Endoscope imaging control method and related product

Abstract

The invention provides an endoscope imaging control method and a related product. The method comprises the steps that in an automatic dimming mode, in response to a switching instruction for switching a current imaging mode to a target imaging mode, first model dimming parameters of an endoscope system in the current imaging mode are obtained, and the parameters are at least part of dimming parameters in current dimming parameters; the model input information is input into a parameter prediction model to predict and obtain second model dimming parameters in the target imaging mode, target dimming parameters are obtained based on the parameters, and the second model dimming parameters are at least part of dimming parameters in the target dimming parameters; the model input information comprises a current imaging mode, a first model dimming parameter and a target imaging mode, and the target dimming parameter is used for enabling a difference value between image brightness in the target imaging mode and target image brightness to be within a preset range; and controlling the endoscope system to switch the current dimming parameter into the target dimming parameter. The scheme can effectively improve the problem of image dithering.

Description

Technical Field

[0001] This application relates to the field of endoscope technology, specifically to an endoscope imaging control method, endoscope system, endoscope device, storage medium, and computer program product. Background Technology

[0002] With the continuous development of endoscopic technology, endoscopic examinations and treatments are becoming increasingly widespread. For example, colonoscopy is one of the important techniques for diagnosing and treating lower gastrointestinal diseases such as colorectal polyps and tumors.

[0003] During endoscopic examinations, endoscopic images can be acquired in real time for observation. In related technologies, endoscopic systems typically have an automatic dimming function. In automatic dimming mode, the endoscopic system can automatically adjust the image brightness to match the target image brightness when there is a significant difference between the image brightness and the target image brightness. Endoscopic systems can also have various imaging modes. The illumination spectrum and image processing parameters differ between these modes, leading to variations in the brightness of the acquired endoscopic images. Switching between imaging modes while in automatic dimming mode can easily cause fluctuations in image brightness, resulting in image jitter. Summary of the Invention

[0004] This application is made in consideration of the above-mentioned problems. This application provides an endoscopic imaging control method, apparatus, endoscopic system, endoscopic device, storage medium, and computer program product. This solution can effectively improve the image jitter problem caused by switching imaging modes in automatic dimming mode.

[0005] According to one aspect of this application, an endoscopic imaging control method is provided for an endoscopic system; the method includes: in an automatic dimming mode, in response to a switching command to switch the current imaging mode to a target imaging mode, performing the following imaging control operations: acquiring first model dimming parameters of the endoscopic system in the current imaging mode, wherein the first model dimming parameters are at least a portion of the dimming parameters in the current dimming parameters; inputting model input information into a parameter prediction model to perform parameter prediction, thereby predicting and obtaining second model dimming parameters of the endoscopic system in the target imaging mode, and obtaining target dimming parameters based on the second model dimming parameters. The second model dimming parameter is at least a portion of the target dimming parameter. The model input information includes the current imaging mode, the first model dimming parameter, and the target imaging mode. The current dimming parameter and the target dimming parameter are parameters that can adjust the image brightness of the image acquired by the endoscope system. The target dimming parameter is used to ensure that the difference between the image brightness of the image acquired by the endoscope system in the target imaging mode and the target image brightness is within a preset range. The target image brightness and the preset range are the reference for the endoscope system to perform automatic dimming. The endoscope system is controlled to switch the current dimming parameter to the target dimming parameter.

[0006] For example, the first model dimming parameters include the current exposure time, current gain, and current drive value of the endoscope system, where the current drive value corresponds to the drive value of at least some of the light sources illuminated in the current imaging mode; the second model dimming parameters include the target exposure time, target gain, and target drive value of the endoscope system, where the target drive value corresponds to the drive value of at least some of the light sources illuminated in the target imaging mode.

[0007] For example, the target driving value is the driving value corresponding to the reference light source illuminated in the target imaging mode; obtaining the target dimming parameter based on the second model dimming parameter includes: determining the driving value corresponding to each of the non-reference light sources (excluding the reference light source) illuminated in the target imaging mode based on the target driving value and the emission ratio among the light sources illuminated in the target imaging mode; wherein, the target dimming parameter includes the second model dimming parameter and the driving value corresponding to each of the non-reference light sources.

[0008] For example, the reference light source is one or more of the light sources that need to be lit in both the current imaging mode and the target imaging mode; the current driving value is the driving value corresponding to the reference light source lit in the current imaging mode.

[0009] For example, the model input information also includes the target image brightness. Inputting the model input information into a parameter prediction model to perform parameter prediction in order to predict and obtain the second model dimming parameters of the endoscope system in the target imaging mode includes: inputting the model input information into a unified parameter prediction model to perform parameter prediction in order to predict and obtain the second model dimming parameters.

[0010] For example, different parameter prediction models are preset for different endoscope types and / or different target image brightness. Before inputting the model input information into the parameter prediction model to perform parameter prediction in order to predict the second model dimming parameters of the endoscope system in the target imaging mode, the imaging control operation further includes: acquiring the parameter prediction model corresponding to the target image brightness and / or the endoscope type of the endoscope system; inputting the model input information into the parameter prediction model to perform parameter prediction in order to predict the second model dimming parameters of the endoscope system in the target imaging mode, including: inputting the model input information into the parameter prediction model corresponding to the target image brightness and / or the endoscope type of the endoscope system to perform parameter prediction in order to predict the second model dimming parameters.

[0011] For example, the parameter prediction model is constructed based on a preset mapping relationship. The preset mapping relationship is used to represent the correspondence between the observation distance, the target image brightness, and the model dimming parameters corresponding to each imaging mode. The observation distance is the distance between the endoscope system and the target object. In the preset mapping relationship, the model dimming parameters corresponding to each imaging mode are the dimming parameters used when the difference between the image brightness of the image acquired by the endoscope system in that imaging mode and the corresponding target image brightness is within a preset range at the corresponding observation distance.

[0012] For example, the parameter prediction model is obtained through the following operations: for each of a variety of preset observation distances, the endoscope system is controlled to image under various imaging modes, and the model dimming parameters corresponding to the difference between the brightness of the acquired image and the brightness of each target image under each imaging mode are recorded, so as to determine the correspondence between the model dimming parameters corresponding to each imaging mode under the same preset observation distance and the same target image brightness; wherein, the various imaging modes include the current imaging mode and the target imaging mode; based on the correspondence between the model dimming parameters corresponding to each imaging mode, polynomial fitting is performed to obtain the parameter prediction model.

[0013] For example, a polynomial fitting is performed based on the correspondence between the model dimming parameters corresponding to each imaging mode to obtain a parameter prediction model. This includes: performing a polynomial fitting based on the correspondence between the model dimming parameters corresponding to each imaging mode under various different target image brightnesses and various different preset viewing distances to obtain a unified parameter prediction model; or, for each target image brightness among various different target image brightnesses, performing a polynomial fitting based on the correspondence between the target image brightness and the model dimming parameters corresponding to each imaging mode under various different preset viewing distances to obtain a parameter prediction model corresponding to the target image brightness.

