An endoscope video image processing method and device based on AIGC

Abstract

The application discloses an endoscope video image processing method and device based on AIGC. Under the starting of a doctor's recording operation, a video recording state is entered, and each frame of picture fed back by an endoscope is recorded. Meanwhile, with the extension of the recording time length, part of the frames of pictures are discarded according to a first preset rule, so as to shorten the content of the recorded video. Therefore, the generation speed of the recorded video is improved, and the space occupation size of the recorded video is reduced.

Description

Technical Field

[0001] This application relates to the field of endoscopy technology, and in particular to an endoscopic video image processing method and apparatus based on AIGC. Background Technology

[0002] Endoscopes, as advanced medical devices integrating traditional optics, ergonomics, precision mechanics, modern electronics, and software technology, are widely used in the field of medical diagnosis. Their principle is mainly to capture images inside the body through optical lenses and image sensors, then convert these images into electrical signals, which are then displayed on a screen for doctors to observe and analyze. Endoscopes can enter the human body through the mouth or other natural body cavities, providing doctors with visual information that is difficult to obtain using traditional imaging techniques such as X-rays, which is of great significance for the early detection and precise treatment of diseases.

[0003] Recording and saving video footage during endoscopic procedures is crucial for doctors' subsequent research. This video data not only helps doctors review and analyze cases but also serves as valuable teaching material and case study data. However, the amount of video data generated increases rapidly with the duration of the procedure.

[0004] Storing such large amounts of video data presents a significant problem: enormous memory consumption. Continuous video recording consumes a large amount of storage space, which not only increases the cost of data storage but also poses challenges to data transmission and management. Summary of the Invention

[0005] The purpose of this application is to provide an endoscopic video image processing method and apparatus based on AIGC, which can improve the above-mentioned problems.

[0006] The embodiments of this application are implemented as follows:

[0007] In the first aspect, this application provides an endoscopic video image processing method based on AIGC, including steps S10 to S40, wherein S10, S20, etc. are only step identifiers, and the execution order of the method is not necessarily in ascending order of numbers. For example, step S20 can be executed first and then step S10 can be executed. This application does not impose any restrictions.

[0008] S10: In response to the recording operation, store the frame images fed back by the endoscope probe in the temporary library;

[0009] S20: Under the first preset condition, discard some frames in the temporary library that meet the second preset condition according to the first preset rule;

[0010] S30: Generate the target video file based on the remaining frames in the temporary library.

[0011] It is understood that this application discloses an endoscopic video image processing method based on AIGC, which enters the video recording state when the doctor starts the recording operation and records each frame of the endoscope feedback; at the same time, as the recording time increases, some frames are discarded according to the first preset rule to shorten the content of the recorded video, which not only improves the generation speed of the recorded video, but also reduces the space occupied by the recorded video.

[0012] In optional embodiments of this application, satisfying the first preset condition includes at least one of the following: the current remaining memory is lower than a preset memory threshold; the current remaining storage space is lower than a preset space threshold.

[0013] In optional embodiments of this application, the first preset rule includes at least one of the following:

[0014] The number of discarded frames increases with the duration of recording;

[0015] Over time, some frames are periodically discarded.

[0016] The discard period shortens as the recording duration increases.

[0017] It's understandable that excessively long recording times and a large number of captured frames will lead to longer compositing times, higher memory or storage space consumption, and other system resource usage, resulting in a poor endoscopic experience. Therefore, as recording time increases, the number of discarded frames should be appropriately increased to further accelerate video compositing. Furthermore, periodically discarding portions of frames, rather than discarding frames from a single period, better preserves the integrity of the video content.

[0018] In optional embodiments of this application, satisfying the second preset condition includes at least one of the following:

[0019] Frames with image quality parameters below a parameter threshold; wherein the image quality parameters include at least one of the following: resolution, brightness, color gamut, and contrast.

[0020] Frames with a viewing angle range smaller than the first requirement include only a partial view of the target object.

[0021] A frame with a viewing angle greater than the first requirement includes the overall image of the target object.

