Stereoscopic endoscope imaging optimization method and system based on objective lens optics

Abstract

The present invention provides a method and system for optimizing stereoscopic endoscope imaging based on objective lens optics, which relates to the technical field of imaging optimization and includes: reading the device information of the stereoscopic endoscope, performing aberration analysis on the objective lens, establishing a set of response parameters, performing pre-acquisition of images in the target area, collecting the imaging of the objective lens, establishing pre-acquired images, performing feature recognition within the images, distributing the attention areas, reconstructing the light control parameters based on the depth identification and the regional features of the attention areas, performing imaging fitting with the light control parameters; performing parameter matching of the set of response parameters, generating optimized response parameters, performing imaging control, and configuring image adaptive enhancement parameters with the imaging fitting results; after enhancing the imaging results, performing image fusion to generate stereoscopic imaging. The present invention solves the technical problem in the prior art that the existing stereoscopic endoscope cannot accurately combine parameters and the environment, resulting in poor imaging effects during the process of imaging control.

Description

Technical Field

[0001] The present invention relates to the field of imaging optimization technology, and particularly to a method and system for optimizing stereoscopic endoscope imaging based on objective lens optics. Background Art

[0002] A stereoscopic endoscope is a medical device that uses the principle of stereoscopic imaging to observe three-dimensional images. It captures and synthesizes images captured by two cameras installed on an optical lens at a certain distance to generate a stereoscopic image. During the application of the stereoscopic endoscope, the imaging effect of the stereoscopic endoscope is affected by various factors. However, the existing stereoscopic endoscopes in the prior art cannot accurately combine parameters and the environment. Therefore, there are technical problems of poor imaging effects during the process of imaging control. Summary of the Invention

[0003] This application provides a method for optimizing stereoscopic endoscope imaging based on objective lens optics, aiming to solve the technical problem that the existing stereoscopic endoscopes in the prior art cannot accurately combine parameters and the environment, resulting in poor imaging effects during the process of imaging control.

[0004] In view of the above problems, this application provides a method and system for optimizing stereoscopic endoscope imaging based on objective lens optics.

[0005] In the first aspect disclosed in this application, a method for optimizing stereoscopic endoscope imaging based on objective lens optics is provided. The method includes: reading device information of the stereoscopic endoscope, and performing aberration analysis of the objective lens based on the device information to establish a response parameter set, where the response parameter set has a sample distance and a light state identifier; pre-collecting an image of a target area with the stereoscopic endoscope and collecting objective lens imaging to establish a pre-collected image, where the pre-collected image has a depth identifier; performing feature recognition within the pre-collected image, and distributing attention areas based on the feature recognition results, reconstructing light control parameters based on the depth identifier and the regional features of the attention areas, and performing imaging fitting with the light control parameters; performing parameter matching of the response parameter set with the imaging fitting results to generate optimized response parameters, performing imaging control with the optimized response parameters and the light control parameters, and configuring image adaptive enhancement parameters with the imaging fitting results; enhancing the imaging result based on the adaptive enhancement parameters, and then performing image fusion to generate stereoscopic imaging with the fusion result.

[0006] The second aspect disclosed in this application provides a stereoscopic endoscope imaging optimization system based on objective lens optics. The system is used for the above-mentioned stereoscopic endoscope imaging optimization method based on objective lens optics. The system includes: an aberration analysis module, which is used to read the device information of the stereoscopic endoscope, perform aberration analysis on the objective lens based on the device information, and establish a set of response parameters. The set of response parameters has a sample distance and a light state identifier; an image pre-acquisition module, which is used to perform image pre-acquisition of the target area with the stereoscopic endoscope and collect the imaging of the objective lens to establish a pre-acquired image, where the pre-acquired image is marked with a depth identifier; an imaging fitting module, which is used to perform in-image feature recognition on the pre-acquired image, distribute the attention area according to the feature recognition result, reconstruct the light control parameters based on the depth identifier and the regional features of the attention area, and perform imaging fitting with the light control parameters; an imaging control module, which is used to perform parameter matching of the set of response parameters with the imaging fitting result, generate optimized response parameters, perform imaging control through the optimized response parameters and the light control parameters, and configure image adaptive enhancement parameters with the imaging fitting result; an image fusion module, which is used to perform image fusion after enhancing the imaging result based on the adaptive enhancement parameters, and generate stereoscopic imaging with the fusion result.

