Image data processing method and device in abdominal cavity scene and computer readable storage medium

Abstract

The present specification provides an image data processing method, device and computer readable storage medium. Based on the method, after obtaining a first image containing a target object based on an RGB space, the G channel data and the B channel data in the first image are respectively subjected to a preset first processing in the RGB space to obtain a first processed image; and a target image meeting a requirement is obtained through further processing based on the first processed image. Thus, the method can be well applied to complex application scenarios, reduce the interference and influence of background noise on the target object, and obtain a target image that can clearly display the detailed features of the target object, conforms to the visual habits of the human eye, and has a good effect.

Description

Technical Field

[0001] This specification belongs to the field of image processing technology, and in particular relates to image data processing methods, apparatus and computer-readable storage media in abdominal cavity scenes. Background Technology

[0002] Images captured in complex environments (such as abdominal cavity scenes) are often difficult to accurately identify and distinguish because the target object is often blended into the background due to low light, complex environmental conditions, and a high degree of color similarity between the target object and the image background.

[0003] Existing methods mostly employ Hessian matrices and other techniques for image enhancement. However, when these methods are implemented, their image enhancement effects are relatively limited in complex environments, and some detailed features of the target object still cannot be clearly displayed in the image. Furthermore, the enhanced images obtained using these methods often do not conform to human visual habits, affecting the user experience.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This manual provides image data processing methods, apparatus, and computer-readable storage media for abdominal cavity scenes. These methods are well-suited for complex application scenarios, reducing the interference and impact of background noise on the target object, and producing target images that clearly display the detailed features of the target object and conform to human visual habits with good results.

[0006] This specification provides an image data processing method for an abdominal cavity scene, comprising: acquiring a first image; wherein the first image is an RGB image; the first image contains a target object; obtaining a first processed image by performing a preset first processing on the G channel data and B channel data in the first image respectively; and processing the first processed image to obtain a target image that meets the requirements.

[0007] This specification also provides an image data processing method for an abdominal cavity scene, comprising: acquiring a first image; wherein the first image is an RGB image; the first image contains a target object; determining a matching first type channel from the RGB space based on the color of the target object in the first image and the background color of the adjacent area of ​​the target object; obtaining a first processed image by performing a preset first processing on the first type channel data in the first image; and processing the first processed image to obtain a target image that meets the requirements.

[0008] This specification also provides an image data processing device for an abdominal cavity scene, comprising: an acquisition module for acquiring a first image; wherein the first image is an RGB image; the first image contains a target object; a first processing module for obtaining a first processed image by performing a preset first processing on the G channel data and B channel data in the first image respectively; and a second processing module for processing the first processed image to obtain a target image that meets the requirements.

[0009] This specification also provides an image data processing device, comprising at least: a sensor, a processor, a memory, and a display; the sensor is used to acquire image signals; the processor is used to execute relevant instructions stored in the memory to implement relevant steps of the image data processing method in the abdominal cavity scene, so as to generate a first image containing a target object based on the image signal; and to obtain a target image that meets the requirements by processing the first image; the display is used to display the target image.

[0010] This specification also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the relevant steps of the image data processing method in the abdominal cavity scene.

[0011] Based on the image data processing method, apparatus and computer-readable storage medium for the abdominal cavity scene provided in this specification, after obtaining a first image containing the target object and based on RGB space, a first pre-set first processing can be performed on the G channel data and B channel data in the first image in RGB space to obtain a first processed image; based on the first processed image, a target image that meets the requirements can be obtained.

[0012] By effectively utilizing the data characteristics of the RGB space, and based on the color of the target object in the first image and the background color of the target object's neighboring area, a preset first processing is performed on the G and B channel data of the first image. This targeted approach increases the brightness of the target object relative to the background, reduces image noise, and enhances the contrast of the target object's details, thus better highlighting the detailed features of the target object in the image. Based on the first-processed image, a better-looking and satisfactory target image can be obtained. Furthermore, by effectively utilizing the data characteristics of the HSV space, the first-processed image in RGB space can be converted into a second image in HSV space. Then, global saturation adjustment is performed on the S channel data of the second image to make the image conform to human visual habits. This results in an interactive and visually pleasing target image, improving the user experience. Attached Figure Description

