An image acquisition processing parameter adaptive generation method and system

Abstract

The application discloses an image acquisition processing parameter self-adaptive generation method and system, which is applied to the technical field of intelligent image processing and comprises the following steps: acquiring a scene type corresponding to a target region as a current scene type; acquiring a current parameter; generating a reference image when the imaging result of the target region through the current parameter is poor; searching for a nearby scene type and acquiring an imaging parameter and an illumination parameter corresponding to the nearby scene type as nearby parameters; and repeatedly approaching the current parameter to the nearby parameters by a preset step length and imaging until the imaging result meets the expected requirement. The application provides a mode in which an on-site staff can manually adjust the related parameters of an endoscope imaging system as a whole, so that when the imaging effect is not ideal, the related parameters can be adjusted on site to obtain the best imaging effect, and the final imaging quality is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image imaging, in particular to an image acquisition processing parameter adaptive generation method and system. BACKGROUND

[0002] Generally, the endoscope image processing device mostly has only a single configuration file for system configuration, and the image effect requirements of different examinations may be different between multiple hospital departments, leading to the problem of complex and inconvenient parameter adjustment. Therefore, some technical solutions in the prior art set a set of endoscope parameters for each medical scene, or simultaneously image the same part through different imaging parameters and illumination parameters, to increase the applicability of the endoscope imaging system.

[0003] In the prior art, a Chinese patent with application number 201110198162.7 discloses an endoscope system, which includes an endoscope, a control unit, a light beam source control unit, and a type inspection unit. The endoscope has an irradiation optical system for irradiating a light beam from a light beam source onto an object and an imaging optical system including an imaging device. The endoscope is removably connected to the control unit. The light beam source control unit controls the emission light beam intensity of the light beam source according to a light beam amount designation value input from the control unit. The type inspection unit inspects the type of the imaging device mounted on the endoscope. The light beam source control unit has a plurality of control modes indicating the relationship between the light beam amount designation value and the control output value, switches to any one of the control modes according to the inspection result, and controls the emission light beam intensity according to the switched control mode, which can provide different illumination intensities for different medical scenes.

[0004] In the prior art, a Chinese patent with application number 202080061715.1 discloses that a main function interface is displayed on a touch display screen of a camera host, and the main function interface at least includes a scene mode area; identification information of a first scene mode is at least displayed in the scene mode area; when a sliding operation in a preset sliding area on the scene mode area is determined, a scene mode switching instruction is generated; based on the scene mode switching instruction, the scene mode in which the camera host currently works is switched to a second scene mode; identification information of the second scene mode is at least displayed in the scene mode area, and the parameter configuration of the camera host is switched to the parameter configuration corresponding to the second scene mode. The user switches different scene modes through the sliding operation in the scene mode area, so that the scene mode corresponding to the current operation type can be quickly selected before the operation, and the convenience of scene mode setting is improved.

[0005] Due to the differences between individuals, there is a large intra-class difference in the same medical scene. If the on-site personnel can only switch the scene mode, the imaging effect is not ideal, and if each single parameter is adjusted during endoscope imaging, it is too cumbersome. SUMMARY

[0006] In order to at least overcome the above deficiencies in the prior art, the purpose of the present application is to provide an image acquisition processing parameter adaptive generation method and system.

[0007] In a first aspect, an image acquisition processing parameter adaptive generation method is provided, comprising:

[0008] When imaging the target area, the scene type corresponding to the target area is obtained as the current scene type;

[0009] The imaging parameters and illumination parameters corresponding to the current scene type are obtained as the current parameters;

[0010] When the imaging result of the target area by the current parameters is not good, a reference image is generated by imaging the target area by the preset parameters;

[0011] The scene type of a non-current scene type that best matches the reference image is found as the adjacent scene type, and the imaging parameters and illumination parameters corresponding to the adjacent scene type are obtained as the adjacent parameters;

[0012] The current parameters are repeatedly moved towards the adjacent parameters by a preset step and imaging is performed until the imaging result meets the expected requirement.