[0007] The third aspect disclosed in this application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in this application is implemented.

[0008] The fourth aspect disclosed in this application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, any step of the first aspect disclosed in this application is implemented.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By reading device information and performing aberration analysis, a set of response parameters can be established to accurately describe the optical characteristics of the objective lens, thereby optimizing in subsequent imaging processes; during the imaging process, since different target regions may have different characteristics and depths, by allocating attention to regions according to the features within the image and reconstructing the light control parameters based on the depth identification and the features of the attention regions, effective control of the imaging quality of different regions is achieved; by performing parameter matching of the set of response parameters according to the imaging fitting results, optimized response parameters are generated to achieve automatic parameter adjustment, improving the efficiency and stability of the imaging process; by enhancing the imaging results based on adaptive enhancement parameters, enhancement processing can be performed on different regions of the image, thereby improving the local detail clarity and consistency of the imaging results. In summary, the stereoscopic endoscope imaging optimization method based on the objective lens optics effectively solves many technical problems existing in the stereoscopic endoscope imaging process and improves the imaging quality, efficiency, and stability by adopting the above technologies.

[0011] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Brief Description of the Drawings

[0012] Figure 1 It is a schematic flowchart of the stereoscopic endoscope imaging optimization method based on the objective lens optics provided by the embodiment of this application;

[0013] Figure 2 It is a schematic structural diagram of the stereoscopic endoscope imaging optimization system based on the objective lens optics provided by the embodiment of this application;

[0014] Figure 3 It is an internal structural diagram of the computer device provided by the embodiment of this application.

[0015] Description of the reference numerals: aberration analysis module 10, image pre-acquisition module 20, imaging fitting module 30, imaging control module 40, image fusion module 50. Detailed Description of the Embodiments

[0016] The embodiment of this application provides a stereoscopic endoscope imaging optimization method based on the objective lens optics, which solves the technical problem that the existing stereoscopic endoscope cannot accurately combine parameters and the environment, resulting in poor imaging effects during the imaging control process.

[0017] After introducing the basic principle of this application, the following will specifically introduce various non-limiting implementation manners of this application in combination with the drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0018] As Figure 1 shown, the embodiment of the present application provides a method for optimizing stereoscopic endoscope imaging based on objective lens optics, and the method includes:

[0019] Reading the device information of the stereoscopic endoscope, performing aberration analysis on the objective lens based on the device information, and establishing a response parameter set, where the response parameter set has a sample distance and a light state identifier;

[0020] Reading the device information of the stereoscopic endoscope includes information in terms of hardware, such as the camera model, lens parameters, etc., and also includes information in terms of software, such as the resolution and frame rate of the captured images. Performing aberration analysis on the objective lens based on the read device information, where aberration refers to the difference between the actual imaging and the ideal imaging, usually caused by various factors, such as errors in the lens manufacturing process, the propagation of light in the lens, etc. Optical simulation methods can be used to simulate and record the aberration conditions under various possible light states to obtain the aberration information of the device. According to the obtained aberration information, a response parameter set is established, which includes a sample distance and a light state identifier. The sample distance refers to the aberration conditions at different imaging distances, and the light state identifier refers to the aberration conditions under different light conditions, such as strong light, weak light, etc.

[0021] Performing pre-acquisition of an image of the target area with the stereoscopic endoscope, and collecting the imaging of the objective lens to establish a pre-acquired image, where the pre-acquired image has a depth identifier;

[0022] Navigating the stereoscopic endoscope to the target area for pre-acquiring an image to obtain the image data of the target area, and the objective lens performs imaging to obtain the optical image of the target area. These images are the images captured by the stereoscopic endoscope in real time for observing the situation of the target area in real time. Saving the pre-acquired image data to form a data set of the pre-acquired image.

[0023] When saving the pre-acquired image, obtaining the depth information of the object in the image through a depth sensor or other depth estimation methods, and associating the depth information with the image data to form a pre-acquired image with a depth identifier.

[0024] Performing feature recognition within the pre-acquired image, distributing the attention area based on the feature recognition result, reconstructing the light control parameter with the depth identifier and the regional feature of the attention area, and performing imaging fitting with the light control parameter;

[0025] Perform image processing and feature extraction on the pre-acquired image, identify various features in the image, including edges, textures, shapes, etc. These features are used to understand the content and structure of the image. Based on the feature recognition results, determine the attention areas in the image, that is, the areas that need special attention. These areas are the target areas or important structures in the image and are used for subsequent imaging analysis.