[0014] According to another aspect of this application, an endoscope system is provided, comprising: an illumination device, an endoscope body, a light source processor, an image processor, a display, and a controller; the illumination device includes a light source; the light source processor controls the light source in the illumination device to emit light towards a target object; an image acquisition device is disposed on the endoscope body to receive light reflected from the target object and generate an image signal; the image processor is connected to the image acquisition device of the endoscope body to receive the image signal and generate an endoscope image based on the image signal; the display is connected to the image processor to display the endoscope image; and the controller is connected to the light source processor and the image processor respectively to execute the aforementioned endoscope imaging control method.

[0015] According to another aspect of this application, an endoscope device is provided, including a processor and a memory, wherein computer program instructions are stored in the memory, and the computer program instructions are executed by the processor to perform the above-described endoscope imaging control method.

[0016] According to another aspect of this application, a storage medium is provided on which program instructions are stored, which are used to execute the above-described endoscopic imaging control method when running.

[0017] According to another aspect of this application, a computer program product is provided, comprising computer program instructions, characterized in that the computer program instructions are used to execute the above-described endoscopic imaging control method when running.

[0018] In the above technical solution, under automatic dimming mode, the target dimming parameter corresponding to the target imaging mode is determined based on the current imaging mode, the current dimming parameter and the target imaging mode. The target dimming parameter enables the image brightness of the image acquired by the endoscope system in the target imaging mode to be maintained near the target image brightness before the mode switch. This allows the image brightness corresponding to the imaging mode of the endoscope system to remain stable before and after the imaging mode switch, and does not trigger the endoscope system to perform automatic dimming due to the imaging mode switch, thereby effectively improving the image jitter problem caused by the imaging mode switch.

[0019] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0020] The following drawings, which are incorporated herein by reference and are used to understand this application, illustrate embodiments of the invention and their descriptions to explain the principles of the invention. In the drawings,

[0021] Figure 1An exemplary flowchart of imaging control operation according to an embodiment of the present invention is shown;

[0022] Figure 2 A schematic block diagram of an endoscopic imaging control device according to an embodiment of this application is shown; and

[0023] Figure 3 A schematic block diagram of an endoscope device according to one embodiment of this application is shown. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application more apparent, exemplary embodiments according to this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of this application, and not all of the embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein. Based on the embodiments described in this application, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of this application.

[0025] In related technologies, to ensure optimal image brightness in endoscopic images, some endoscopic systems are equipped with an automatic dimming function. This function automatically adjusts dimming parameters such as light intensity, exposure time, and gain when the current image brightness differs significantly from the target image brightness, keeping the image brightness close to the target level. Furthermore, due to differences in illumination spectra and image processing parameters across different imaging modes, the image brightness of endoscopic images acquired before and after mode switching may vary significantly. Therefore, when switching imaging modes in automatic dimming mode, the image typically darkens or brightens noticeably. Based on this, the endoscopic system triggers automatic dimming, automatically and gradually adjusting the image brightness to the target level. Consequently, during mode switching, brightness fluctuations often occur, with the image brightness initially darkening and then brightening, or vice versa. When the brightness change before and after mode switching is excessive, even oscillating brightness fluctuations may occur during automatic dimming.

[0026] To at least partially solve the aforementioned technical problems, embodiments of the present invention provide an endoscopic imaging control method for use in an endoscope system. When the endoscope system switches from a current imaging mode to a target imaging mode, it can acquire at least a portion of the current dimming parameters (i.e., first model dimming parameters) from the current dimming parameters in the current imaging mode, such as exposure time, gain, and the driving value of the reference light source in the current imaging mode. The first model dimming parameters, the current imaging mode, and the target imaging mode are then used in an input parameter prediction model to calculate a second model dimming parameter for the target imaging mode to be switched to, such as exposure time, gain, and the driving value of the reference light source in the target imaging mode. The target dimming parameter is then obtained through the second model dimming parameter. Subsequently, the current dimming parameters can be replaced with the target dimming parameter corresponding to the target imaging mode to be switched to. The target dimming parameter ensures that the image brightness of the endoscope image acquired by the endoscope system in the target imaging mode remains substantially consistent with the image brightness of the endoscope image acquired in the current imaging mode using the current dimming parameter. This avoids screen flickering caused by changes in image brightness during the switching of imaging modes while the automatic dimming mode is running, thus preventing image jitter.

[0027] The endoscopic system described herein may include an endoscope body, an illumination device, a light source processor, an image processor, a controller (or main processor), and a display. The illumination device may be connected to the endoscope body or mounted on it. The illumination device may include a light source; the light source processor controls the light source in the illumination device to emit light towards the target object; the endoscope body is equipped with an image acquisition device to receive light reflected from the target object and generate an image signal; the image processor is connected to the image acquisition device on the endoscope body to receive the image signal and generate an endoscopic image based on the image signal; the display is connected to the image processor to display the endoscopic image; the controller is connected to both the light source processor and the image processor to execute the endoscopic imaging control method described herein.

[0028] The endpiece (i.e., the end that extends into the body cavity) can be equipped with an observation window and an illumination window. Illumination light emitted from the light source is transmitted to the illumination window via a light guide device connected to the light source within the endpiece to illuminate the target object. Light reflected from the target object can enter the objective lens optical system through the observation window and be imaged onto an image sensor. The image signal generated by the image sensor can then be transmitted back to the image processor. Exemplarily, when the endpiece is connected to the illumination device via an integrated connector, the image signal is first transmitted to the illumination device and then sent to the image processor. In other embodiments, the endpiece can also be connected to the illumination device and the image processor separately via separate connectors. In this case, the image signal can be directly transmitted from the endpiece to the image processor. A controller can be connected to both the light source processor and the image processor to execute the aforementioned endoscopic imaging control method. The controller can control the light source to emit light according to the driving value via the light source processor, and can also control the exposure time and gain during imaging via the image processor. An image acquisition device can be provided on the endpiece. The image acquisition device can include components such as an imaging objective lens and an image sensor. The imaging objective lens can be located at the endpiece. The image acquisition device can acquire static endoscopic images or dynamic videos of the target object, where the video contains multiple consecutive endoscopic images. The target object can include any biological cavity suitable for endoscopic examination, such as the digestive tract, bronchus, and pancreatic duct. The light source processor can be used to control the illumination device to emit corresponding illumination light according to the selected illumination mode (each imaging mode has a corresponding illumination mode). The illumination light is led out to the endoscope tip through a light guide device in the endoscope body, and the image acquisition device receives the light reflected from the target object and generates an image signal. The image processor processes the image signal to generate an endoscopic image. The display is used to display the endoscopic image processed by the image processor. The controller can be connected to the light source processor and the image processor respectively to perform overall control of the light source processor and the image processor. The operating part of the endoscope body can be equipped with a switch for the doctor to operate to switch the imaging mode during the endoscopic examination. When switching imaging modes, the illumination device changes the current illumination mode accordingly (e.g., changing the light source to be lit and / or the emission ratio between the light sources), and the image processor changes the image processing method accordingly. Furthermore, it is understood that this application does not limit the method of triggering the switching of imaging modes. For example, the imaging mode switching command that triggers the switching of imaging modes can be input by the user or can be automatically generated when the AI ​​model determines that there may be a lesion site.