[0013] In a possible implementation, the acquisition of the current parameters and the adjacent parameters comprises:

[0014] The current parameters and the adjacent parameters are obtained by querying a parameter table; the parameter table is a corresponding relationship of the scene type, the imaging parameters and the illumination parameters.

[0015] In a possible implementation, the acquisition of the adjacent scene type comprises:

[0016] The image parameters corresponding to the reference image are obtained as reference image parameters; the image parameters include normalized R channel data, normalized B channel data, normalized G channel data and reflected light intensity ratio;

[0017] The Euclidean distance between the reference image parameters and the sample parameters corresponding to all non-current scene types is calculated, and the scene type with the smallest Euclidean distance is taken as the adjacent scene type; the sample parameters are the image parameters obtained by imaging the scene of the corresponding scene type by the preset parameters.

[0018] In a possible implementation, the obtaining of the normalized R channel data comprises:

[0019] obtaining an average value of R channel data of the whole image, and normalizing the average value in the interval [0, 255];

[0020] The obtaining of the normalized B channel data comprises:

[0021] obtaining an average value of B channel data of the whole image, and normalizing the average value in the interval [0, 255];

[0022] The obtaining of the normalized G channel data comprises:

[0023] obtaining an average value of G channel data of the whole image, and normalizing the average value in the interval [0, 255];

[0024] The obtaining of the reflected light intensity ratio comprises:

[0025] obtaining a reflected light intensity of the whole image, and calculating a ratio of the reflected light intensity to the illumination light intensity in the preset parameter as the reflected light intensity ratio.

[0026] In a possible implementation, the repeatedly approaching the current parameter to the adjacent parameter by a preset step size and imaging comprises:

[0027] obtaining an imaging parameter and an illumination parameter that exist difference between the current parameter and the adjacent parameter as an adjustable parameter;

[0028] calculating an absolute value of a difference of the adjustable parameter corresponding to the adjacent parameter and the current parameter;

[0029] when the adjustable parameter is a continuous parameter, segmenting the difference by a preset adjustment number of times on average, and adjusting the current parameter to the adjacent parameter by one segment each time of re-imaging;

[0030] when the adjustable parameter is a stage-type point value parameter, no adjustment is made each time of re-imaging.

[0031] In a second aspect, the embodiments of the present application further provide an image acquisition and processing parameter adaptive generation system, comprising:

[0032] an imaging unit configured to image a target region;

[0033] a scene unit configured to obtain a scene type corresponding to the target region as a current scene type when imaging the target region;

[0034] An acquisition unit configured to acquire imaging parameters and lighting parameters corresponding to a current scene type as current parameters;

[0035] A control unit configured to control the imaging unit to generate a reference image by imaging the target region with preset parameters when the imaging result of the target region with the current parameters is poor;

[0036] find a scene type of a non-current scene type that is most matched with the reference image as a neighboring scene type through the reference image, and control the acquisition unit to acquire imaging parameters and lighting parameters corresponding to the neighboring scene type as neighboring parameters;

[0037] repeat approaching the current parameters to the neighboring parameters by a preset step size and imaging until the imaging result meets an expected requirement.

[0038] In a possible implementation, the acquisition unit is further configured to:

[0039] acquire the current parameters and the neighboring parameters by querying a parameter table; the parameter table is a corresponding relationship of the scene types, the imaging parameters and the lighting parameters.

[0040] In a possible implementation, the control unit is further configured to:

[0041] acquire image parameters corresponding to the reference image as reference image parameters; the image parameters include normalized R channel data, normalized B channel data, normalized G channel data and a reflected light intensity ratio;

[0042] calculate Euclidean distances between the reference image parameters and sample parameters corresponding to all scene types of non-current scene types, and take a scene type with the smallest Euclidean distance as the neighboring scene type; the sample parameters are the image parameters acquired by imaging a scene corresponding to the scene type with the preset parameters.