[0026] Combine the pre-acquired depth identification and the regional features of the attention areas to reconstruct the light control parameters. These parameters include the color, intensity, direction, etc. of the light. By adjusting these parameters, the imaging effect can be optimized, so that better imaging results can be obtained for the attention areas. Use the reconstructed light control parameters to perform imaging fitting on the image, such as using optical simulation or imaging algorithms, and adjust the light control parameters to make the image more consistent with the actual scene and achieve the best imaging effect.

[0027] Perform parameter matching on the response parameter set based on the imaging fitting results to generate optimized response parameters. Perform imaging control through the optimized response parameters and light control parameters, and configure the image adaptive enhancement parameters with the imaging fitting results;

[0028] Analyze the imaging fitting results to obtain the imaging differences and optimization space therein, including comparing the differences between the fitting results and the actual scene, and evaluating the impact of various parameter adjustments on the imaging effect.

[0029] Based on the imaging fitting results, adjust the parameters in the response parameter set, including adjusting parameters such as the sample distance and light state identification in the parameter set according to the characteristics of the fitting results, so that the parameter set can better reflect the actual imaging situation. According to the results of parameter matching, generate optimized response parameters, which are adjusted and optimized to adapt to the current imaging requirements and scene characteristics.

[0030] Use the optimized response parameters and light control parameters to perform imaging control, including adjusting the light source, lens parameters, etc., to make the imaging process more accurate. Finally, use the imaging fitting results to configure the image adaptive enhancement parameters, including sharpening, contrast enhancement, noise removal, etc. of the image, to further improve the quality and clarity of the image.

[0031] After enhancing the imaging results based on the adaptive enhancement parameters, perform image fusion to generate stereoscopic imaging with the fusion results.

[0032] Using the obtained adaptive enhancement parameters, perform enhancement processing on the imaging results, including contrast adjustment, sharpening, denoising, etc. of the image to improve the quality and clarity of the image. Perform image fusion on the enhanced imaging results. Image fusion can be achieved by superimposing multiple images, weighted averaging, etc. to obtain richer and more comprehensive information. In the case of stereoscopic imaging, the imaging results of the left and right eyes can be fused. Generate stereoscopic imaging based on the result of image fusion, that is, apply the fused image to the left and right eyes respectively so that the human eye can perceive the stereoscopic effect.

[0033] Furthermore, the image feature recognition of the pre-acquired image and the distribution of the attention area based on the feature recognition result include:

[0034] Establish a feature library of features to be recognized;

[0035] Traverse the pre-acquired image with the feature library, and generate a matching degree identifier in the two-dimensional image coordinates according to the image traversal result;

[0036] Complete the distribution of the attention area through the matching degree identifier result.

[0037] Determine the features that need to be recognized in the image. These features are related to the target area or can also be used to identify other important structures in the image. Organize the recognized feature data to form a feature library, which contains description information of various features and related identifiers.

[0038] Traverse the image by sliding a window on the pre-acquired image. For each area, extract the corresponding features, which are the features to be recognized defined in the feature library before. Match each extracted feature with the features in the feature library. For example, calculate the similarity between features, such as using Euclidean distance, cosine similarity, etc. for matching. According to the matching result, generate a matching degree identifier for each area in the image. The matching degree identifier is a numerical value indicating the matching degree of the area with the features in the feature library. Map the generated matching degree identifier to the two-dimensional image coordinates of the pre-acquired image to obtain the matching degree identifier corresponding to the pixels of the pre-acquired image.

[0039] Set a threshold according to the result of the matching degree identifier. This threshold can be determined according to specific situations and is used to judge whether an area belongs to the attention area. According to the set threshold, determine the areas in the matching degree identifier result that exceed the threshold as the attention areas. These areas are considered to have a higher matching degree with the features in the feature library and may be important areas in the pre-acquired image. Mark the determined attention areas in the pre-acquired image, which can be achieved by drawing a bounding box on the image and performing color marking.

