements, verifications and comparisons with authoritative materials. By calling the existing data of the same model as the target sighting scope, the existing data resources are fully utilized to quickly establish a targeted and practical information library, which provides basic data support for subsequent analysis, optimization, etc. For example, in the performance evaluation or improvement design of the sighting scope, the relevant topological structure and lens information can be directly obtained from the information library for analysis and reference.

[0023] Step S200: Based on the information library, a reference scene is divided, and N scene spaces are established, wherein the N scene spaces are mapped with corresponding adjustment parameters.

[0024] Specifically, based on the target sighting information library that has been established, the reference scene is divided according to different use requirements, environmental conditions, target characteristics, etc. For example, according to the distance, it can be divided into close-range scene, medium-range scene and long-range scene; or according to the light conditions, it can be divided into strong light scene, normal light scene and weak light scene, etc. For each divided scene, a special scene space is established, and in the scene space, there are corresponding adjustment parameters, including the focal length adjustment value of the sighting scope, the brightness adjustment value, the magnification setting, etc. For example, in the long-range scene space, the corresponding adjustment parameters are larger magnification and more precise focal length adjustment; and in the weak light scene, the corresponding are higher brightness setting and specific optical coating adjustment method. Through such explicit scene division and corresponding adjustment parameter setting, the user can quickly and accurately find the parameter configuration suitable for the scene when facing different scenes, thereby improving the use effect and adaptability of the sighting scope.

[0025] Step S300: based on the information base, individual difference evaluation of the corresponding type of scope is performed, and a fine adjustment control interval is constructed based on the individual difference evaluation result.

[0026] Specifically, based on the established target scope information base, detailed analysis and comparison of each scope of the same type are performed. Due to factors such as tolerances in the production process, slight differences in the performance of parts, and the like, even scopes of the same type may have certain individual differences in actual performance. For example, it may be found that some scopes are slightly clearer in optical imaging, and some scopes differ in the smoothness of the adjustment mechanism. Through comprehensive evaluation and quantification of these differences, the unique characteristics and performance of each scope are determined. According to the individual difference evaluation results, a special fine adjustment control interval is constructed. This interval includes the specific adjustment range and limitations for each scope. For example, for a scope with slightly poor imaging, a specific focal length fine adjustment interval is determined to improve its imaging quality; for a scope with less smooth operation, a more delicate adjustment force control interval is set. Precise fine adjustment is made according to the specific situation of each scope to make them all achieve the best performance state, rather than adjusting them with a unified standard. At the same time, specific guidance and basis are provided for subsequent maintenance, calibration, and the like, to ensure that each scope can perform its due performance and improve the overall use effect and reliability.

[0027] Step S400: obtain the input environment data of the user, take the input environment data as the first matching data, call the laser sensor integrated in the target scope, perform triggered collection, and establish the second matching data.

[0028] Specifically, through human-computer interface input, voice input, external device connection, and the like, the input environment data of the user is obtained, including the current geographical position, light conditions, target distance, target type, and various information related to the use scene. The input environment data is regarded as the first matching data, which provides a scene description. Then, the laser sensor integrated in the target scope is started, and various measurements are performed through emission and reception of laser, such as accurate measurement of target distance, environmental brightness, and the like. Through triggered collection of the laser sensor, more accurate and real-time environment data is obtained, which constitutes the second matching data. The combination of the first matching data and the second matching data more comprehensively and accurately reflects the current actual use environment, and provides key data support for subsequent accurate scope adjustment and optimization, to ensure that the scope can be adjusted most appropriately according to the actual situation, thereby improving the accuracy and effect of aiming.

[0029] Step S500: perform adaptive matching of N scene spaces based on the first matching data and the second matching data, and call the target adjustment parameter according to the matching result.

[0030] Specifically, various information contained in the first matching data, such as specific geographic location information, approximate target distance range, description of light conditions, etc., are integrated and associated with the actual distance of the target measured by the laser sensor in the second matching data, the precise environmental brightness value, etc., and are compared in detail with the respective characteristic data of the N scene spaces. For example, a certain scene space is defined as a long distance (such as more than 500 meters) and weak light (such as brightness lower than a certain value), and the integrated data will be checked one by one with the defined conditions of this scene space. If the user input environment data shows that the target distance may be around 700 meters, and the distance measured by the laser sensor in the second matching data is 650 meters, and the environmental brightness also meets the standard of weak light, then it can be determined that it is highly matched with this long distance weak light scene space. Once the matching is successful, a series of target adjustment parameters corresponding to this scene space are immediately called. For example, for the focal length, according to the specific value of 650 meters, the corresponding optimal focal length setting value is found from the parameter library, and then the focal length of the scope is automatically adjusted to this value through the internal mechanical or electronic structure; for brightness, according to the degree of weak light and the characteristics of the scope, a brightness level is called that can ensure clear observation of the target without being too dazzling.