[0043] In a possible implementation, the control unit is further configured to:

[0044] acquire an average value of R channel data of the whole image, and normalize the average value in an interval [0, 255];

[0045] the acquisition of the normalized B channel data includes:

[0046] acquire an average value of B channel data of the whole image, and normalize the average value in an interval [0, 255];

[0047] the acquisition of the normalized G channel data includes:

[0048] An average value of G channel data of the whole image is obtained, and the average value is normalized in the interval [0, 255];

[0049] The acquisition of the reflection light intensity ratio comprises:

[0050] The reflection light intensity of the whole image is obtained, and a ratio of the reflection light intensity to the illumination light intensity in the preset parameter is calculated as the reflection light intensity ratio.

[0051] In a possible implementation, the control unit is further configured to:

[0052] An imaging parameter and an illumination parameter, which have a difference between the current parameter and the adjacent parameter, are obtained as an adjustable parameter;

[0053] An absolute value of a difference of the adjustable parameter corresponding to the adjacent parameter and the current parameter is calculated;

[0054] When the adjustable parameter is a continuous parameter, the difference is evenly segmented by a preset number of adjustment times, and the current parameter is adjusted to the adjacent parameter by one segment each time of re-imaging;

[0055] When the adjustable parameter is a stage-type point value parameter, no adjustment is made each time of re-imaging.

[0056] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0057] The present application provides a method for manually adjusting the related parameters of an endoscope imaging system by an on-site staff, so that the related parameters can be adjusted on site when the imaging effect is not ideal, and the best imaging effect can be obtained, thereby effectively improving the final imaging quality. BRIEF DESCRIPTION OF DRAWINGS

[0058] The accompanying drawings, which are included to provide a further understanding of the embodiments of the present application and are incorporated herein and constitute a part of the application, illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings:

[0059] Figure 1 The accompanying drawings, which are included to provide a further understanding of the embodiments of the present application and are incorporated herein and constitute a part of the application, illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings: DETAILED DESCRIPTION

[0060] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the drawings in the present application serve only the purpose of description and illustration, and do not serve to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented in no particular order, and the steps that have no logical context relationship can be reversed in order or implemented simultaneously. In addition, one or more other operations can be added to the flowcharts or one or more operations can be removed from the flowcharts under the guidance of the content of the present application.

[0061] In addition, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0062] Please refer to Figure 1 A flowchart of a method for adaptively generating image acquisition and processing parameters is provided in the embodiments of the present application. Further, the method for adaptively generating image acquisition and processing parameters can specifically include the contents described in steps S1-S5.

[0063] S1: When imaging a target region, a scene type corresponding to the target region is obtained as a current scene type;

[0064] S2: Imaging parameters and illumination parameters corresponding to the current scene type are obtained as current parameters;

[0065] S3: When the imaging result of the target region by the current parameters is poor, a reference image is generated by imaging the target region by preset parameters;

[0066] S4: The scene type of a non-current scene type that best matches the reference image is found as a proximate scene type by using the reference image, and imaging parameters and illumination parameters corresponding to the proximate scene type are obtained as proximate parameters;

[0067] S5: The current parameters are repeatedly moved to the proximate parameters by a preset step size and imaging is performed until the imaging result meets the expected requirement.

[0068] When the target region is imaged, the on-site personnel can know the specific scene type that needs to be imaged at present, such as early cancer screening by a gastroscope, liver resection by a laparoscope, lung segment resection by a thoracoscope, polyp resection by a hysteroscope, ureteral lithotripsy by a flexible ureteroscope, and vocal cord polyp by a laryngoscope, and the on-site personnel can select the corresponding scene type on the operation interface.

[0069] In the embodiment of the application, when the current scene type is obtained, the imaging parameters and the illumination parameters corresponding to the current scene type can be obtained from the database that has been prepared in advance. If the imaging effect is not good, such as imaging blur, excessive reflection, and the like, the current imaging parameters and the illumination parameters can be adjusted to the preset parameters, and a reference image for subsequent analysis is obtained by imaging. Through the reference image, the adjacent scene type that is not the current scene type and that is most matched with the reference image can be found out, and then the adjacent parameters corresponding to the adjacent scene type are obtained from the database. For example, the illumination parameters can include the R channel value of the illumination light, the B channel value of the illumination light, the G channel value of the illumination light, and the color temperature of the light source; and the imaging parameters can include the imaging R channel gain, the imaging B channel gain, the imaging G channel gain, the image resolution, the image frame rate, the noise reduction gain, the sharpness, the contrast, and the like.