[0040] Furthermore, reconstructing the light control parameters with the regional features of the depth identification and the attention area, and performing imaging fitting with the light control parameters, includes:

[0041] Obtain the accuracy requirements for imaging. Based on the accuracy requirements, depth identification, and attention area, perform adaptive aggregation of the regions to generate a region adaptive clustering result, and the region adaptive clustering result carries a mapped focus identification;

[0042] Input the depth identification, the regional features of the attention area, and the focus identification into a light response model to generate light control parameters. Among them, the light control parameters include light color, light intensity, and lighting direction, and perform imaging fitting with the light control parameters.

[0043] Obtain the accuracy requirements for imaging, that is, how high the imaging quality and accuracy need to be achieved, including requirements for aspects such as the resolution, clarity, and contrast of the imaging. Combine the accuracy requirements for imaging, depth identification, and attention area, and perform adaptive aggregation on each region in the pre-acquired image. That is, according to the accuracy requirements for imaging, perform aggregation processing on the pixels in different depths and attention areas to improve the quality and accuracy of the imaging. Generate a region adaptive clustering result from the result of the adaptive aggregation, including grouping the image pixels into different clusters, and each cluster represents a specific region with similar imaging characteristics. For each region adaptive clustering result, identify the mapped foci therein, and these foci are the regions that need special attention during the imaging process.

[0044] First, establish a light response model. This model can generate light control parameters suitable for binocular imaging according to the depth identification, the regional features of the attention area, and the focus identification. These parameters include the color, intensity, and lighting direction of the light, etc. Take the depth identification, the regional features of the attention area, and the focus identification as input data and input them into the light response model. In the light response model, generate light control parameters according to the input data. These parameters are used to control the color, intensity, and lighting direction of the light during the imaging process, etc., to meet the requirements of binocular imaging.

[0045] Use the generated light control parameters to perform imaging fitting on the pre-acquired image, including using optical simulation or imaging algorithms to make the image more consistent with the actual scene by adjusting the light control parameters to achieve the best imaging effect.

[0046] Since this imaging is binocular and binocular fusion is required to establish stereoscopic imaging, therefore, for each eye camera, the above steps need to be performed to obtain the light control parameters suitable for that camera. These two sets of solutions will be different because binocular imaging usually needs to consider the differences between the left and right eyes and the perspective problems.

[0047] Furthermore, inputting the depth identifier, the regional features of the attention area, and the focus identifier into the light response model to generate light control parameters includes:

[0048] Obtain the objective lens deviation angle of binocular imaging;

[0049] After the light control parameter of any one objective lens is set, perform light direction compensation for the second objective lens according to the objective lens deviation angle, and establish the light control parameter of the second objective lens based on the light direction compensation result.

[0050] In binocular imaging, the objective lens deviation angle refers to the angular deviation between the left and right cameras, that is, the viewing angle difference between the two cameras. This angular deviation can affect the effect of stereoscopic imaging. A common method to obtain the objective lens deviation angle of binocular imaging is through camera calibration. Camera calibration refers to determining the internal parameters of the camera, such as focal length and optical center, and external parameters, such as rotation matrix and translation vector. In binocular camera calibration, images are taken at different angles through a specific calibration board, and image processing and computer vision methods are used to calculate the relative position between the cameras, thereby obtaining the objective lens deviation angle.

[0051] By obtaining the objective lens deviation angle of binocular imaging, this angular deviation can be considered in subsequent image processing and imaging fitting processes to ensure that the images of the left and right cameras can be correctly matched, thereby obtaining a more accurate stereoscopic imaging effect.

[0052] In binocular imaging, after the light control parameter of any one objective lens is set, perform light direction compensation for the second objective lens according to the objective lens deviation angle to ensure that the imaging between the left and right cameras can match each other and maintain the accuracy and stability of stereoscopic imaging.

[0053] Specifically, select the light control parameter of one of the objective lenses, for example, the left camera, and set it to the required value. According to the objective lens deviation angle, perform light direction compensation on the light control parameter of the other objective lens, for example, the right camera, that is, adjust the original light control parameter so that the imaging direction of the right camera matches that of the left camera. Based on the light direction compensation result, establish the new light control parameter of the second objective lens, for example, the right camera. These parameters are used in the imaging process of the right camera to ensure consistency with the imaging of the left camera.