[0031] Step S600: Optimal adjustment of the target scope is performed through the target adjustment parameters and the fine adjustment control interval, and an electronic imaging data set of the ocular lens is established. Iterative evaluation is performed through the electronic imaging data set, and a scope parameter optimization result is generated according to the evaluation result.

[0032] Specifically, the target scope is initially adjusted using the determined target adjustment parameters, and the ideal settings determined based on the matched scene space, and in combination with the fine-tuning control interval, the scope is adjusted more accurately and meticulously within this range. For example, based on the focal length determined by the target adjustment parameters, a small up and down floating adjustment can be made according to the fine-tuning control interval to seek better results. During the adjustment process, as the state of the scope changes, a series of electronic images will be formed through the eyepiece. These imaging data are collected to form an electronic imaging dataset. The electronic imaging dataset is used for optimization and iterative evaluation. In the optimization and iterative evaluation, the imaging effect after each adjustment is analyzed, such as clarity, contrast, and target recognition. By comparing and evaluating with the previous imaging, it is determined whether the current adjustment has reached a better state. If not, the adjustment and iterative evaluation continue, and different fine-tuning combinations are tried until the optimal imaging effect is found. Finally, the evaluation results determine the optimization results of the aiming parameters. This optimization result contains the most suitable scope parameter settings for the current environment and user needs after optimization and adjustment, including focal length, brightness, magnification, and other specific values. For example, during the adjustment process, it is found that by slightly increasing the focal length and slightly reducing the brightness, the target imaging in the electronic imaging dataset becomes clearer and sharper. After multiple iterative evaluations, it is determined that this parameter combination is the best, and the corresponding aiming parameter optimization result is generated. This enables the scope to better adapt to various complex situations in actual use, improving its performance and practicality.

[0033] Step S700: Control and management of the target scope based on the aiming parameter optimization result.

[0034] Specifically, when the aiming parameter optimization result is obtained, it will be used as the key basis to comprehensively implement the control and management of the target scope. First, the specific parameters contained in the optimization result will be accurately read, such as the specific value of focal length, the setting value of brightness, magnification, etc. These parameter information will be accurately transmitted to the relevant control components of the target scope. For the adjustment of focal length, the relevant mechanical structure or electronic adjustment device is driven to make accurate setting according to the focal length value in the optimization result, to ensure that the target can be clearly and accurately presented when the user observes the target through the scope; for brightness, the lighting system or the light transmittance of the lens will be adjusted accordingly to achieve the brightness level specified in the optimization result, so that the most suitable visual effect can be provided under different environmental light conditions, neither too bright to cause dazzling or unclear target, nor too dark to make it difficult to distinguish the target; at the same time, similar accurate control will be carried out on other parameters such as magnification, to continuously monitor and ensure that the scope always maintains the state set by the optimization result, and real-time fine-tuning or correction is carried out to cope with possible environmental changes or other interference factors. Through such fine and intelligent control and management, the target scope can better adapt to various actual needs and maximize its performance.

[0035] In one possible implementation manner, as Figure 2 , step S400 further includes:

[0036] Step S410: analyzing the input environment data to establish fuzzy recognition parameters.

[0037] Step S420: establishing the characteristics of the object to be observed, and constructing the fuzzy recognition parameters and the characteristics of the object to be observed into a fuzzy recognition model to construct fuzzy matching characteristics.

[0038] Step S430: controlling the target scope to collect the object to be observed in a predetermined search space, and performing fuzzy matching through fuzzy matching characteristics to establish fuzzy matching results.

[0039] Step S440: center alignment according to the fuzzy matching results, and calling the laser sensor integrated in the target scope after center alignment to perform trigger collection.