[0022] It is understandable that, depending on the purpose, frames that meet the first preset rule can be selectively discarded. For example, to ensure video quality, frames with unsatisfactory image quality parameters can be deleted; to obtain the overall shape of targets such as tumors, frames with too small a field of view can be deleted; and to obtain the lesion details of targets such as the heart, liver, and lungs, frames with too large a field of view can be deleted.

[0023] In an optional embodiment of this application, the above-mentioned AIGC-based endoscopic video image processing method further includes step S40: generating a three-dimensional model of the target object using generative artificial intelligence (AIGC) based on frames with a viewing angle range smaller than the first requirement.

[0024] It is understandable that, in order to further obtain the overall shape of targets such as tumors, AIGC technology can be used to generate a 3D model of the target based on all frames with a viewing range smaller than the first requirement, that is, frames containing the overall shape of the target, so as to provide doctors with further information for judgment and research.

[0025] In an optional embodiment of this application, the above-mentioned AIGC-based endoscopic video image processing method further includes step S200 between steps S20 and S30: generating supplementary frame images according to a second preset rule and inserting them into the temporary library to fill the deleted frame images.

[0026] It is understandable that, in order to reduce the impact of deleted frames on the continuity of the recorded video, AIGC technology or copying technology can be used to fill in the deleted frames and ensure the continuity of the overall recorded video.

[0027] In optional embodiments of this application, the second preset rule includes at least one of the following: copying the previous frame or the next frame as a supplementary frame; generating an intermediate supplementary frame based on the content of the previous frame and the next frame using AIGC technology.

[0028] Secondly, this application discloses an endoscopic video image processing method and apparatus based on AIGC, including an endoscope handle, a host processor, a light source driving module, and a display; the end of the endoscope handle is provided with an endoscope probe for acquiring detection frame images of target living tissue; the host processor is connected to the endoscope handle through a transmission optical fiber and receives the detection frame images; the host processor is also electrically connected to the display and the light source driving module, and the light source driving module is connected to the endoscope handle through a light source transmission optical fiber to provide an illumination source for the endoscope handle; the host processor is configured to execute the method as described in any of the first aspects.

[0029] Beneficial effects:

[0030] This application discloses an endoscopic video image processing method based on AIGC. When the doctor initiates the recording operation, the method enters the video recording state and records each frame of the endoscope feedback. At the same time, as the recording time increases, some frames are discarded according to a first preset rule to shorten the content of the recorded video. This not only improves the generation speed of the recorded video but also reduces the space occupied by the recorded video.

[0031] As recording time increases, the number of dropped frames should be appropriately increased to further accelerate video compositing. Furthermore, periodically dropping portions of frames, rather than dropping frames from a single period, better preserves the integrity of the video content.

[0032] Depending on the purpose, frames that meet the first preset rules can be selectively discarded. For example, to ensure video quality, frames with unsatisfactory image quality parameters can be deleted; to obtain the overall shape of targets such as tumors, frames with too small a field of view can be deleted; and to obtain the lesion details of targets such as the heart, liver, and lungs, frames with too large a field of view can be deleted.

[0033] To further obtain the overall shape of targets such as tumors, AIGC technology can be used to generate a 3D model of the target based on all frames with a viewing range smaller than the first requirement, i.e., frames that contain the overall shape of the target, so as to provide doctors with further information for judgment and research.

[0034] To minimize the impact of deleted frames on the continuity of the recorded video, AIGC or copying techniques can be used to fill in the deleted frames, thus ensuring the overall continuity of the recorded video.

[0035] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, optional embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a schematic diagram of an endoscopic video image processing method based on AIGC provided in this application;

[0038] Figure 2 This is a schematic diagram of an embodiment of the first preset rule in this application;

[0039] Figure 3 This is a schematic diagram of an embodiment of the second preset rule in this application;

[0040] Figure 4 This is a schematic diagram of another embodiment of the second preset rule in this application;

[0041] Figure 5 This is a schematic diagram of an endoscopic video image processing method device based on AIGC provided in this application. Detailed Implementation

[0042] 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 some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0043] Firstly, such as Figure 1 As shown, this application provides an endoscopic video image processing method based on AIGC, including steps S10 to S40. Here, S10, S20, etc. are only step identifiers, and the execution order of the method does not necessarily follow the order of numbers from smallest to largest. For example, step S20 can be executed first and then step S10 can be executed. This application does not impose any restrictions.