[0054] Furthermore, after enhancing the imaging result based on the adaptive enhancement parameter, perform image fusion, including:

[0055] Sample the attention area and non-attention area of the imaging result, and perform consistency verification on the imaging fitting result based on the sampling result;

[0056] Perform adaptive enhancement parameter incremental compensation based on the consistency verification result, where the incremental compensation control is as follows:

[0057] S1: Establish an adaptive enhancement model based on big data, extract the image features of the imaging fitting result, use them as input features and input them into the adaptive enhancement model to output adaptive enhancement parameters;

[0058] S2: Configure an incremental fine-tuning interval, use the incremental fine-tuning interval as the hidden layer constraint, input the consistency verification result into the incremental training model with hidden layer constraint to complete the adaptive enhancement parameter incremental compensation, where the incremental training model is obtained by incremental training with the adaptive enhancement model as the base model.

[0059] Select a certain number of sample points from the imaging result, which come from the attention area and the non-attention area respectively. The attention area is determined according to the previous analysis, and the non-attention area is other areas except the attention area. For each sample point, obtain the corresponding data from the imaging fitting result, including image pixel values, color information, depth information, etc.

[0060] Compare the data of the sampled attention area and non-attention area to verify their consistency. This can be achieved by calculating indicators such as the difference in pixel values, color consistency, and depth information consistency. According to the result of the consistency verification, analyze whether the performance of the imaging result in the attention area and the non-attention area is consistent. If the consistency is good, it indicates that the imaging fitting result has good accuracy and stability throughout the image range.

[0061] Perform adaptive enhancement parameter incremental compensation according to the consistency verification result to improve the imaging quality and accuracy and meet the imaging requirements in different scenarios. The incremental compensation control is as follows:

[0062] First, collect a large amount of image data, which covers various different scenarios, lighting conditions, shooting angles, etc. This data can be images from real scenes or images generated through simulation or synthesis. Based on the collected large amount of image data, train an adaptive enhancement model, which can be various machine learning models, such as deep neural networks, support vector machines, random forests, etc. The goal of the model is to learn the relationship between image features and the best enhancement parameters.

[0063] Extract features from the image of the imaging fitting result. These features include color histograms, gradient information, texture features, etc. The purpose of feature extraction is to convert the information of the image into a numerical form that can be processed by machine learning models.

[0064] Taking the extracted image features as input, input them into the established adaptive enhancement model. The model outputs the adaptive enhancement parameters corresponding to the input features according to the mapping relationship learned between the image features and the optimal enhancement parameters. These parameters are dynamically adjusted according to the features of the input image to adapt to different imaging scenarios and requirements.

[0065] Determine the range of the incremental fine-tuning interval, which can be determined according to factors such as the metrics of consistency verification and the performance of the model. Take the configured incremental fine-tuning interval as the hidden layer constraint, which restricts the range of parameter changes of the incremental training model during the fine-tuning process to ensure that the performance of the fine-tuned model is still within an acceptable range.

[0066] Apply the incremental training model with hidden layer constraints to the adaptive enhancement model. This incremental training model is obtained by incremental training based on the adaptive enhancement model, and it can fine-tune the adaptive enhancement parameters according to the consistency verification results while maintaining the overall performance of the model.

[0067] Take the consistency verification results as input and input them into the incremental training model with hidden layer constraints. These results include various metrics regarding image consistency, such as pixel differences, color consistency, contrast, etc. Under the action of the incremental training model, perform incremental compensation on the adaptive enhancement parameters according to the consistency verification results, so that the parameters can be dynamically adjusted according to the verification results to improve the consistency and accuracy of imaging, thereby optimizing the quality and effect of imaging.

[0068] Furthermore, the method further includes:

[0069] Perform co-location alignment on the enhanced images, and perform image feature stitching with the co-location alignment results;

[0070] Complete image fusion with the image feature stitching results to establish stereoscopic imaging.

[0071] Perform co-location alignment on the enhanced images, which can be achieved by methods such as image registration or feature point matching. The goal is to make the same positions of different images have the same pixel coordinates for subsequent feature stitching.

[0072] Extract features from the co-location aligned images. These features include local features, global features, or depth features, etc. The purpose of feature extraction is to capture the key information of the images. Align the extracted image features. For example, convert the feature point coordinates so that they are in the same coordinate system. Stitch the aligned image features. The stitched features contain information from different images and have a more comprehensive and rich representation.

[0073] Fuse the features obtained by feature concatenation. For example, perform weighted averaging of features, fusion of depth information, fusion of color information, etc. The goal is to fuse information from different perspectives into an overall feature representation. Using the fused features, generate a stereoscopic image. The goal of the stereoscopic image is to enable the observer to perceive the stereoscopic effect of the image, that is, the objects seen in the image have a sense of depth.