[0040] Specifically, after receiving the input environment data, a deep analysis and disassembly of these data is performed, which aims to extract key features and information from complex data to establish parameters for subsequent fuzzy recognition. First, the environment data is classified and screened, and the data is distinguished according to different attributes such as light intensity, temperature, humidity, air pressure, wind speed, etc. For the data of each attribute, specific algorithms and analysis methods are used to extract key information, such as using standard deviation algorithm to measure the fluctuation of light intensity for light intensity data, and using linear regression analysis method to determine the temperature trend over time for temperature data. These extracted key information is integrated and correlated, and by analyzing the mutual relationship between these information, further refined parameters that can effectively describe the environmental characteristics are obtained, which are comprehensive indicators such as environmental complexity index, environmental stability index, etc. The established fuzzy recognition parameters are actually a highly generalized and abstract representation of the input environment data, providing important input and basis for the subsequent fuzzy recognition model, enabling the model to better adapt to different environmental conditions, improving the accuracy and reliability of target observation and recognition. For example, in a specific environment, the input environment data includes light intensity of 800 lux, temperature of 25 degrees Celsius, and humidity of 60%, after analysis, the established fuzzy recognition parameters include moderate light intensity, suitable temperature, and normal humidity range, etc. These parameters will provide specific guidance and basis for the subsequent fuzzy recognition process, helping the system to more accurately identify and process the observed object.

[0041] To determine the characteristics of the observed object, the shape, color, size, texture, etc. of the observed object are described, and these fuzzy recognition parameters (light intensity, temperature range, etc.) and observed object characteristics (outline, color, etc.) are used as input data to the fuzzy recognition model. The fuzzy recognition model is constructed by first defining the fuzzy set according to the characteristics of the object. For example, color can be divided into red, yellow, green, etc. fuzzy set; shape can be divided into circular, elliptical, long strip, etc. fuzzy set, and image processing technology is used to extract the characteristics of the object from the image, such as color characteristics and shape characteristics. Color histogram, edge detection, shape descriptor, etc. can be used to extract features, and fuzzy logic or fuzzy neural network, etc. can be used to establish the fuzzy recognition model, taking the extracted features as input and the fuzzy set as output, and training the model to learn the relationship between the features and the fuzzy set. The object image to be recognized is input into the trained fuzzy recognition model for fuzzy matching, and the model calculates the matching degree with each fuzzy set according to the input features, thereby constructing fuzzy matching features, more comprehensively and accurately capturing the characteristics of the object, and improving the accuracy of object recognition.

[0042] The target sighting scope collects information of the object to be observed in a predetermined search space. The search space is a range set in advance according to specific application scenarios and task requirements. After collecting the relevant data of the object to be observed, the fuzzy matching feature constructed in advance is used to perform a fuzzy matching operation, and the collected information is compared and analyzed with the fuzzy matching feature to determine whether there is a matching condition and to establish a corresponding fuzzy matching result. The fuzzy matching result indicates whether a similar target to the object to be observed is found in the search space and how the matching degree is, thereby enhancing the adaptability and reliability of the target sighting scope.

[0043] After obtaining the fuzzy matching result, the target sighting scope is precisely adjusted to operate towards the direction of achieving center alignment, and the sighting scope is guided to gradually approach the center position of the most likely target. For example, according to the fuzzy matching result, it is determined that the target is possibly in a certain direction and has a higher matching probability, and then fine rotation and movement operations are performed to gradually approach the center region of the target with the center of the sighting scope, so as to achieve center alignment. At this time, the laser sensor integrated in the target sighting scope is immediately started to trigger the collection of more accurate and detailed data of the target by using the laser sensor, such as the accurate distance of the target, the surface features, and the like.

[0044] In a possible implementation, step S430 further includes:

[0045] Step S431: activating the target sighting scope and placing the target sighting scope in a state to be observed.

[0046] Step S432: reading the control parameters of the user and recording the control results of the user, wherein the control results are control results of the user manually identifying the object to be observed appearing in the ocular lens.

[0047] Step S433: establishing the predetermined search space according to the control results.

[0048] Specifically, the activation of the target scope refers to the transition from the dormant or inactive state to the working state, so that it can start to perform observation tasks, and the preparation for the subsequent operation is to place the scope in a standby mode that can receive and process information at any time. Then start reading the user's control parameters, which can include the user's adjustment operations on the scope, such as the setting of the focal length, the change of the angle, etc., while recording the user's control results, especially the user's manual identification of the appearance of the observed object in the eyepiece. This process is a key point in capturing the user's interaction with the scope, so that the user's behavior and intentions can be better understood and analyzed later. Based on the user's control results recorded in the previous step, a predetermined search space is established, and based on the various operations and adjustments performed by the user when the observed object is actually observed, a general search range is determined, which includes the area where the user believes the observed object may appear and the related feature information. For example, if the user finds the observed object at a certain angle and focal length, the space range corresponding to this angle and focal length may be included in the predetermined search space, which provides a strong basis for subsequent more accurate observation and analysis in this way.