[0029] For example, the endoscopic imaging control method described herein can be applied to an endoscopic system. The endoscopic imaging control method can be specifically executed by a controller within the endoscopic system. Endoscopic systems may include, but are not limited to, gastroscopes, colonoscopes, laparoscopes, and bronchoscopes. Endoscopic systems can be used to examine lesions such as inflammation, ulcers, and tumors in cavities of the digestive tract and liver, gallbladder, and pancreas ducts.

[0030] The endoscopic imaging control method includes: in automatic dimming mode, performing an imaging control operation in response to a switching command to switch the current imaging mode to a target imaging mode. For example, the endoscopic system can switch the current imaging mode to the target imaging mode upon receiving an imaging mode switching command. Figure 1 An exemplary flowchart of imaging control operations according to an embodiment of the present invention is shown. Figure 1 As shown, the imaging control operation may include, but is not limited to, steps S110, S120 and S130.

[0031] In step S110, the first model dimming parameters of the endoscope system in the current imaging mode are obtained. The first model dimming parameters are at least a portion of the dimming parameters in the current dimming parameters.

[0032] An endoscopic system can perform imaging based on dimming parameters. Dimming parameters are parameters that can adjust the brightness of the image acquired by the endoscopic system. Current dimming parameters refer to the dimming parameters in the current imaging mode. Similarly, target dimming parameters refer to the dimming parameters in the target imaging mode. For example, the dimming parameters described herein may include one or more of the exposure time, gain, and drive value corresponding to the light source to be illuminated used by the endoscopic system during imaging. It is understood that gain refers to the gain of the image sensor in the endoscopic system. The drive value of the light source may include one or more of the drive voltage, drive current, and drive power of the light source. It is understood that by changing the drive value of the light source, the luminous intensity of the light source can be changed. The imaging modes of the endoscopic system may include various types. Different imaging modes correspond to different illumination modes, such as white light mode (WL), enhanced white light mode (EWL), excitation light mode (emitting excitation light for fluorescence imaging), special light modes, etc. Each lighting mode has its own corresponding illumination spectrum. For any two different lighting modes, the light sources required to illuminate the corresponding illumination spectrum are different, and / or the luminous intensities of the same light source required to illuminate the corresponding illumination spectrum are different. The following uses white light mode and enhanced white light mode as examples. For instance, in white light mode, red, green, and blue lights are illuminated; in enhanced white light mode, UV lights, green, red, and blue lights are illuminated. That is to say, the light sources corresponding to white light mode and enhanced white light mode are different; green, red, and blue lights are light sources that need to be illuminated in both lighting modes.

[0033] For example, the current dimming parameter may include one or more of the following parameters of the endoscope system in the current imaging mode: current exposure time; current gain; and drive values ​​corresponding to each light source illuminated in the current imaging mode. The target dimming parameter may include one or more of the following parameters of the endoscope system in the target imaging mode: target exposure time; target gain; and drive values ​​corresponding to each light source illuminated in the target imaging mode. The model dimming parameter may include at least some dimming parameters, that is, the model dimming parameter used to input the parameter prediction model (i.e., the first model dimming parameter) and the model dimming parameter that can be predicted by the parameter prediction model (i.e., the second model dimming parameter) may both be at least some of the corresponding dimming parameters. For example, the target dimming parameter may include the exposure time, gain, and drive values ​​corresponding to each light source illuminated when the endoscope system is imaging in the target imaging mode, and the second model dimming parameter may include the exposure time, gain, and drive values ​​corresponding to the reference light source illuminated when the endoscope system is imaging in the target imaging mode, and the drive values ​​corresponding to other non-reference light sources may be calculated based on the drive values ​​corresponding to the reference light source. A parameter prediction model can be pre-established to predict the model dimming parameters corresponding to each imaging mode, and the corresponding model dimming parameters for each imaging mode can be determined based on the parameter prediction model. For example, the parameter prediction model can be a neural network model, such as by training the neural network model with imaging modes related to the target image brightness and the corresponding model dimming parameters as sample data. Alternatively, the parameter prediction model can be a preset data association table or preset transformation formula built based on a preset mapping relationship. For example, imaging modes related to the target image brightness and the corresponding model dimming parameters can be pre-collected, and a preset data association table or preset transformation formula can be established based on the correspondence between the target image brightness, imaging mode, and model dimming parameters, so that the corresponding second model dimming parameter can be found in the preset data association table or calculated based on the preset transformation formula according to the target imaging mode.

[0034] The first model dimming parameters obtained in step S110 can be a portion of the dimming parameters in the current dimming parameters of the current imaging mode, or all of the dimming parameters in the current dimming parameters. For example, the first model dimming parameters can include the drive values ​​corresponding to some of the light sources illuminated by the endoscope system when imaging in the current imaging mode, or the exposure time, gain, and drive values ​​corresponding to some of the light sources illuminated by the endoscope system when imaging in the current imaging mode, or the exposure time, gain, and drive values ​​corresponding to all the light sources illuminated by the endoscope system when imaging in the current imaging mode, and so on.

[0035] In step S120, the model input information is input into the parameter prediction model for parameter prediction to predict and obtain the second model dimming parameters of the endoscope system in the target imaging mode, and the target dimming parameters are obtained based on the second model dimming parameters. The second model dimming parameters are at least a part of the dimming parameters in the target dimming parameters. The model input information includes the current imaging mode, the first model dimming parameters, and the target imaging mode. The current dimming parameters and the target dimming parameters are parameters that can adjust the image brightness of the image acquired by the endoscope system. The target dimming parameters are used to ensure that the difference between the image brightness of the image acquired by the endoscope system in the target imaging mode and the target image brightness is within a preset range. The target image brightness and the preset range are the reference for the endoscope system to perform automatic dimming.