[0044] S10: In response to the recording operation, store the frame images fed back by the endoscope probe in a temporary library.

[0045] The recording operation mainly involves the operator of the endoscope device triggering the recording. Before the recording operation is performed, the endoscope device only displays the frames detected by the endoscope probe in real time.

[0046] S20: Under the condition of satisfying the first preset condition, discard some frames in the temporary library that satisfy the second preset condition according to the first preset rule.

[0047] In optional embodiments of this application, satisfying the first preset condition includes at least one of the following: the current remaining memory is lower than a preset memory threshold; the current remaining storage space is lower than a preset space threshold.

[0048] S30: Generate the target video file based on the remaining frames in the temporary library.

[0049] It is understood that this application discloses an endoscopic video image processing method based on AIGC, which enters the video recording state when the doctor starts the recording operation and records each frame of the endoscope feedback; at the same time, as the recording time increases, some frames are discarded according to the first preset rule to shorten the content of the recorded video, which not only improves the generation speed of the recorded video, but also reduces the space occupied by the recorded video.

[0050] In optional embodiments of this application, the first preset rule includes at least one of the following:

[0051] The number of discarded frames increases with the duration of recording;

[0052] Over time, some frames are periodically discarded.

[0053] The discard period shortens as the recording duration increases.

[0054] It's understandable that excessively long recording times and a large number of captured frames will lead to longer compositing times, higher memory or storage space consumption, and other system resource usage, resulting in a poor endoscopic experience. Therefore, as recording time increases, the number of discarded frames should be appropriately increased to further accelerate video compositing. Furthermore, periodically discarding portions of frames, rather than discarding frames from a single period, better preserves the integrity of the video content.

[0055] Optionally, in the first preset rule, the discard period can be determined based on the association period of the duration threshold interval to which the recording duration belongs. Different duration threshold intervals have different association periods. For example, the association period for the first duration threshold is the first period, the association period for the second duration threshold is the second period, the association period for the third duration threshold is the third period, and so on. Specifically, the maximum value of the first duration threshold interval is less than the minimum value of the second duration threshold interval, and the first period is greater than the second period; conversely, the maximum value of the second duration threshold interval is less than the minimum value of the second duration threshold interval, and the second period is greater than the third period.

[0056] For example, such as Figure 2 As shown, the temporary library stores each frame of the endoscope probe feedback; when the recording duration is less than the duration threshold T, the association period associated with the current recording duration is the first period, that is, a frame is dropped once every 20 frames; when the recording duration exceeds the duration threshold T, the association period associated with the current recording duration is the second period, that is, a frame is dropped once every 40 frames.

[0057] In optional embodiments of this application, satisfying the second preset condition includes at least one of the following:

[0058] Frames with image quality parameters below the parameter threshold; wherein the image quality parameters include at least one of the following: resolution, brightness, color gamut, and contrast.

[0059] Frames with a viewing angle range smaller than the first requirement include only a partial view of the target object.

[0060] A frame with a viewing angle greater than the first requirement includes the overall image of the target object.

[0061] It is understandable that, depending on the purpose, frames that meet the first preset rule can be selectively discarded. For example, to ensure video quality, frames with unsatisfactory image quality parameters can be deleted; to obtain the overall shape of targets such as tumors, frames with too small a field of view can be deleted; and to obtain the lesion details of targets such as the heart, liver, and lungs, frames with too large a field of view can be deleted.

[0062] In an optional embodiment of this application, the above-mentioned AIGC-based endoscopic video image processing method further includes step S40: generating a three-dimensional model of the target object using generative artificial intelligence (AIGC) based on frames with a viewing angle range smaller than the first requirement.

[0063] InstantMesh technology can generate high-quality 3D Mesh models from a single image within 10 seconds. It combines a multi-view diffusion generation model with a sparse view reconstruction model based on the LRM architecture, improving the efficiency and consistency of the generated model. Furthermore, another technology, Shap-E, a groundbreaking model developed by OpenAI, can generate a series of 3D objects using text or images as input, demonstrating the versatility of AIGC in 3D generation.