[0049] In a possible implementation, step S600 further includes:

[0050] Step S610: Establish the adjustment limit interval of the key parameter based on the target adjustment parameter and the fine adjustment control interval, and divide the adjustment limit interval by the preset segmentation point.

[0051] Step S620: Obtain the electronic imaging data corresponding to the adjustment limit interval segmentation result, perform the identification effect evaluation, and reconstruct the adjustment limit interval according to the evaluation result.

[0052] Step S630: Perform iterative processing of segmentation and reconstruction to generate the scope parameter optimization result.

[0053] Specifically, a rough range is obtained based on the analysis of the target adjustment parameter, such as according to the characteristics of the target, environmental factors, device performance, etc. A wide parameter value range is preliminarily set as the basis of the limit interval. In combination with the specific fine-tuning control interval, it is further clarified and refined. The fine-tuning control interval provides more accurate adjustable range information, which is combined and limited with the preliminary wide range, so as to obtain a relatively more accurate and operable limit interval. Past experience data or parameter setting situations in similar scenarios are also considered. If there are relevant historical data or cases for reference, the reasonable range of key parameters is extracted from them and integrated into the limit interval construction to construct an adjustment limit interval for key parameters, which defines the maximum and minimum range of the key parameters that can be adjusted, ensuring that the adjustment operation will not exceed the reasonable limit and avoiding inappropriate or ineffective adjustment. According to specific needs and problems, determine the preset partition point, and according to the preset partition point, divide the adjustment limit interval into multiple subintervals. The boundary of each subinterval is determined by the adjacent two partition points, and the target adjustment parameter is allocated to each partition interval. Different allocation strategies can be used as needed, such as uniform allocation, proportional allocation, or allocation according to specific rules.

[0054] When the partitioning of the adjustment limit interval is completed, the corresponding electronic imaging data is obtained for each partitioned subinterval, which means that for each parameter setting in a specific range, the corresponding imaging result can be obtained. The recognition effect is evaluated, various image analysis algorithms and indicators are used, such as image clarity, contrast, target distinguishability, feature integrity, etc. The effect of each electronic imaging data is judged by these standards. According to the evaluation results, the adjustment limit interval is reconstructed. If the imaging effect of some subintervals is not good, the range of these subintervals will be adjusted. For example, the poor-performing subintervals are reduced or merged with other subintervals, or the well-performing subintervals are expanded.

[0055] According to the established rules, one segmentation is completed to obtain a plurality of subdivided intervals, and corresponding electronic imaging data is obtained based on the intervals to evaluate the identification effect, and then the reconstruction of the limit interval is adjusted according to the evaluation result, and the newly reconstructed limit interval is taken as the basis for the next round of segmentation operation. This round of segmentation will be based on the new interval division, which may be different from the last round, and then the steps of obtaining data, evaluating effect and reconstructing interval are repeated. Such continuous circulation improves and optimizes each iteration based on the previous one. With the iteration, the segmentation and reconstruction will be more and more refined, and the exploration of the aiming parameter will be more and more accurate and in-depth. Through multiple iterations, the aiming parameter combination that can best improve the imaging effect and identification effect is gradually found, and finally the aiming parameter optimization result is generated. This optimization result is the best state obtained after repeated adjustment and improvement. For example, in the first iteration, it may be found that the imaging effect in a certain large interval is different, and after reconstruction, the specific sub-interval with better effect can be determined more accurately in the second iteration. After subsequent iterations, the aiming parameter setting is continuously refined and optimized to obtain the most suitable aiming parameter setting, such as the best focal length and angle, which is the final aiming parameter optimization result.

[0056] In a possible implementation, step S630 further includes:

[0057] Step S631: The iteration result is continuously monitored, and the iteration result is compared with the evaluation result of the last round.

[0058] Step S632: If there is a comparison anomaly, a rollback instruction is generated, and after the preset segmentation point is updated through the rollback instruction, the reconstruction processing is performed again to continue the iteration.

[0059] Specifically, the result generated by each iteration is continuously monitored, which includes various data, indicators, etc. obtained after adjustment of the key parameters. At the same time, the current iteration result is compared with the result of the last round in detail. This comparison involves multiple aspects, such as the specific value change of the key parameters, the improvement or decline degree of the related performance indicators, the difference of the imaging effect, etc. Through such continuous monitoring and comparison, the abnormality or unreasonable change that may occur in the iteration process can be found in time.