[0074] Furthermore, the method further includes:

[0075] Perform feature matching on the stereoscopic image, and generate an additional identifier based on the matching similarity and the matching subject. Among them, the additional identifier includes a warning level identifier, and the warning features of different warning levels are different;

[0076] Perform annotation management of the stereoscopic image through the additional identifier.

[0077] Extract features from the stereoscopic image. These features can include local features, global features, depth features, etc. of the image. Perform matching on the extracted features, including comparison of feature descriptors and matching of feature points. The goal is to find similar feature points or feature regions in the image.

[0078] According to the result of feature matching, calculate the matching similarity, including comparing indicators such as the number of matching points and the similarity of feature descriptors. According to the matching similarity and the matching subject, generate an additional identifier, which includes a warning level identifier. The warning level identifier can be determined according to the size of the matching similarity, that is, the higher the similarity, the higher the warning level. In addition, the warning features can also vary according to different matching subjects. For example, different warning measures need to be taken for different types of targets or different matching situations.

[0079] Parse the generated additional identifier, including the warning level identifier. According to the parsed additional identifier, extract the corresponding annotation information, including information such as matching similarity, matching subject, and warning level. Establish an annotation management system for recording and managing the annotation information of the stereoscopic image. Record the extracted annotation information into the annotation management system, including associating information such as matching similarity, matching subject, and warning level with the corresponding stereoscopic image. Provide a query function that enables users to retrieve annotation information as needed, such as querying relevant stereoscopic images according to a specific warning level, or analyzing according to the matching subject. Such an annotation management system can provide users with a convenient and fast annotation query function, which helps to better understand and utilize the information of the stereoscopic image.

[0080] In summary, the stereoscopic endoscope imaging optimization method based on objective lens optics provided by the embodiments of the present application has the following technical effects:

[0081] 1. By reading device information and performing aberration analysis, a set of response parameters can be established to accurately describe the optical characteristics of the objective lens, so as to optimize in the subsequent imaging process;

[0082] 2. During the imaging process, since different target regions may have different characteristics and depths, by allocating attention to regions according to the features within the image, and reconstructing the light control parameters based on the depth identification and the features of the attention regions, the effective control of the imaging quality of different regions is achieved;

[0083] 3. By performing parameter matching of the set of response parameters according to the imaging fitting results, optimized response parameters are generated to achieve automatic parameter adjustment, improving the efficiency and stability of the imaging process;

[0084] 4. Through the enhancement of the imaging results based on the adaptive enhancement parameters, enhancement processing can be performed on different regions of the image, thereby improving the local detail clarity and consistency of the imaging results.

[0085] In summary, the stereoscopic endoscope imaging optimization method based on the objective lens optics effectively solves many technical problems existing in the stereoscopic endoscope imaging process by adopting the above technologies, improving the imaging quality, efficiency and stability.

[0086] Based on the same inventive concept as the stereoscopic endoscope imaging optimization method based on the objective lens optics in the foregoing embodiments, as Figure 2 shown, the present application provides a stereoscopic endoscope imaging optimization system based on the objective lens optics, and the system includes:

[0087] An aberration analysis module 10, which is used to read the device information of the stereoscopic endoscope and perform aberration analysis of the objective lens based on the device information to establish a set of response parameters, and the set of response parameters has a sample distance and a light state identifier;

[0088] An image pre-acquisition module 20, which is used to perform pre-acquisition of the image of the target region with the stereoscopic endoscope and collect the imaging of the objective lens to establish a pre-acquired image, wherein the pre-acquired image is provided with a depth identifier;

[0089] An imaging fitting module 30, which is used to identify the features within the pre-acquired image, distribute the attention regions according to the feature recognition results, reconstruct the light control parameters based on the depth identifier and the regional features of the attention regions, and perform imaging fitting with the light control parameters;

[0090] An imaging control module 40, which is used to perform parameter matching of a response parameter set with an imaging fitting result, generate optimized response parameters, perform imaging control through the optimized response parameters and light control parameters, and configure image adaptive enhancement parameters with the imaging fitting result;

[0091] An image fusion module 50, which is used to enhance the imaging result based on the adaptive enhancement parameters and then perform image fusion to generate a stereoscopic image with the fusion result.