[0064] It is understandable that, in order to further obtain the overall shape of targets such as tumors, AIGC technology can be used to generate a 3D model of the target based on all frames with a viewing range smaller than the first requirement, that is, frames containing the overall shape of the target, so as to provide doctors with further information for judgment and research.

[0065] In an optional embodiment of this application, the above-mentioned AIGC-based endoscopic video image processing method further includes step S200 between steps S20 and S30: generating supplementary frame images according to a second preset rule and inserting them into a temporary library to fill the deleted frame images.

[0066] It's understandable that after dropping frames according to the first rule, the resulting empty frames might cause discontinuity between consecutive frames, affecting the operator's judgment. To minimize the impact of deleted frames on the continuity of the recorded video, AIGC or copying techniques can be used to fill in the missing frames, ensuring the overall continuity of the recorded video.

[0067] In optional embodiments of this application, the second preset rule includes at least one of the following: copying the previous frame or the next frame as a supplementary frame; generating an intermediate supplementary frame based on the content of the previous and next frames using AIGC technology.

[0068] For example, such as Figure 3 As shown, after dropping frames according to the first rule, the frame preceding the empty frame can be directly copied and inserted as a replacement frame. Although the diagram only illustrates the case of copying the previous frame as a replacement frame, it is also possible to copy the next frame as a replacement frame, which will not be elaborated here.

[0069] For example, such as Figure 4 As shown, after frame dropping according to the first rule, AIGC technology can use a suitable AIGC model to generate intermediate supplementary frames based on the content of the previous and next frames.

[0070] AIGC can generate intermediate frames based on the previous and next frames. This process mainly relies on artificial intelligence algorithms and computer vision technology. The specific implementation methods and steps are as follows:

[0071] 1. Data Training:

[0072] AI needs to be trained on large amounts of image data to learn the features and styles of images. This data typically includes images or video sequences of various scenes, actions, and objects.

[0073] Through deep learning algorithms, AI builds models of image features, enabling it to understand and analyze the composition and structure of images.

[0074] 2. Feature extraction and fusion:

[0075] Given a previous and next frame, the AI ​​first extracts key features from these two frames, such as edges, corners, and textures.

[0076] Next, these features are fused using interpolation algorithms or other computer vision techniques to generate features for the intermediate frame.

[0077] 3. Intermediate frame generation:

[0078] Based on the fused features, the AI ​​constructs the intermediate frame. This process may involve interpolating the motion trajectories of objects in the preceding and following frames to ensure that the motion of objects in the intermediate frame is continuous.

[0079] At the same time, AI will also consider environmental factors such as lighting and shadows to ensure the image quality of intermediate frames.

[0080] 4. Optimization and Adjustment:

[0081] After generating intermediate frames, the AI ​​will optimize and adjust them to eliminate potential artifacts, blurring, and other adverse effects.

[0082] This step may involve various image processing techniques, such as noise reduction and sharpening.

[0083] 5. Output and Evaluation:

[0084] Finally, the AI ​​will output the generated intermediate frame. This frame should be consistent with the preceding and following frames and of high quality.

[0085] To evaluate the quality of the generated intermediate frames, various metrics and methods can be used, such as peak signal-to-noise ratio (PSNR), structural similarity metric (SSIM), etc.

[0086] Secondly, such as Figure 5 As shown, this application discloses an endoscopic video image processing method and apparatus based on AIGC, including an endoscope handle 101, a host processor 102, a light source driving module 103, and a display 104; the end of the endoscope handle 101 is provided with an endoscope probe for acquiring detection frame images of target living tissue.

[0087] The host processor 102 is connected to the endoscope handle 101 via a transmission optical fiber 105 to receive probe frame images; the host processor 102 is also electrically connected to the display 104 and the light source driving module 103, the light source driving module 103 is connected to the endoscope handle 101 via a light source transmission optical fiber 106 to provide an illumination source for the endoscope handle 101; the host processor 102 is configured to perform the method as described in any of the first aspects.

[0088] After the endoscope handle 101 acquires the light signal of the target living tissue, it converts the light signal into an electrical signal through the photoelectric conversion module. In order to prevent electromagnetic interference, the sensor adapter board in the endoscope handle 101 samples and processes the transmitted electrical signal and converts it into a parallel-to-serial signal format. The serialized electrical signal is then converted back into a light signal so that it can be transmitted to the host processor 102 through the transmission fiber optic cable 105 for photoelectric conversion again. Finally, the detection frame image is output on the display 104.