[0060] If an abnormal situation is found during the comparison process, that is, the comparison of the current iteration result with the previous round result shows an unexpected or unreasonable situation, such as a sudden abnormal change in the trend of key parameters, or a significant decline in performance indicators, etc., a rollback instruction will be generated. The function of this rollback instruction is to trigger the update of the preset segmentation point, which will adjust the position, number or distribution of the segmentation point, etc. to change the subsequent segmentation and reconstruction method. Then, based on the updated preset segmentation point, the reconstruction process is re-performed, that is, a new round of iteration process is started again. The purpose of this is to adjust the strategy in time when an abnormality occurs, avoid continuing in the wrong iteration direction, and try to find a more suitable solution through rollback and re-adjustment, so as to ensure the accuracy and effectiveness of the iteration process, and continuously advance towards the direction of optimizing the aiming parameter. For example, if it is found that the imaging clarity has decreased significantly after a certain iteration and the difference with the previous round is obvious, a rollback instruction is generated, the segmentation point is adjusted, and reconstruction and iteration are performed again to find a better result.

[0061] In a possible implementation, step S700 further includes:

[0062] Step S710: Obtain user feedback corresponding to the aiming parameter optimization result, and establish a feedback data set.

[0063] Step S720: Perform device deviation feature establishment under N scene spaces according to the feedback data set.

[0064] Step S730: Perform subsequent aiming parameter optimization management based on the device deviation feature establishment result.

[0065] Specifically, user feedback corresponding to the aiming parameter optimization result is obtained in multiple ways. This may include the following ways: by setting a feedback submission interface in the relevant device or application program, allowing users to directly input their evaluations, opinions and suggestions on the optimization result. These feedbacks may include evaluations of imaging quality, feelings of convenience, whether the expected effect is achieved, etc. These user feedbacks are collected and sorted to form a special feedback data set.

[0066] Detailed analysis is performed on the information in the feedback dataset, and for each scene space, the feedback content related to the scene is extracted. For example, in an outdoor strong light scene, the user may feedback that the imaging is overexposed, the color is inaccurate, etc.; in a low light indoor scene, the user may feedback that the picture is blurred, there are many noise points, etc. According to these specific feedback contents, the characteristics that the device may deviate from the normal state in this scene space are summarized and concluded, such as the deviation of the optical performance of the device, such as inaccurate focal length, abnormal transmittance; or the deviation of the electronic performance, such as deviation of signal processing, circuit stability problem, etc. Through the analysis and summary of each scene, a unique device deviation characteristic set is established in each of the N scene spaces. This set can clearly show the problems and deviations from the normal state that the device is prone to in different scenes. For example, it may be found that the device's autofocus cannot keep up with the object's motion speed in the motion scene, thereby establishing a deviation characteristic related to the focusing speed; it may be found that the device's white balance is inaccurate in a complex light scene, thereby establishing a deviation characteristic in the color restoration aspect. Such establishment of device deviation characteristics provides an important basis and direction for subsequent targeted improvement and optimization of device performance.

[0067] The established device deviation characteristics are analyzed, and for each characteristic, the causes and possible effects on the aiming parameters are analyzed. For example, if it is found that there is an imaging blur deviation characteristic in a certain scene, it may be caused by improper focal length setting or insufficient shake compensation, etc. According to these analysis results, the optimization strategy of the aiming parameters is adjusted accordingly, such as for the problem of imaging blur, the focal length parameter range may need to be adjusted more finely in this scene, or the shake compensation strength may need to be increased. Specific optimization schemes are developed for device deviation characteristics in different scenes, and it is clear that in a specific scene, which aiming parameters should be focused on and adjusted, and the direction and amplitude of the adjustment. At the same time, a monitoring mechanism is established to monitor the running state and performance of the device in different scenes in real time to verify whether the optimized aiming parameters effectively solve the previous device deviation characteristics. If there are still problems, further analysis and adjustment of the optimization strategy are needed. Through such a cyclic process, the performance and performance of the device in various scenes are continuously improved to achieve better use effect.

[0068] In one possible implementation, step S700 further includes:

[0069] Step S740: Record the aiming parameter optimization results and input environment data to build a control database.

[0070] Step S750: When performing subsequent aiming parameter optimization, perform control similarity analysis of the control database.

[0071] Step S760: Perform control database call according to the control similarity analysis result, take the call result as the ground state result, and perform aiming fitting.