[0036] The target image brightness and the preset range serve as the benchmark for the endoscope system's current automatic dimming. In other words, in automatic dimming mode, when the difference between the brightness of the acquired image and the target image exceeds a preset range, the endoscope system automatically adjusts its dimming parameters until the difference is within the preset range. The preset range can be set to any brightness value range as needed. For example, the phrase "the difference between the acquired image brightness and the target image brightness is within the preset range" can mean that the difference is less than a preset difference (which can be called the first preset difference). The size of the first preset difference can be set to any size as needed. Using the current dimming parameters in the current imaging mode, the endoscope system can make the acquired image brightness reach or substantially reach the target image brightness. Through a parameter prediction model, at least some of the dimming parameters (i.e., the target dimming parameters) required to make the acquired image brightness also reach or substantially reach the target image brightness in the target imaging mode can be obtained. In other words, the current dimming parameters are used to ensure that the difference between the image brightness of the image acquired by the endoscope system in the current imaging mode and the target image brightness is within a preset range. The target dimming parameters are used to ensure that the difference between the image brightness of the image acquired by the endoscope system in the target imaging mode and the target image brightness is within a preset range. The target image brightness is a known quantity for the endoscope system. In some embodiments, the target image brightness may optionally be included as part of the model input information and input into the parameter prediction model for prediction. The second model dimming parameters may be a portion of the target dimming parameters in the target imaging mode, or all of the target dimming parameters. For example, the target dimming parameters may include the drive values ​​corresponding to some of the light sources illuminated by the endoscope system when imaging in the target imaging mode, or the exposure time, gain, and drive values ​​corresponding to some of the light sources illuminated by the endoscope system when imaging in the target imaging mode, or the exposure time, gain, and drive values ​​corresponding to all the light sources illuminated by the endoscope system when imaging in the target imaging mode, and so on. When the dimming parameters of the second model are all the dimming parameters in the target dimming parameters, the dimming parameters of the second model obtained through the parameter prediction model are the required target dimming parameters. When the dimming parameters of the second model are only a portion of the dimming parameters in the target dimming parameters, the remaining dimming parameters in the target dimming parameters can be further determined based on the dimming parameters of the second model.

[0037] The parameter prediction model can be any pre-configured algorithmic model capable of predicting model dimming parameters (i.e., second model dimming parameters) under the target imaging mode based on model input information. As mentioned above, for example, the parameter prediction model can be represented by a neural network model, obtained by training an initial neural network model, or it can be represented by a preset data association table or a preset transformation formula. The preset data association table or preset transformation formula can express the correspondence between each imaging mode and dimming parameter, so that, given at least the current imaging mode, the first model dimming parameter, and the target imaging mode, the second model dimming parameter corresponding to the target imaging mode can be calculated.

[0038] In step S130, the endoscope system is controlled to switch the current dimming parameter to the target dimming parameter.

[0039] The execution order between step S130 and other steps involved in the imaging mode switching process (such as switching the illumination spectrum, switching image processing parameters, etc.) can be set as needed, and this application does not impose any restrictions on this. For example, step S130 and other steps involved in the imaging mode switching process can be executed synchronously or in any order. It is preferable to execute step S130 while switching the illumination spectrum, for example, by adjusting the driving values ​​of each light source so that the switched light source can simultaneously meet the brightness and spectral requirements. The controller of the endoscope system can control the various components of the endoscope system to switch from the current dimming parameters to the target dimming parameters. For example, when the controller receives the imaging mode switching command, it can first determine the current illumination mode of the light source processor and the illumination mode to be switched to. Next, obtain the dimming parameters (i.e., the current dimming parameters) in the current imaging mode, such as the drive value, exposure time, and gain of at least one current light source illuminated in the current imaging mode. These parameters can be defined as L0, G0, and T0, respectively. Then, import these parameters into the parameter prediction model to calculate the drive value, exposure time, and gain of each light source in the switched illumination mode. These parameters are defined as L1, G1, and T1. Finally, replace the L1, G1, and T1 parameters of the current illumination mode with the L0, G0, and T0 parameters of the switched illumination mode.

[0040] According to the endoscopic imaging control method of the present invention, in automatic dimming mode, a target dimming parameter corresponding to the target imaging mode is determined based on the current imaging mode, the current dimming parameter, and the target imaging mode. The target dimming parameter enables the image brightness of the image acquired by the endoscopic system in the target imaging mode to be maintained near the target image brightness before the mode switch. This allows the image brightness corresponding to the imaging mode of the endoscopic system to remain stable before and after the imaging mode switch, and prevents the endoscopic system from executing automatic dimming due to the imaging mode switch, thereby effectively improving the image jitter problem caused by the imaging mode switch.

[0041] According to an embodiment of the present invention, the first model dimming parameters include the current exposure time, current gain, and current drive value of the endoscope system, wherein the current drive value is the drive value corresponding to at least a portion of the light sources illuminated in the current imaging mode; the second model dimming parameters include the target exposure time, target gain, and target drive value of the endoscope system, wherein the target drive value is the drive value corresponding to at least a portion of the light sources illuminated in the target imaging mode.

[0042] In one embodiment, the "light control value" B1 = L1 * K1 after switching can be determined based on the light control value (i.e., the driving value of the light source) L1 of the imaging mode before switching, and the standard light ratio K1 between the light control values ​​corresponding to different imaging modes before and after switching (the standard value of the light control value corresponding to the imaging mode after switching / the standard value of the light control value corresponding to the imaging mode before switching). This scheme can improve the image jitter problem to a certain extent, but the effect still needs to be improved. Research and analysis have found that the above scheme only considers the influence of light quantity on the overall image brightness, but does not consider the influence of exposure time and gain on the overall image brightness. In practical applications, image brightness is determined by the parameter values ​​of exposure time, illumination light quantity, and gain. Changes in any of these parameters may have a significant impact on image brightness. Therefore, for example, the first model dimming parameters and the second model dimming parameters can include exposure time and gain in addition to the driving value of the light source. This comprehensively considers the parameters affecting image brightness. By having these three parameters participate in the adjustment of the dimming parameters simultaneously, the control accuracy of image brightness can be further improved, thereby helping to further reduce image jitter.

[0043] Optionally, the current drive value in the first model dimming parameters described in this paper can also be replaced with the current light intensity value of the light source (i.e., the total light output of the light source illuminated in the current imaging mode). Based on the current light intensity value of the light source, the target light intensity value of the light source illuminated in the target imaging mode can be determined. After determining the target light intensity value, the drive value of each light source can be determined by combining the light power ratio (i.e., emission ratio) between the light sources illuminated in the target imaging mode. This method of calculating the drive value from the light intensity value is relatively cumbersome. However, directly using the current drive value as part of the first model dimming parameters can more directly and efficiently determine the target dimming parameters, saving the derivation process between the intermediate light intensity value and the drive value.

[0044] According to an embodiment of the present invention, the target driving value is the driving value corresponding to the reference light source illuminated in the target imaging mode; obtaining the target dimming parameter based on the second model dimming parameter includes: determining the driving value corresponding to each of the non-reference light sources (excluding the reference light source) illuminated in the target imaging mode based on the target driving value and the emission ratio among the light sources illuminated in the target imaging mode; wherein, the target dimming parameter includes the second model dimming parameter and the driving value corresponding to each of the non-reference light sources.