[0070] In the embodiment of the application, for the same application scene, it corresponds to two scene types, i.e., the current scene type and the adjacent scene type. The current scene type should be the most matched scene, and the adjacent scene type is the scene that is relatively close to the tissue environment of the target region currently imaged. Therefore, the goal is to gradually approach the adjacent parameters corresponding to the adjacent scene type from the current parameters corresponding to the current scene type. There is a point of a parameter that can have a better imaging effect than the current parameter, so the parameter value can be advanced in a preset step length. It should be understood that the preset step length described in the embodiment of the application can use different fixed step lengths for each parameter, or can use a fixed number of segments to calculate the corresponding step length. The embodiment of the application provides a way for the on-site personnel to manually adjust the related parameters of the endoscope imaging system as a whole, so that when the imaging effect is not ideal, the related parameters can be adjusted on site to obtain the best imaging effect, and the final imaging quality is effectively improved.

[0071] In a possible implementation, the obtaining of the current parameter and the adjacent parameter includes:

[0072] The current parameter and the adjacent parameter are obtained by querying a parameter table. The parameter table is a corresponding relationship among the scene types, the imaging parameters, and the illumination parameters.

[0073] The database can be in the form of a query table in the implementation of the embodiments of the present application. Building a query table is a necessary thing for each endoscope system that can adapt to a scene, and is a relatively mature content in the prior art. Therefore, the embodiments of the present application do not make further limitations. Since the database in the embodiments of the present application also needs to have the function of selecting a proximate scene type, a specific example is given here for this point:

[0074] Different scene types are shot by using preset parameters. The preset parameters selected here are illumination parameters of white light with a color temperature of 6000K, and the imaging parameters are three imaging channel gains of 1, a noise reduction gain of 0.8, an image resolution of 1080P, an image frame rate of 40fps, a contrast of 10 / 20, and a sharpness of 50 / 100. Four features of the images after shooting are extracted as features for scene type matching: normalized R channel data, normalized B channel data, normalized G channel data, and a reflected light intensity ratio. After mapping the obtained features and the corresponding scene types, the database can be built.

[0075] In a possible implementation, the acquisition of the proximate scene type includes:

[0076] The image parameters corresponding to the reference image are acquired as reference image parameters; the image parameters include normalized R channel data, normalized B channel data, normalized G channel data, and a reflected light intensity ratio;

[0077] The Euclidean distances between the reference image parameters and sample parameters corresponding to all scene types except the current scene type are calculated, and the scene type with the smallest Euclidean distance is taken as the proximate scene type; the sample parameters are the image parameters obtained by imaging a scene of the corresponding scene type by using the preset parameters.

[0078] In the above embodiments, the construction process of the database for scene type matching is illustrated, and the image parameters used are corresponding features: normalized R channel data, normalized B channel data, normalized G channel data, and a reflected light intensity ratio. The data of the three channels can represent the color features of the current tissue, and the reflected light intensity ratio can represent the smooth features and the surface liquid features of the current tissue. In this way, the proximate scene type can be matched at a relatively low cost.

[0079] In a possible implementation, the acquisition of the normalized R channel data includes:

[0080] The average value of the R channel data of the entire image is acquired, and the average value is normalized in the interval [0, 255];

[0081] The obtaining of the normalized B channel data comprises:

[0082] obtaining an average value of B channel data of the whole image, and normalizing the average value in the interval [0, 255];

[0083] The obtaining of the normalized G channel data comprises:

[0084] obtaining an average value of G channel data of the whole image, and normalizing the average value in the interval [0, 255];

[0085] The obtaining of the reflection light intensity ratio comprises:

[0086] obtaining a reflection light intensity of the whole image, and calculating a ratio of the reflection light intensity to the illumination light intensity in the preset parameter as the reflection light intensity ratio.