[0072] Specifically, the specific results of aiming parameter optimization are recorded in detail, including the optimized parameter values such as focal length, aperture size, and sensitivity. At the same time, the input environment data related to this optimization are also recorded one by one, such as the light intensity at that time, the environmental temperature, the distance and motion state of the target object, and other information. These recorded information is sorted and stored according to a certain format and structure, thereby constructing a control database. Through continuous accumulation and storage of these data, the control database will become more and more rich and comprehensive.

[0073] When subsequent aiming parameter optimization needs to be performed, control similarity analysis of the control database is started. First, the current input environment data are extracted, including various environmental factors and related characteristics, etc. Then, these data are compared with the existing records in the control database one by one, and a specific algorithm and standard are used to evaluate the similarity degree of the current data and each record in the database, such as Pearson correlation coefficient, cosine similarity, Jaccard similarity, etc. The similarity degree of environmental factors, the matching degree of target characteristics, etc. are considered. Through this analysis, the most similar records to the current situation are found from the control database, and the aiming parameter optimization results corresponding to these similar records can be used as an important reference.

[0074] According to the control similarity analysis result, the control database is called, and the call result is taken as the ground state result, which means that through the similarity analysis of the control database, the most similar data to the current situation are found. The state represented by these data, such as a specific aiming parameter combination and the configuration of related environmental factors, is regarded as the ground state result. Then, this ground state result is used to perform aiming fitting, that is, to adjust and optimize the current aiming parameters to achieve better results. By combining control similarity analysis and control database call, efficiency and accuracy can be improved, and unnecessary attempts and errors can be reduced.

[0075] In summary, the embodiments of the present application have at least the following technical effects:

[0076] The self-adaptive aiming parameter optimization method provided by the present application establishes an information library of the target sighting telescope, constructs a fine adjustment control interval, performs optimization adjustment of the target sighting telescope through the target adjustment parameter and the fine adjustment control interval, establishes an electronic imaging data set of the ocular lens for optimization iteration evaluation, and performs control management of the target sighting telescope according to the aiming parameter optimization result. The technical effects of rapid adaptation to the environment, improvement of aiming precision and adaptability, intelligent management of the sighting telescope, and continuous improvement are achieved.

[0077] Embodiment Two

[0078] Based on the same inventive concept as the adaptive aiming parameter optimization method in the foregoing embodiment, as shown in the following table, the present application provides an adaptive aiming parameter optimization system, and the system and method embodiments in the present application are based on the same inventive concept. The system comprises: Figure 3

[0079] A scope information library establishing module 10 is configured to establish an information library of a target scope, wherein the information library comprises a topological structure information library and a basic lens information database, and the information library is constructed by calling a database of the same model as the target scope.

[0080] A reference scene division module 20 is configured to divide a reference scene based on the information library, and establish N scene spaces, wherein the N scene spaces are mapped with corresponding adjustment parameters.

[0081] A fine-tuning control interval constructing module 30 is configured to evaluate individual differences of a corresponding model scope based on the information library, and construct a fine-tuning control interval based on the evaluation result of the individual differences.

[0082] An input environment data acquisition module 40 is configured to acquire input environment data of a user, take the input environment data as first matching data, call a laser sensor integrated in a target scope, perform trigger collection, and establish second matching data.

[0083] A target adjustment parameter calling module 50 is configured to perform adaptive matching of the N scene spaces based on the first matching data and the second matching data, and call a target adjustment parameter according to the matching result.

[0084] A scope parameter optimization result generating module 60 is configured to perform optimization adjustment of the target scope through the target adjustment parameter and the fine-tuning control interval, establish an electronic imaging data set of the eyepiece, perform optimization iteration evaluation through the electronic imaging data set, and generate a scope parameter optimization result according to the evaluation result.

[0085] A scope control module 70 is configured to perform control management of the target scope based on the scope parameter optimization result.

[0086] Further, the input environment data acquisition module 40 further comprises:

[0087] ​A fuzzy parameter identification unit is configured to analyze the input environment data and establish fuzzy identification parameters.

[0088] A fuzzy matching feature construction unit is configured to establish features of the object to be observed and input the fuzzy identification parameters and the features of the object to be observed into a fuzzy identification model to construct fuzzy matching features.

[0089] A fuzzy matching result establishment unit is configured to control the target scope to collect the object to be observed in a predetermined search space and perform fuzzy matching through the fuzzy matching features to establish fuzzy matching results.