[0045] In different imaging modes, the light sources satisfy different light power ratios (i.e., emission ratios). For example, in imaging mode 1, the emission ratio of the three lights (A, B, and C) is 1:1:1; in imaging mode 2, the emission ratio of the three lights (A, B, and C) is 1:1:0 (i.e., light C is off); and in imaging mode 3, the emission ratio of the three lights (A, B, and C) is 0:1:0.5 (i.e., light A is off). Therefore, a reference light source can be set for each imaging mode. For example, a light source that needs to be lit in all lighting modes can be used as the reference light source. The driving value of the reference light source can be used as the light source setting parameter in the dimming parameters of the above model. Then, the driving value of other non-reference light sources can be directly calculated from the driving value of the reference light source.

[0046] When switching imaging modes, light sources that need to be lit both before and after the switch (referred to as common light sources) do not need to be turned off and then on again. The drive values ​​of other non-reference light sources can be calculated based on the drive values ​​of the reference light sources in the target imaging mode. For example, when switching from a special light mode to an enhanced white light mode, the green and UV lamps, as common light sources, do not need to be turned off. The green lamp serves as the reference light source, and the red and blue lamps also need to be lit when switching from the special light mode to the enhanced white light mode. In this case, the exposure time, gain, and green lamp drive value in the special light mode can be obtained and imported into the parameter prediction model to calculate the exposure time, gain, and green lamp drive value in the enhanced white light mode. Then, based on the green lamp drive value in the enhanced white light mode, the drive values ​​of the red, blue, and UV lamps can be calculated. Finally, all dimming parameters are updated to the exposure time, gain, and drive values ​​of the light sources in the enhanced white light mode, and the settings are updated in the registers.

[0047] The above method allows for the estimation of driving values ​​for non-reference light sources based on the driving values ​​of the reference light source. This reduces the number of parameters that the parametric prediction model needs to predict and improves prediction efficiency.

[0048] According to an embodiment of the present invention, the reference light source is one or more of the light sources that need to be lit in both the current imaging mode and the target imaging mode; the current driving value is the driving value corresponding to the reference light source lit in the current imaging mode.

[0049] For example, all or part of the common light sources in the current imaging mode and the target imaging mode can be used as the reference light source. For instance, the illumination mode corresponding to the current imaging mode could be a white light mode, in which red, green, and blue lights are illuminated; the illumination mode corresponding to the target imaging mode could be an enhanced white light mode, in which UV, green, red, and blue lights are illuminated. In this case, the green, red, and blue lights can be used as the reference light sources. The first model dimming parameters include the driving values ​​of all the light sources illuminated in the current imaging mode, and the second model dimming parameters include the driving values ​​of some of the light sources illuminated in the target imaging mode. More specifically, the common light sources of all imaging modes of the endoscope system can be used as the reference light source. For example, the endoscope system can have three imaging modes, corresponding to three illumination modes: white light mode, enhanced white light mode, and special light mode. The common light source for the three imaging modes is the green light, meaning the green light needs to be illuminated in each mode. The UV, blue, and red lights can be used as complementary light sources, selectively illuminated according to the different imaging modes. Therefore, the green light can be used as the reference light source for each imaging mode.

[0050] Since the emission ratio of each light source in the same imaging mode can be known, the driving values ​​of other non-reference light sources can be determined by using the driving value of the reference light source. This approach reduces the number of parameters in the model's dimming parameters involved in the prediction, thereby further improving parameter prediction efficiency.

[0051] According to an embodiment of the present invention, the model input information further includes the target image brightness. The model input information is input into a parameter prediction model for parameter prediction to predict and obtain the second model dimming parameters of the endoscope system in the target imaging mode. This includes: inputting the model input information into a unified parameter prediction model for parameter prediction to predict and obtain the second model dimming parameters.

[0052] The parameter prediction model can be a unified model, meaning it can be used for parameter prediction regardless of image brightness. For example, the parameter prediction model could be a single neural network model. In this case, the target image brightness can optionally be included as part of the model input information into the parameter prediction model. This allows the model to comprehensively determine the second model dimming parameters under the target imaging mode based on the target image brightness, the current imaging mode, the first model dimming parameters, and the target imaging mode. It should be noted that the above-described method of inputting the target image brightness into the parameter prediction model is merely an example and not a limitation of the invention. For instance, the image brightness during endoscopic imaging can be fixed and unique, rather than having multiple different image brightnesses. In this case, the specific magnitude of the target image brightness does not need to be known. When constructing the parameter prediction model, it can be manually determined whether the image brightness of the endoscopic image meets a certain brightness requirement. When the image brightness of the endoscopic image is manually determined to meet the brightness requirement (the image brightness at this point is the target image brightness, and the specific brightness value is unknown to the endoscopic system), the imaging mode and model dimming parameters are recorded, and the parameter prediction model is constructed based on the recorded imaging mode and model dimming parameters.

[0053] The unified parameter prediction model has strong predictive power, wide applicability, and high portability, making it suitable for various application scenarios.

[0054] According to an embodiment of the present invention, different parameter prediction models are preset for different endoscope types and / or different target image brightness. Before inputting model input information into the parameter prediction model to predict the second model dimming parameters of the endoscope system in the target imaging mode, the imaging control operation further includes: acquiring a parameter prediction model corresponding to the target image brightness and / or the endoscope type of the endoscope system; inputting model input information into the parameter prediction model to predict the second model dimming parameters of the endoscope system in the target imaging mode, including: inputting model input information into the parameter prediction model corresponding to the target image brightness and / or the endoscope type of the endoscope system to predict the second model dimming parameters.

[0055] For example, different parameter prediction models can be preset for different image brightness levels. That is, a dedicated parameter prediction model can be preset for each image brightness level. For instance, parameter prediction model A can be preset for image brightness L1; parameter prediction model B can be preset for image brightness L2; ​​and parameter prediction model C can be preset for image brightness L3. When it is determined that the target image brightness belongs to image brightness L2, the corresponding parameter prediction model B can be obtained for parameter prediction to determine the dimming parameters of the second model. In this scheme, when inputting the model input information into the parameter prediction model, it is not necessary to input the target image brightness.

[0056] For example, different parameter prediction models can be preset for different lens types. That is, each lens type can have a dedicated parameter prediction model for prediction. For instance, for lens type T1, parameter prediction model D can be preset; for lens type T2, parameter prediction model E can be preset; and for lens type T3, parameter prediction model F can be preset. When it is determined that the target image brightness belongs to image brightness T3, the corresponding parameter prediction model F can be obtained for parameter prediction to determine the dimming parameters of the second model. In this scheme, when inputting the model input information into the parameter prediction model, the target image brightness can be optionally input.

[0057] Optionally, different parameter prediction models can be preset simultaneously for different image brightness and different lens types. For example, parameter prediction model A can be preset for image brightness L1 and lens type T1; parameter prediction model B can be preset for image brightness L2 and lens type T1; parameter prediction model C can be preset for image brightness L3 and lens type T1; parameter prediction model D can be preset for image brightness L1 and lens type T2; parameter prediction model E can be preset for image brightness L2 and lens type T2; parameter prediction model F can be preset for image brightness L3 and lens type T2; parameter prediction model G can be preset for image brightness L1 and lens type T3; parameter prediction model H can be preset for image brightness L2 and lens type T3; and parameter prediction model I can be preset for image brightness L3 and lens type T3. When it is determined that the target image brightness belongs to image brightness L3 and the lens type is lens type T3, the corresponding parameter prediction model I can be obtained to perform parameter prediction to determine the dimming parameters of the second model.