[0092] Furthermore, the system further includes an attention area distribution module to perform the following operation steps:

[0093] Establish a feature library of features to be recognized;

[0094] Perform image traversal of pre-acquired images with the feature library, and generate a matching degree identifier in two-dimensional image coordinates according to the image traversal result;

[0095] Complete the distribution of the attention area through the matching degree identifier result.

[0096] Furthermore, the system further includes an imaging fitting module to perform the following operation steps:

[0097] Obtain the accuracy requirement of imaging, perform adaptive aggregation of regions based on the accuracy requirement, depth identifier, and attention area, and generate a region adaptive clustering result with a mapping focus identifier;

[0098] Input the depth identifier, regional features of the attention area, and focus identifier into a light response model to generate light control parameters, where the light control parameters include light color, light intensity, and lighting direction, and perform imaging fitting with the light control parameters.

[0099] Furthermore, the system further includes a lighting direction compensation module to perform the following operation steps:

[0100] Obtain the objective lens deviation angle of binocular imaging;

[0101] When the light control parameters of any one objective lens are set, perform lighting direction compensation for the second objective lens according to the objective lens deviation angle, and establish the light control parameters of the second objective lens with the lighting direction compensation result.

[0102] Furthermore, the system further includes an incremental compensation module to perform the following operation steps:

[0103] Sample the attention area and non-attention area of the imaging result, and perform consistency verification of the imaging fitting result based on the sampling result;

[0104] Perform adaptive enhancement parameter incremental compensation according to the consistency verification result, where the incremental compensation control is as follows:

[0105] S1: Establish an adaptive enhancement model based on big data, extract the image features of the imaging fitting result, and use them as input features to input into the adaptive enhancement model to output adaptive enhancement parameters;

[0106] S2: Configure an incremental fine-tuning interval, use the incremental fine-tuning interval as the hidden layer constraint, input the consistency verification result into the incremental training model with hidden layer constraint to complete the adaptive enhancement parameter incremental compensation, where the incremental training model is obtained by incremental training with the adaptive enhancement model as the basic model.

[0107] Furthermore, the system further includes a stereoscopic imaging establishment module to perform the following operation steps:

[0108] Perform co-location alignment of the enhanced image, and perform image feature splicing with the co-location alignment result;

[0109] Complete image fusion with the image feature splicing result to establish stereoscopic imaging.

[0110] Furthermore, the system further includes a labeling management module to perform the following operation steps:

[0111] Perform feature matching on the stereoscopic imaging, and generate an additional identifier with the matching similarity and the matching subject, where the additional identifier includes a warning level identifier, and the warning features of different warning levels are different;

[0112] Perform labeling management of the stereoscopic imaging through the additional identifier.

[0113] Through the foregoing detailed description of the method for optimizing stereoscopic endoscope imaging based on objective lens optics in this specification, those skilled in the art can clearly know the stereoscopic endoscope imaging optimization system based on objective lens optics in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For related parts, refer to the description in the method part.

[0114] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 3As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the network interface of the computer device is used to communicate with an external terminal via a network connection. The computer program is executed by the processor to implement an optimization method for stereoscopic endoscope imaging based on objective lens optics.

[0115] Those skilled in the art can understand that Figure 3 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0116] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0117] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An optimization method for stereoscopic endoscope imaging based on the optics of the objective lens, characterized in that, The method includes: Reading the device information of the stereoscopic endoscope, performing aberration analysis on the objective lens based on the device information, and establishing a set of response parameters. The set of response parameters has a sample distance and a light state identifier. The sample distance refers to the aberration at different imaging distances, and the light state identifier refers to the aberration under different light conditions; Pre-collecting an image of the target area with the stereoscopic endoscope and collecting the imaging of the objective lens to establish a pre-collected image, where the pre-collected image has a depth identifier; Performing in-image feature recognition on the pre-collected image, distributing the attention area according to the feature recognition result, reconstructing the light control parameters based on the depth identifier and the regional features of the attention area, and performing imaging fitting with the light control parameters; Performing parameter matching on the set of response parameters with the imaging fitting result to generate optimized response parameters, performing imaging control with the optimized response parameters and the light control parameters, and configuring the image adaptive enhancement parameters with the imaging fitting result; After enhancing the imaging result based on the adaptive enhancement parameters, performing image fusion, and generating a stereoscopic image with the fusion result; The reconstructing the light control parameters based on the depth identifier and the regional features of the attention area and performing imaging fitting with the light control parameters includes: Obtaining the accuracy requirement of imaging, performing adaptive aggregation of the area based on the accuracy requirement, the depth identifier, and the attention area to generate a region adaptive clustering result, and the region adaptive clustering result has a mapped focus identifier; Inputting the depth identifier, the regional features of the attention area, and the focus identifier into a light response model to generate light control parameters. The light control parameters include light color, light intensity, and lighting direction, and performing imaging fitting with the light control parameters.