[0090] A trigger collection execution unit is configured to perform center alignment according to the fuzzy matching results and call a laser sensor integrated in the target scope to perform trigger collection after the center alignment.

[0091] Further, the fuzzy matching result establishment unit further includes:

[0092] A target scope activation unit is configured to activate the target scope and place the target scope in a state to be observed.

[0093] A control parameter reading unit is configured to read control parameters of a user and record control results of the user, wherein the control results are control results of the user manually identifying the object to be observed in the ocular lens.

[0094] A predetermined search space establishment unit is configured to establish the predetermined search space according to the control results.

[0095] Further, the targeting parameter optimization result generation module 60 further includes:

[0096] A key parameter adjustment limit interval establishment unit is configured to establish an adjustment limit interval of a key parameter based on the target adjustment parameter and the fine adjustment control interval and segment the adjustment limit interval through a preset segmentation point.

[0097] An adjustment limit interval reconstruction unit is configured to obtain electronic imaging data corresponding to an adjustment limit interval segmentation result, perform identification effect evaluation, and reconstruct the adjustment limit interval according to the evaluation result.

[0098] A targeting parameter optimization result generation unit is configured to perform iterative processing of segmentation and reconstruction to generate a targeting parameter optimization result.

[0099] Further, the aiming parameter optimization result generation unit further comprises:

[0100] An iteration result monitoring unit is configured to continuously monitor the iteration result and perform comparison between the iteration result and the evaluation result of the last round.

[0101] A rollback instruction generation unit is configured to generate a rollback instruction if there is a comparison abnormality, and perform reconstruction processing again to complete continuous iteration through the rollback instruction after a preset segmentation point is updated.

[0102] Further, the scope control module 70 further comprises:

[0103] A feedback data set establishment unit is configured to obtain user feedback corresponding to the aiming parameter optimization result, and establish a feedback data set.

[0104] A device deviation feature establishment unit is configured to establish device deviation features in N scene spaces according to the feedback data set.

[0105] An aiming parameter optimization management unit is configured to perform subsequent aiming parameter optimization management based on the device deviation feature establishment result.

[0106] Further, the scope control module 70 further comprises:

[0107] A control database construction unit is configured to record the aiming parameter optimization result and input environment data, and construct a control database.

[0108] A control database analysis unit is configured to perform control similarity analysis of the control database when performing subsequent aiming parameter optimization.

[0109] An aiming fitting unit is configured to perform control database calling according to the control similarity analysis result, take the calling result as a ground state result, and perform aiming fitting.

[0110] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0111] The above description is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0112] The specification and drawings are only exemplary and illustrative of the present application and are to be considered within the scope of the present application. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and equivalent technology, the present application is intended to include these modifications and variations.

Claims

1. A method of adaptive collimation parameter optimization, characterized in that, The method comprises: establishing an information base of the target sighting telescope, the information base comprising a topological structure information base and a basic lens information database, the information base being constructed by calling a database constructed based on data of the same model as the target sighting telescope; performing reference scene division based on the information base to establish N scene spaces, wherein the N scene spaces are mapped with corresponding adjustment parameters; performing individual difference evaluation of the corresponding model sighting telescope based on the information base, and constructing a fine adjustment control interval based on the individual difference evaluation result; obtaining input environment data of a user, taking the input environment data as first matching data, calling a laser sensor integrated in the target sighting telescope, performing triggered collection, and establishing second matching data; performing adaptive matching of the N scene spaces based on the first matching data and the second matching data, and calling target adjustment parameters according to the matching result; performing optimization adjustment of the target sighting telescope through the target adjustment parameters and the fine adjustment control interval, establishing an electronic imaging data set of the ocular lens, performing iterative evaluation through the electronic imaging data set, and generating a sighting parameter optimization result according to the evaluation result; performing control management of the target sighting telescope based on the sighting parameter optimization result; obtaining input environment data of a user, taking the input environment data as first matching data, calling a laser sensor integrated in the target sighting telescope, performing triggered collection, and establishing second matching data, and further comprising: analyzing the input environment data to establish fuzzy recognition parameters; establishing features of the object to be observed, and constructing the fuzzy recognition parameters and the features of the object to be observed into a fuzzy recognition model to construct fuzzy matching features; controlling the target sighting telescope to collect the object to be observed in a predetermined search space, and performing fuzzy matching through the fuzzy matching features to establish a fuzzy matching result; performing center alignment according to the fuzzy matching result, and calling the laser sensor integrated in the target sighting telescope after center alignment to perform triggered collection.