[0058] Different parameter prediction models are preset for different lens types and / or different image brightness. This allows for targeted setting of various parameter prediction models, resulting in more accurate prediction of model dimming parameters in different scenarios.

[0059] According to an embodiment of the present invention, the parameter prediction model is constructed based on a preset mapping relationship. The preset mapping relationship is used to represent the correspondence between the observation distance, the target image brightness, and the model dimming parameters corresponding to each imaging mode. The observation distance is the distance between the endoscope system and the target object. In the preset mapping relationship, the model dimming parameters corresponding to each imaging mode are the dimming parameters used when the difference between the image brightness of the image acquired by the endoscope system in that imaging mode and the corresponding target image brightness is within a preset range at the corresponding observation distance.

[0060] The observation distance is the distance between the endoscope system and the target object. This distance can be represented by the distance between components of the endoscope system, such as the endoscope tip, and the target object. During endoscopic observation, the observation distance is usually variable. The dimming parameters corresponding to the same brightness level (target image brightness) differ at different observation distances. Therefore, the same brightness level and imaging mode can have multiple different standard dimming parameters. However, when switching between two imaging modes, the observation distance is usually constant. Therefore, a preset mapping relationship between the observation distance, imaging mode, and model dimming parameters can be predetermined, and a parameter prediction model can be constructed based on this preset mapping relationship, such as a preset data association table or a preset transformation formula. The preset mapping relationship can optionally include information on one or more target image brightness levels. The target image brightness based on which the second model dimming parameters are predicted in step S120 is one or more target image brightness levels included in the preset mapping relationship. When the target image brightness is a fixed value, or when the target image brightness has multiple different values ​​and different preset mapping relationships are used for different target image brightnesses, the preset mapping relationship does not need to include the target image brightness. When the target image brightness has multiple different values ​​and a uniform preset mapping relationship is used for different values, the preset mapping relationship can include the target image brightness. In this case, the preset mapping relationship can be used to represent the correspondence between viewing distance, target image brightness, imaging mode, and model dimming parameters. The following example illustrates an exemplary method for constructing a preset mapping relationship.

[0061] When determining the preset mapping relationship, commonly used observation distances can be selected in advance based on the actual usage scenario of the endoscope system as the observation distances for data collection. For example, the range of observation distances where the endoscope system can clearly image can be determined first, and then each observation distance for the endoscope system to collect data can be determined according to a preset step size. Model dimming parameters corresponding to different observation distances, different target image brightnesses, and different imaging modes can be collected (i.e., recorded), and a preset data association table "Observation Distance - Target Image Brightness - Imaging Mode - Model Dimming Parameter" can be established to record the preset mapping relationship. For example, this preset data association table can be directly used as a parameter prediction model. Thus, when determining the second model dimming parameter, the second model dimming parameter can be determined by looking up the table based on the currently required target image brightness, the first model dimming parameter, the current imaging mode, and the target imaging mode. Optionally, a parameter prediction model can be further constructed based on the preset mapping relationship recorded in the preset data association table. For example, a preset conversion relationship between the imaging mode and the model dimming parameter can be constructed. In this case, the second model dimming parameter can be calculated based on the preset conversion relationship. The data acquisition process can be as follows: At a certain observation distance, for the brightness of a target image, determine the model dimming parameters under one imaging mode when the difference between the image brightness and the target image brightness is within a preset range. Then, switch to another imaging mode, wait for dimming to stabilize, record the model dimming parameters under this imaging mode when the difference between the image brightness and the target image brightness is within the preset range, and establish a correspondence with the model dimming parameters of the imaging mode before switching, and so on. For example, based on the data in the preset data association table mentioned above, perform polynomial fitting to obtain the preset conversion relationship between different imaging modes and the model dimming parameters of different imaging modes. In other words, the principle of constructing the parameter prediction model can be to collect the LGT values ​​(LGT = AGC + ALC + AEC) of the brightness of each target image at various observation distances and under various imaging modes, compile these data into a table of the relationship between imaging modes and model dimming parameters, and then use a polynomial function model to fit these data to deduce the parameter prediction model. AEC adjusts the exposure time; the longer the exposure time, the more light energy is irradiated to the pixels of the image sensor, and the higher the image brightness. ALC controls the amount of light emitted from the light source, for example, by controlling the current; the greater the current, the greater the light output and the brighter the image. AGC adjusts the gain of the image sensor's output signal; the higher the AGC, the higher the image signal amplification level and the brighter the image.

[0062] Using the above approach, a parameter prediction model can be constructed based on a preset mapping relationship. This model construction method has advantages such as fast computation speed, which helps to improve the speed of imaging mode switching. In addition, the preset mapping relationship takes into account the observation distance, which helps to improve the accuracy of parameter prediction.

[0063] According to an embodiment of the present invention, the parameter prediction model is obtained through the following operations: for each of a variety of preset observation distances, the endoscope system is controlled to image under various imaging modes, and the model dimming parameters corresponding to the difference between the brightness of the acquired image and the brightness of each target image under each imaging mode are recorded respectively, so as to determine the correspondence between the model dimming parameters corresponding to each imaging mode under the same preset observation distance and the same target image brightness; wherein, the various imaging modes include the current imaging mode and the target imaging mode; based on the correspondence between the model dimming parameters corresponding to each imaging mode, polynomial fitting is performed to obtain the parameter prediction model.

[0064] The exemplary fitting method of polynomial fitting has been described above and will not be repeated here. In this embodiment, the brightness of the target image is also taken into account when constructing the parameter prediction model. This allows the constructed parameter prediction model to cope with scenes under various target image brightness conditions, thus broadening the application range of the endoscopic imaging control method.

[0065] For example, a polynomial fitting is performed based on the correspondence between the model dimming parameters corresponding to each imaging mode to obtain a parameter prediction model. This includes: performing a polynomial fitting based on the correspondence between the model dimming parameters corresponding to each imaging mode under various different target image brightnesses and various different preset viewing distances to obtain a unified parameter prediction model; or, for each target image brightness among various different target image brightnesses, performing a polynomial fitting based on the correspondence between the target image brightness and the model dimming parameters corresponding to each imaging mode under various different preset viewing distances to obtain a parameter prediction model corresponding to the target image brightness.

[0066] Table 1. Preset data association table for recording the mapping relationship between observation distance, target image brightness, and model dimming parameters corresponding to each imaging mode.