[0089] It should be understood that, in the embodiments of the present invention, the host processor may be a Central Processing Unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0090] In specific implementations, the host processor described in the embodiments of the present invention can execute the implementation method described in any of the methods in the first aspect, or it can execute the implementation method of the terminal device described in the embodiments of the present invention, which will not be elaborated here.

[0091] Thirdly, the present invention provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, implement the steps of any of the methods of the first aspect.

[0092] The aforementioned computer-readable storage medium can be an internal storage unit of the terminal device in any of the foregoing embodiments, such as a hard disk or memory of the terminal device. The aforementioned computer-readable storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal device. Furthermore, the aforementioned computer-readable storage medium may include both internal storage units and external storage devices of the terminal device. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the terminal device. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0093] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed terminal devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, or it may be an electrical, mechanical or other form of connection.

[0095] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0096] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0097] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] The terms "first," "second," "first," or "second" as used in the various embodiments of this disclosure may modify various components regardless of their order and / or importance, but these terms do not limit the corresponding components. The above terms are configured only for the purpose of distinguishing an element from other elements. For example, "first user equipment" and "second user equipment" refer to different user equipments, although both are user equipment. For example, without departing from the scope of this disclosure, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element.

[0099] When a component (e.g., a first component) is referred to as being "(operably or communicatively) coupled" or "(operably or communicatively) coupled to" or "connected to" another component (e.g., a second component), it should be understood that the first component is directly connected to the second component or that the first component is indirectly connected to the second component via yet another component (e.g., a third component). Conversely, it can be understood that when a component (e.g., a first component) is referred to as being "directly connected" or "directly coupled" to another component (the second component), no component (e.g., a third component) is inserted between the two.

[0100] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0101] The above description is merely an optional embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this application.

[0102] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0103] The above description is merely an optional embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this application.

[0104] The above description is merely an optional embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An apparatus for endoscopic video image processing based on AIGC, characterized in that, The system includes an endoscope handle, a main unit processor, a light source driving module, and a display. The endoscope handle has an endoscope probe at its end for acquiring detection frames of target living tissue. The main unit processor is connected to the endoscope handle via a transmission optical fiber and receives the detection frames. The main unit processor is also electrically connected to the display and the light source driving module, which is connected to the endoscope handle via a light source transmission optical fiber to provide illumination to the endoscope handle. The main unit processor is configured to perform the following steps: S10: In response to the recording operation, store the frame images fed back by the endoscope probe in the temporary library; S20: Under the first preset condition, discard some frames in the temporary library that meet the second preset condition according to the first preset rule; S30: Generate the target video file based on the remaining frames in the temporary library; The condition of satisfying the first preset condition includes at least one of the following: the current remaining memory is lower than a preset memory threshold; The current remaining storage space is lower than the preset space threshold; The first preset rule includes: the number of discarded frames increases with the length of recording time; some frames are discarded periodically over time; and the discarding period shortens with the length of recording time. The second preset condition includes at least one of the following: a frame with a viewing angle range smaller than the first requirement; or a frame with a viewing angle range larger than the first requirement. When the viewing angle is less than the first requirement, the corresponding frame only includes a partial view of the target object; when the viewing angle is greater than the first requirement, the corresponding frame includes the overall image of the target object. The host processor is also configured to perform step S40: generating a three-dimensional model of the target object by means of AIGC based on frames with a viewing angle range smaller than the first requirement.

2. The apparatus for the endoscopic video image processing method based on AIGC according to claim 1, characterized in that, Between steps S20 and S30, the host processor is further configured to perform step S200: generate supplementary frame images according to a second preset rule and insert them into the temporary library to fill the deleted frame images.

3. The apparatus for the endoscopic video image processing method based on AIGC according to claim 1, characterized in that, The second preset rule includes at least one of the following: Copy the previous or next frame as a supplementary frame. AIGC technology is used to generate intermediate supplementary frames based on the content of the previous and next frames.

Images