[0087] In a possible implementation, repeatedly approaching the current parameter to the adjacent parameter by a preset step size and imaging comprises:

[0088] obtaining an imaging parameter and an illumination parameter that exist difference between the current parameter and the adjacent parameter as an adjustable parameter;

[0089] calculating an absolute value of a difference of the adjustable parameter corresponding to the adjacent parameter and the current parameter;

[0090] when the adjustable parameter is a continuous parameter, equally segmenting the difference by a preset adjustment number, and adjusting the current parameter to the adjacent parameter by one segment each time of re-imaging;

[0091] when the adjustable parameter is a stage-type point value parameter, no adjustment is made each time of re-imaging.

[0092] In the implementation of the embodiments of the present application, the current parameter and the adjacent parameter can have some same parameters and some different parameters. In the embodiments of the present application, the parameters that have difference are divided into two types. One type is a continuous adjustable parameter, such as gain data. Another type is a stage-type point value parameter, such as resolution and fluorescence imaging laser wavelength. The resolution and the fluorescence imaging laser wavelength are not continuous because they are in gears, but the gears are continuous, so they can be regarded as continuous adjustable parameters. The resolution and the fluorescence imaging laser wavelength are determined in a specific scene and cannot be modified, so no adjustment is made in re-imaging.

[0093] For example, when the on-site personnel are imaging the target region through the endoscope in the laparoscopic cholecystectomy, the current scene type of the point selection is the laparoscopic cholecystectomy, at this time, the lighting parameter is white light 6000K color temperature, the imaging parameter is that the R channel gain is 0.82, the G channel gain is 1.00, the B channel image gain is 0.91, the noise reduction gain is 0.90, the image resolution is 2K, the image frame rate is 40fps, the contrast is 13 / 20, and the sharpness is 60 / 100. At this time, the image is blurred, at this time, the reference image is generated through the preset parameter, and the reference image parameter of the reference image is calculated: the normalized R channel data is 0.50, the normalized B channel data is 0.33, the normalized B channel data is 0.23, and the reflected light intensity ratio is 0.27. The closest adjacent scene type retrieved from the data is thoracoscopic pulmonary segmentectomy, and the corresponding adjacent parameters of the thoracoscopic pulmonary segmentectomy are retrieved: the lighting parameter is white light 6000K color temperature, the imaging parameter is that the R channel gain is 0.93, the G channel gain is 1.00, the B channel image gain is 1.11, the noise reduction gain is 0.9, the image resolution is 1080P, the image frame rate is 40fps, the contrast is 12 / 20, and the sharpness is 70 / 100. At this time, the difference of the adjustable parameter is calculated: the R channel gain is 0.11, the B channel image gain is 0.20, the contrast is 1 / 20, and the sharpness is 10 / 100. For the above data, although the image resolution changes, it is considered to be not adjustable, and the difference 1 / 20 of the contrast is also considered to be not adjustable; for other adjustable parameters, the adjustment times are set to 10 for average segmentation, and the segmentation length of each parameter is: the R channel gain is 0.011, the B channel image gain is 0.020, and the sharpness is 1 / 100. Then, when adjusting for the first time, the parameter is adjusted to the lighting parameter of white light 6000K color temperature, and the imaging parameter is that the R channel gain is 0.831, the G channel gain is 1.00, the B channel image gain is 0.930, the noise reduction gain is 0.90, the image resolution is 2K, the image frame rate is 40fps, the contrast is 13 / 20, and the sharpness is 61 / 100. In this way, the imaging result is adjusted until the on-site personnel consider that the imaging result meets the expected demand.

[0094] Based on the same inventive concept, the embodiment of the present application also provides an image acquisition and processing parameter adaptive generation system, comprising:

[0095] An imaging unit configured to image a target region;

[0096] A scene unit configured to obtain a scene type corresponding to the target region as a current scene type when imaging the target region;

[0097] An acquisition unit configured to obtain imaging parameters and lighting parameters corresponding to the current scene type as current parameters;

[0098] a control unit configured to control the imaging unit to image the target region by a preset parameter to generate a reference image when an imaging result of the target region by the current parameter is poor;

[0099] find, through the reference image, a scene type of a non-current scene type that is most matched with the reference image as a proximate scene type, and control the acquisition unit to acquire an imaging parameter and an illumination parameter corresponding to the proximate scene type as proximate parameters;

[0100] repeat approaching the current parameters to the proximate parameters by a preset step size and imaging until an imaging result meets an expected requirement.