[0067]

[0068] Referring to Table 1 above, an example of a preset data association table is shown for recording the mapping relationship between observation distance, target image brightness, and model dimming parameters corresponding to each imaging mode. As shown in the table above, for each preset distance D1, D2...Dn, the model dimming parameters of each imaging mode can be obtained when the target image brightness is set to L1, L2, L3...Lm, thereby obtaining the correspondence between the model dimming parameters of each imaging mode under the same observation distance and the same target image brightness, for example: A11-B11-C11, A12-B12-C12, A13-B13-C13, A21-B21-C21, A22-B22-C22, A23-B23-C23...Anm-Bnm-Cnm, etc. Since the observation distance and target image brightness usually remain unchanged before and after switching imaging modes, based on the aforementioned preset data association table, the model dimming parameters of other imaging modes can be directly derived from the model dimming parameters of one imaging mode. For example, B11 or C11 can be directly derived from A11. However, due to limited test data, to meet broader usage needs, polynomial fitting can be performed based on the correspondences of A11-B11-C11, A12-B12-C12, A13-B13-C13, A21-B21-C21, A22-B22-C22, and A23-B23-C23…Anm-Bnm-Cnm, etc., to obtain formulas for the mutual conversion between model dimming parameters of any two imaging modes (A, B, and C) under various target image brightness levels. Examples include the conversion relationships of AB, AC, and BC (i.e., preset conversion relationships).

[0069] Considering that the brightness of the target image can be known when switching imaging modes, in order to improve prediction accuracy, a corresponding parameter prediction model can be constructed for each target image brightness. That is, the parameter prediction model corresponding to the brightness of the target image can be constructed by using the correspondence between the model dimming parameters of each imaging mode corresponding to the same target image brightness. For example, the parameter prediction model corresponding to the target image brightness L1 can be constructed based on the correspondences A11-B11-C11, A21-B21-C21, A31-B31-C31, ..., An1-Bn1-Cn1. This yields the formulas for mutual conversion between the model dimming parameters of any two imaging modes A, B, and C under the target image brightness L1, such as the conversion relationship of AB, AC, and BC (i.e., the preset conversion relationship).

[0070] The above approach allows for polynomial fitting based on different data to obtain either a unified parameter prediction model or a targeted parameter prediction model corresponding to the brightness of each target image. This polynomial fitting method is computationally simple and supports a wide range of parameters when inputting the dimming parameters of the first model. Furthermore, the unified parameter prediction model offers strong predictive power, wide applicability, and high portability, making it suitable for various application scenarios. Conversely, using a targeted parameter prediction model corresponding to the brightness of each target image helps improve prediction speed and accuracy.

[0071] According to an embodiment of the present invention, the method further includes: when the difference between the image brightness of the image acquired by the endoscope in the current imaging mode and the target image brightness is greater than a preset difference, controlling the endoscope system to switch from the current imaging mode to the target imaging mode.

[0072] The preset difference (in this embodiment, the preset difference can be referred to as the second preset difference) can be set as needed, and it can be any suitable value. For example, the second preset difference can be greater than the first preset difference. During the imaging process of the endoscopic system, the difference between the current image brightness and the target image brightness can be determined in real time based on the acquired endoscopic image. If this difference is greater than the second preset difference, the imaging mode can be automatically switched. For example, when the difference between the image brightness of the image acquired in the current imaging mode and the target image brightness is greater than the second preset difference, an imaging mode switching command can be generated to control the various components of the endoscopic system to adjust their working modes, switching from the current imaging mode to the target imaging mode. Using this approach, the imaging mode can be automatically switched when conventional brightness adjustments are insufficient in the current imaging mode. This is an automated and intelligent mode switching scheme, which helps to further improve the stability of the endoscopic system's imaging.

[0073] According to another aspect of the present invention, an endoscope system is provided, comprising: an illumination device, an endoscope body, a light source processor, an image processor, a display, and a controller; the illumination device includes a light source; the light source processor is used to control the light source in the illumination device to emit light to a target object; an image acquisition device is provided on the endoscope body for receiving light reflected from the target object and generating an image signal; the image processor is connected to the image acquisition device of the endoscope body for receiving the image signal and generating an endoscope image based on the image signal; the display is connected to the image processor for displaying the endoscope image; and the controller is connected to the light source processor and the image processor respectively for executing the above-described endoscope imaging control method.

[0074] The structure and working principle of the endoscopic imaging system have been described above. You can refer to the above description to understand the implementation of this embodiment. It will not be repeated here.

[0075] According to another aspect of the present invention, an endoscopic imaging control device is also provided. See also... Figure 2 The diagram shown is a schematic block diagram of an endoscopic imaging control device 200 according to an embodiment of the present invention. The endoscopic imaging control device 200 includes: an imaging control module 210, configured to, in automatic dimming mode, in response to a switching command to switch the current imaging mode to a target imaging mode, perform the following imaging control operations: acquiring first model dimming parameters of the endoscopic system in the current imaging mode, wherein the first model dimming parameters are at least a portion of the dimming parameters in the current dimming parameters; inputting model input information into a parameter prediction model for parameter prediction to predict and obtain second model dimming parameters of the endoscopic system in the target imaging mode, and obtaining target dimming parameters based on the second model dimming parameters, wherein the second… The model dimming parameters are at least a portion of the target dimming parameters. The model input information includes the current imaging mode, the first model dimming parameters, and the target imaging mode. The current dimming parameters and the target dimming parameters are parameters that can adjust the image brightness of the image acquired by the endoscope system. The target dimming parameters are used to ensure that the difference between the image brightness of the image acquired by the endoscope system in the target imaging mode and the target image brightness is within a preset range. The target image brightness and the preset range are the reference for the endoscope system to perform automatic dimming. The endoscope system is controlled to switch the current dimming parameters to the target dimming parameters.

[0076] According to another aspect of the present invention, an endoscopic device is also provided. See also... Figure 3 As shown, it is a schematic block diagram of an endoscope device 300 according to an embodiment of the present invention. Figure 3 As shown, the endoscopic device includes a processor 310 and a memory 320. The memory 320 stores computer program instructions, which are executed by the processor 310 to perform the aforementioned endoscopic imaging control method. The endoscopic device 300 can be an image processor for an endoscopic system, or it can be an integrated unit combining an illumination device and an image processor.

[0077] According to another aspect of the present invention, a storage medium is also provided, on which program instructions are stored. When the program instructions are executed by a computer or processor, the computer or processor performs corresponding steps of the endoscopic imaging control method described in the embodiments of the present invention, and is used to implement corresponding modules in the endoscopic imaging control method apparatus according to the embodiments of the present invention or corresponding modules in the endoscopic imaging control method apparatus described above. The storage medium may, for example, include a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. A computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0078] According to another aspect of the present invention, a computer program product is also provided, including computer program instructions, which, when executed, are used to perform the endoscopic imaging control method as described above.

[0079] Those skilled in the art can understand the specific implementation schemes of the above-mentioned endoscopic imaging control device, endoscopic equipment, and storage medium by reading the relevant descriptions of the endoscopic imaging control method. For the sake of brevity, they will not be described in detail here.