2. A method of adaptive collimation parameter optimization as claimed in claim 1, wherein, Before the controlling the target sighting telescope to collect the object to be observed in a predetermined search space, and performing fuzzy matching through the fuzzy matching features to establish a fuzzy matching result, further comprising: activating the target sighting telescope, and placing the target sighting telescope in a state to be observed; reading control parameters of a user, and recording control results of the user, wherein the control results are control results of the user manually identifying the object to be observed appearing in the ocular lens; establishing the predetermined search space according to the control results.

3. The method of adaptive collimation parameter optimization of claim 1, wherein, The iterative evaluation through the electronic imaging data set, and the generation of the sighting parameter optimization result according to the evaluation result further comprise: establishing an adjustment limit interval of key parameters based on the target adjustment parameters and the fine adjustment control interval, and segmenting the adjustment limit interval through a preset segmentation point; obtaining electronic imaging data corresponding to the segmentation result of the adjustment limit interval, performing identification effect evaluation, and reconstructing the adjustment limit interval according to the evaluation result; performing iterative processing of segmentation and reconstruction to generate the sighting parameter optimization result.

4. A method of adaptive collimation parameter optimization as claimed in claim 3, wherein, The iterative processing of segmentation and reconstruction to generate the sighting parameter optimization result further comprises: continuously monitoring the iterative result, and performing comparison of the iterative result with the evaluation result of the previous round of result; If there is an abnormal comparison, a rollback instruction is generated, through which, after presetting a segmentation point update, reconstruction processing is re-performed to complete a continuous iteration.

5. The method of adaptive collimation parameter optimization of claim 1, wherein, The control management of the target sighting telescope based on the sighting parameter optimization result further includes: Obtaining user feedback corresponding to the sighting parameter optimization result to establish a feedback dataset; Performing device deviation feature establishment under N scene spaces according to the feedback dataset; Based on the device deviation feature establishment result, subsequent sighting parameter optimization management is performed.

6. The method of adaptive collimation parameter optimization of claim 1, wherein, The method further includes: Recording the sighting parameter optimization result and input environment data to construct a control database; When performing subsequent sighting parameter optimization, control similarity analysis of the control database is performed; According to the control similarity analysis result, control database calling is performed, and the calling result is taken as a ground state result to perform sighting fitting.

7. An adaptive collimation parameter optimization system, comprising: The system includes: A sighting telescope information library establishment module, which is configured to establish an information library of a target sighting telescope, the information library including a topological structure information library and a basic lens information database, and the information library being constructed by calling a database of the same model as the target sighting telescope; A benchmark scene division module, which is configured to divide benchmark scenes based on the information library to establish N scene spaces, wherein the N scene spaces are mapped with corresponding adjustment parameters; A fine-tuning control interval construction module, which is configured to perform individual difference evaluation of corresponding models of sighting telescopes based on the information library, and to construct a fine-tuning control interval based on the individual difference evaluation result; An input environment data acquisition module, which is configured to acquire input environment data of a user, take the input environment data as first matching data, call a laser sensor integrated in a target sighting telescope, perform triggered collection, and establish second matching data; A target adjustment parameter calling module, which is configured to perform adaptive matching of the N scene spaces based on the first matching data and the second matching data, and to call target adjustment parameters according to the matching result; A sighting parameter optimization result generation module, which is configured to perform optimization adjustment of a target sighting telescope through the target adjustment parameters and the fine-tuning control interval, establish an ocular electronic imaging dataset, perform optimization iteration evaluation through the electronic imaging dataset, and generate a sighting parameter optimization result according to the evaluation result; A sighting telescope control module, which is configured to perform control management of a target sighting telescope based on the sighting parameter optimization result; The input environment data acquisition module further includes: A fuzzy parameter identification unit, which is configured to analyze the input environment data to establish fuzzy identification parameters; A fuzzy matching feature construction unit, which is configured to establish features of an object to be observed, and to construct fuzzy matching features by inputting the fuzzy identification parameters and the features of the object to be observed into a fuzzy identification model. The fuzzy matching result establishing unit is configured to control the target sighting telescope to collect the object to be observed in a predetermined search space, and perform fuzzy matching through fuzzy matching features to establish a fuzzy matching result. The trigger collection executing unit is configured to perform center alignment according to the fuzzy matching result, and call a laser sensor integrated in the target sighting telescope after the center alignment to perform trigger collection.

Images