[0101] In a possible implementation, the acquisition unit is further configured to:

[0102] acquire the current parameters and the proximate parameters by querying a parameter table; the parameter table is a corresponding relationship of the scene types, the imaging parameters, and the illumination parameters.

[0103] In a possible implementation, the control unit is further configured to:

[0104] acquire an image parameter corresponding to the reference image as a reference image parameter; the image parameter includes normalized R channel data, normalized B channel data, normalized G channel data, and a reflected light intensity ratio.

[0105] calculate a Euclidean distance between the reference image parameter and a sample parameter corresponding to a scene type of a non-current scene type, and take a scene type with a minimum Euclidean distance as the proximate scene type; the sample parameter is the image parameter acquired by imaging a scene of the corresponding scene type by the preset parameter.

[0106] In a possible implementation, the control unit is further configured to:

[0107] acquire an average value of R channel data of the whole image, and normalize the average value in an interval [0, 255];

[0108] the acquisition of the normalized B channel data includes:

[0109] acquire an average value of B channel data of the whole image, and normalize the average value in an interval [0, 255];

[0110] the acquisition of the normalized G channel data includes:

[0111] acquire an average value of G channel data of the whole image, and normalize the average value in an interval [0, 255];

[0112] The acquisition of the reflected light intensity ratio comprises:

[0113] The reflected light intensity of the whole image is acquired, and a ratio of the reflected light intensity to the preset parameter of the irradiation light intensity is calculated as the reflected light intensity ratio.

[0114] In a possible implementation, the control unit is further configured to:

[0115] An imaging parameter and an illumination parameter, for which there is a difference between the current parameter and the adjacent parameter, are acquired as an adjustable parameter;

[0116] An absolute value of a difference of the adjustable parameter corresponding to the adjacent parameter and the current parameter is calculated;

[0117] When the adjustable parameter is a continuous parameter, the difference is evenly segmented by a preset number of adjustment times, and the current parameter is adjusted to the adjacent parameter by one segment each time of re-imaging;

[0118] When the adjustable parameter is a stage-type point value parameter, no adjustment is made each time of re-imaging.

[0119] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person 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 the present application.

[0120] In several embodiments provided in the present 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 only schematic. For example, the division of the units is only a logical function division, and actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can also be electrical, mechanical or other forms of connection.

[0121] The units described as separate components may or may not be physically separate, and as such it will be apparent to those ordinarily skilled in the art that the units and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various examples have been described generally in terms of their functionality, without describing in detail the corresponding structure thereof. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall architecture. Skilled persons can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0122] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0123] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a grid device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0124] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An image acquisition processing parameter adaptive generation method, characterized in that, The method comprises the following steps: When imaging a target region, a scene type corresponding to the target region is obtained as a current scene type; An imaging parameter and an illumination parameter corresponding to the current scene type are obtained as current parameters; When the imaging result of the target region by the current parameters is poor, a reference image is generated by imaging the target region by preset parameters; A scene type of a non-current scene type that is most matched with the reference image is found as a neighboring scene type, and an imaging parameter and an illumination parameter corresponding to the neighboring scene type are obtained as neighboring parameters; The current parameters are repeatedly adjusted to the neighboring parameters by a preset step size until the imaging result meets the expected requirement; The repeatedly adjusting the current parameters to the neighboring parameters by the preset step size comprises the following steps: An imaging parameter and an illumination parameter that are different between the current parameters and the neighboring parameters are obtained as adjustable parameters; An absolute value of a difference between the adjustable parameters corresponding to the neighboring parameters and the current parameters is calculated; When the adjustable parameters are continuous parameters, the difference is evenly segmented by a preset number of adjustments, and the current parameters are adjusted to the neighboring parameters by one segment each time of re-imaging; When the adjustable parameters are stage-type point value parameters, no adjustment is made each time of re-imaging. The current scene type is the most matched scene, and the neighboring scene type is a scene close to the organization environment of the target region currently imaged.