[0080] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of this application. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of this application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

[0081] 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, or a combination of computer software and electronic hardware. 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 implementation should not be considered beyond the scope of this application.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units 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 device, or some features may be ignored or not executed.

[0083] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0084] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more aspects of the application, various features of this application may sometimes be grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of this application. However, this approach should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, the point of application is that the corresponding technical problem can be solved with fewer features than all of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0085] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0086] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0087] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules in the endoscopic imaging control device according to the embodiments of this application. This application can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0088] It should be noted that the above embodiments are illustrative of this application and not limiting of it, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0089] The above are merely specific embodiments or descriptions of specific embodiments of this application. The scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. An endoscopic imaging control method, characterized in that, For use in an endoscope system; the method includes: In automatic dimming mode, in response to the switching command to switch the current imaging mode to the target imaging mode, the following imaging control operations are performed: The first model dimming parameters of the endoscope system in the current imaging mode are obtained, wherein the first model dimming parameters are at least a portion of the dimming parameters in the current dimming parameters; The model input information is input into the parameter prediction model for parameter prediction to predict the second model dimming parameters of the endoscope system in the target imaging mode, and the target dimming parameters are obtained based on the second model dimming parameters. The second model dimming parameters are at least a portion of the dimming parameters in the target dimming parameters. The model input information includes the current imaging mode, the first model dimming parameters, and the target imaging mode. The current dimming parameters and the target dimming parameters are parameters that can adjust the image brightness of the image acquired by the endoscope system. The target dimming parameters are used to ensure that the difference between the image brightness of the image acquired by the endoscope system in the target imaging mode and the target image brightness is within a preset range. The target image brightness and the preset range are the reference for the endoscope system to perform automatic dimming. The endoscope system is controlled to switch the current dimming parameter to the target dimming parameter.

2. The endoscopic imaging control method according to claim 1, characterized in that, The first model dimming parameters include the current exposure time, current gain, and current drive value of the endoscope system, wherein the current drive value is the drive value corresponding to at least some of the light sources illuminated in the current imaging mode; The second model dimming parameters include the target exposure time, target gain, and target drive value of the endoscope system, wherein the target drive value is the drive value corresponding to at least a portion of the light sources illuminated in the target imaging mode.

3. The endoscopic imaging control method according to claim 2, characterized in that, The target driving value is the driving value corresponding to the reference light source illuminated in the target imaging mode; Obtaining the target dimming parameters based on the dimming parameters of the second model includes: Based on the target driving value and the emission ratio among the light sources illuminated in the target imaging mode, determine the driving value corresponding to each of the non-reference light sources (excluding the reference light source) illuminated in the target imaging mode. The target dimming parameters include the dimming parameters of the second model and the driving values ​​corresponding to the non-reference light source.

4. The endoscopic imaging control method according to claim 3, characterized in that, The reference light source is one or more of the light sources that need to be lit in both the current imaging mode and the target imaging mode; The current driving value is the driving value corresponding to the reference light source illuminated in the current imaging mode.

5. The endoscopic imaging control method according to claim 1, characterized in that, The model input information also includes the target image brightness. The step of inputting the model input information into a parameter prediction model for parameter prediction, to predict and obtain the second model dimming parameters of the endoscope system in the target imaging mode, includes: The model input information is input into a unified parameter prediction model for parameter prediction, so as to obtain the dimming parameters of the second model.

6. The endoscopic imaging control method according to claim 1, characterized in that, Different prediction models with different parameters are preset for different mirror types and / or different target image brightness; Before inputting the model input information into the parameter prediction model for parameter prediction to predict and obtain the second model dimming parameters of the endoscope system in the target imaging mode, the imaging control operation further includes: Obtain a parameter prediction model corresponding to the brightness of the target image and / or the type of the endoscope system; The step of inputting model input information into a parameter prediction model for parameter prediction, in order to predict and obtain the second model dimming parameters of the endoscope system in the target imaging mode, includes: The model input information is input into a parameter prediction model corresponding to the target image brightness and / or the endoscope type of the endoscope system to predict the second model dimming parameters.

7. The endoscopic imaging control method according to any one of claims 1-6, characterized in that, The parameter prediction model is constructed based on a preset mapping relationship, which represents the correspondence between observation distance, target image brightness, and model dimming parameters corresponding to each imaging mode. The observation distance is the distance between the endoscope system and the target object. In the preset mapping relationship, the model dimming parameters corresponding to each imaging mode are the dimming parameters used when the difference between the image brightness of the image acquired by the endoscope system in that imaging mode and the corresponding target image brightness is within the preset range at the corresponding observation distance.

8. The endoscopic imaging control method according to claim 7, characterized in that, The parameter prediction model is obtained through the following operations: For each of the various preset observation distances, the endoscope system is controlled to image under multiple imaging modes, and the model dimming parameters corresponding to the difference between the brightness of the acquired image and the brightness of each target image under each imaging mode are recorded when the difference is within the preset range. This is to determine the correspondence between the model dimming parameters corresponding to each imaging mode under the same preset observation distance and the same target image brightness. The various imaging modes include the current imaging mode and the target imaging mode. Based on the correspondence between the model dimming parameters corresponding to each imaging mode, a polynomial fitting is performed to obtain the parameter prediction model.

9. The endoscopic imaging control method according to claim 8, characterized in that, The step of performing polynomial fitting based on the correspondence between the model dimming parameters corresponding to each imaging mode to obtain the parameter prediction model includes: Based on the correspondence between the model dimming parameters corresponding to various imaging modes under different target image brightness and different preset viewing distances, polynomial fitting is performed to obtain a unified parameter prediction model; or, For each target image brightness among a variety of different target image brightnesses, a polynomial fitting is performed based on the correspondence between the target image brightness and the model dimming parameters corresponding to each imaging mode under various preset observation distances to obtain a parameter prediction model corresponding to the target image brightness.

10. An endoscope system, characterized in that, include: Lighting devices, mirrors, light source processors, image processors, displays, and controllers; The lighting device includes a light source; The light source processor controls the light source in the illumination device to emit light towards the target object; the endoscope is provided with an image acquisition device to receive light reflected from the target object and generate an image signal; the image processor is connected to the image acquisition device of the endoscope and receives the image signal to generate an endoscopic image based on the image signal; the display is connected to the image processor and displays the endoscopic image; the controller is connected to the light source processor and the image processor respectively and executes the endoscopic imaging control method as described in any one of claims 1-9.

11. An endoscopic device, characterized in that, It includes a processor and a memory, wherein the memory stores computer program instructions, which, when executed by the processor, are used to perform the endoscopic imaging control method as described in any one of claims 1-9.

12. A storage medium, characterized in that, The storage medium stores program instructions that, when executed, perform the endoscopic imaging control method as described in any one of claims 1-9.

13. A computer program product comprising computer program instructions, characterized in that, The computer program instructions, when executed, are used to perform the endoscopic imaging control method as described in any one of claims 1-9.

Images