2. The method according to claim 1, characterized in that The performing in-image feature recognition on the pre-collected image and distributing the attention area according to the feature recognition result includes: Establishing a feature library of features to be recognized; Traversing the pre-collected image with the feature library, and generating a matching degree identifier in the two-dimensional image coordinates according to the image traversal result; Completing the distribution of the attention area through the matching degree identifier result.

3. The method according to claim 1, characterized in that The inputting the depth identifier, the regional features of the attention area, and the focus identifier into a light response model to generate light control parameters includes: Obtaining the objective lens deviation angle of binocular imaging; After setting the light control parameters of any one objective lens, compensating the lighting direction of the second objective lens according to the objective lens deviation angle, and establishing the light control parameters of the second objective lens with the lighting direction compensation result.

4. The method according to claim 1, characterized in that, The performing image fusion after enhancing the imaging result based on the adaptive enhancement parameters includes: Sampling the attention area and the non-attention area of the imaging result, and performing consistency verification on the imaging fitting result based on the sampling result; Performing incremental compensation of the adaptive enhancement parameters according to the consistency verification result, and the incremental compensation control is as follows: S1: Establishing an adaptive enhancement model based on big data, extracting the image features of the imaging fitting result, and inputting them as input features into the adaptive enhancement model to output adaptive enhancement parameters; S2: Configure an incremental fine-tuning range, use the incremental fine-tuning range as a hidden layer constraint, and input the consistency verification result into an incremental training model with a hidden layer constraint to complete the incremental compensation of the adaptive enhancement parameters, where the incremental training model is obtained by incrementally training based on an adaptive enhancement model.

5. The method according to claim 4, wherein The method further includes: Perform co-location alignment on the enhanced image, and perform image feature splicing based on the co-location alignment result; Complete image fusion with the image feature splicing result to establish stereoscopic imaging.

6. The method according to claim 1, characterized in that, The method further includes: Perform feature matching on the stereoscopic imaging, and generate an additional identifier based on the matching similarity and the matching subject, where the additional identifier includes a warning level identifier, and the warning features of different warning levels are different; Perform annotation management of the stereoscopic imaging through the additional identifier.

7. An optimized system for stereoscopic endoscope imaging based on the objective lens optics, characterized in that, For implementing the method for optimizing stereoscopic endoscope imaging based on objective lens optics according to any one of claims 1-6, the system includes: An aberration analysis module, which is used to read the device information of the stereoscopic endoscope, perform aberration analysis of the objective lens based on the device information, and establish a response parameter set, where the response parameter set has a sample distance and a light state identifier. The sample distance refers to the aberration situation at different imaging distances, and the light state identifier refers to the aberration situation under different light conditions; An image pre-acquisition module, which is used to perform pre-acquisition of an image of a target area with the stereoscopic endoscope and collect the objective lens imaging to establish a pre-acquired image, where the pre-acquired image has a depth identifier; An imaging fitting module, which is used to perform in-image feature recognition on the pre-acquired image, distribute the attention area based on the feature recognition result, reconstruct the light control parameters with the depth identifier and the regional features of the attention area, and perform imaging fitting with the light control parameters; An imaging control module, which is used to perform parameter matching of the response parameter set with the imaging fitting result, generate optimized response parameters, perform imaging control with the optimized response parameters and the light control parameters, and configure the image adaptive enhancement parameters with the imaging fitting result; An image fusion module, which is used to perform image fusion after enhancing the imaging result based on the adaptive enhancement parameters, and generate stereoscopic imaging with the fusion result.

8. A computer device, including a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for optimizing stereoscopic endoscope imaging based on objective lens optics according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for optimizing stereoscopic endoscope imaging based on objective lens optics according to any one of claims 1 to 6.

Images