2. The method of claim 1, wherein, The current parameters and the neighboring parameters are obtained by querying a parameter table; the parameter table is a corresponding relationship among the scene types, the imaging parameters, and the illumination parameters. The neighboring scene type is obtained by the following steps:

3. The method of claim 1, wherein, An image parameter corresponding to the reference image is obtained as a reference image parameter; the image parameter comprises normalized R channel data, normalized B channel data, normalized G channel data, and a reflected light intensity ratio; Euclidean distances between the reference image parameter and sample parameters corresponding to all non-current scene types are calculated, and a scene type with the smallest Euclidean distance is taken as the neighboring scene type; the sample parameters are the image parameters obtained by imaging a scene corresponding to the scene type by the preset parameters. The normalized R channel data are obtained by the following steps:

4. The method of claim 3, wherein, An average value of R channel data of the entire image is obtained, and the average value is normalized in an interval [0, 255]; The normalized B channel data are obtained by the following steps: An average value of B channel data of the entire image is obtained, and the average value is normalized in an interval [0, 255]; The normalized G channel data are obtained by the following steps: An average value of G channel data of the entire image is obtained, and the average value is normalized in an interval [0, 255]; The reflected light intensity ratio is obtained by the following steps: A reflected light intensity of the entire image is obtained, and a ratio of the reflected light intensity to an illumination light intensity in the preset parameters is taken as the reflected light intensity ratio. The method comprises the following steps:

5. An image acquisition processing parameter adaptive generation system, characterized in that, An imaging unit is configured to image a target region; ​ The scene unit is configured to acquire a scene type corresponding to the target region as a current scene type when imaging the target region; The acquisition unit is configured to acquire imaging parameters and illumination parameters corresponding to the current scene type as current parameters; The control unit is configured to control the imaging unit to generate a reference image by imaging the target region using preset parameters when the imaging result of the target region using the current parameters is not good; The control unit is further configured to: Acquire imaging parameters and illumination parameters that differ between the current parameters and the adjacent parameters as adjustable parameters; Calculate the absolute value of the difference between the adjustable parameters corresponding to the adjacent parameters and the current parameters; When the adjustable parameters are continuous parameters, divide the difference into segments by a preset adjustment number, and adjust the current parameters to the adjacent parameters by one segment each time of re-imaging; When the adjustable parameters are stage-type point value parameters, do not adjust each time of re-imaging; The current scene type is the most matched scene, and the adjacent scene type is a scene close to the organizational environment of the target region currently imaged. The acquisition unit is further configured to: Acquire the current parameters and the adjacent parameters by querying a parameter table; the parameter table is a corresponding relationship between the scene types, the imaging parameters, and the illumination parameters.

6. The system of claim 5, wherein, The control unit is further configured to: Acquire image parameters corresponding to the reference image as reference image parameters; the image parameters include normalized R channel data, normalized B channel data, normalized G channel data, and a reflected light intensity ratio; 7. The system of claim 5, wherein, Calculate the Euclidean distance between the reference image parameters and sample parameters corresponding to all scene types other than the current scene type, and take the scene type with the smallest Euclidean distance as the adjacent scene type; The sample parameters are image parameters acquired after imaging a scene corresponding to the scene type using the preset parameters. The control unit is further configured to: Acquire the average value of the R channel data of the entire image, and normalize the average value in the interval [0, 255]; 8. The system of claim 7, wherein, The acquisition of the normalized B channel data includes: Acquire the average value of the B channel data of the entire image, and normalize the average value in the interval [0, 255]; The acquisition of the normalized G channel data includes: Acquire the average value of the G channel data of the entire image, and normalize the average value in the interval [0, 255]; The acquisition of the reflected light intensity ratio includes: Acquire the reflected light intensity of the entire image, and calculate the ratio of the reflected light intensity to the illumination light intensity in the preset parameters as the reflected light intensity ratio. ​ ​

Images