[0013] To more clearly illustrate the embodiments of this specification, the accompanying drawings used in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating an image data processing method in an abdominal cavity scene according to one embodiment of this specification. Figure 2 This is a schematic diagram illustrating the process of processing an image using the image data processing method for an abdominal cavity scene provided in the embodiments of this specification, in a scenario example. Figure 3 This is a schematic diagram of the structural composition of an image data processing system that applies the image data processing method for the abdominal cavity scene provided in the embodiments of this specification in a scenario example; Figure 4 This is a schematic diagram of an embodiment of an image data processing system using an endoscope to acquire image signals in a scenario example; Figure 5 This is a schematic diagram of the structural composition of the image processing host in an image data processing system, presented in a scenario example. Figure 6 This is a schematic diagram of an embodiment in which the image data processing method for the abdominal cavity scene provided in this specification is applied to perform equalization processing on the G channel data and B channel data respectively in a scenario example; Figure 7 This is a schematic diagram of an embodiment in which the image data processing method for the abdominal cavity scene provided in this specification is applied to filter and enhance the details of the G channel data in a scenario example. Figure 8 This is a schematic diagram of an embodiment in which the image data processing method for the abdominal cavity scene provided in this specification is applied to filter and enhance the details of the B channel data in a scenario example. Figure 9 This is a schematic diagram of an embodiment in which the image data processing method for the abdominal cavity scene provided in this specification is applied to adjust the saturation of the S-channel data in a scenario example. Figure 10 In a scenario example, a schematic diagram comparing the effect of an image processed by the image data processing method for an abdominal cavity scene provided in the embodiments of this specification with that of an unprocessed image is shown. Figure 11 This is a flowchart illustrating an image data processing method in an abdominal cavity scene according to another embodiment of this specification; Figure 12This is a schematic diagram of the structural composition of an image data processing device provided in one embodiment of this specification; Figure 13 This is a schematic diagram of the structural composition of an image data processing device in an abdominal cavity scene provided in one embodiment of this specification. Detailed Implementation

[0015] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0016] See Figure 1 As shown in the figure, this specification provides an image data processing method for an abdominal cavity scene. Combined with... Figure 2 The method described above may include the following components in its implementation: S101: Obtain a first image; wherein the first image is an RGB image; the first image contains the target object; S102: By performing a preset first processing on the G channel data and B channel data in the first image respectively, a first-processed image is obtained; S103: Based on the first processed image, process to obtain a target image that meets the requirements.

[0017] In some embodiments, the target object mentioned above can be specifically understood as the observation object that the user is interested in.

[0018] Specifically, in the abdominal cavity scenario, the target object can be the blood vessels of organs and tissues within the abdominal cavity. Accordingly, using the image data processing method for the abdominal cavity scenario provided in this specification, the images acquired in the abdominal cavity scenario can be processed to reduce background noise and specifically highlight the detailed features of the blood vessels in the image.

[0019] Of course, the application scenarios listed above are only illustrative examples. In practice, depending on the specific circumstances and processing requirements, the image data processing method in the abdominal cavity scenario described above can also be applied to other types of application scenarios. Correspondingly, the target objects mentioned above can also include related observation objects in other application scenarios. For example, the image data processing method in the abdominal cavity scenario described above can also be applied to the analysis of leaf veins. Accordingly, the target objects mentioned above can also include leaf veins in the leaf, etc.

[0020] In some embodiments, the above-described processing of the first processed image to obtain a target image that meets the requirements may specifically include the following: S1: Convert the first processed image to HSV space to obtain the corresponding second image; S2: By performing a preset second processing on the S-channel data in the second image, a target image that meets the requirements is obtained.

[0021] In some embodiments, the aforementioned RGB (or RGB color space) specifically refers to a color space based on the three primary colors R (Red), G (Green), and B (Blue), which are superimposed to varying degrees to produce a rich and wide range of colors. Specifically, in a Cartesian coordinate system, a cube of unit length can be used to represent colors based on the three primary colors of red, green, and blue. The eight common colors—black, blue, green, cyan, red, purple, yellow, and white—are respectively placed at the eight vertices of the cube. Typically, black is placed at the origin of the three-dimensional Cartesian coordinate system, and red, green, and blue are placed on the three coordinate axes respectively. The entire cube can be placed within the first octet.

[0022] The aforementioned HSV (or HSV space) specifically refers to a color space constructed based on the intuitive characteristics of color: H (Hue), S (Saturation), and V (Value). It can also be called the Hexcone Model. Specifically, in the HSV space, hue (H) can be measured in angles, ranging from 0° to 360°. It can be calculated counter-clockwise starting with red; for example, red is 0°, green is 120°, and blue is 240°. Their complementary colors are: yellow is 60°, cyan is 180°, and violet is 300°. Saturation (S) represents how close a color is to a spectral color. A color can be seen as the result of mixing a spectral color with white. The greater the proportion of the spectral color, the closer the color is to the spectral color, and the higher the saturation. Generally, high saturation results in a relatively deep and vibrant color. Specifically, the white light component of a spectral color is 0, and the saturation reaches its maximum. The value can be set from 0% to 100%, with a higher S value indicating a more saturated color. Lightness (V) is used to represent the brightness of a color. Specifically, for light source colors, the value of lightness (V) is usually related to the luminance of the light source; for object colors, the value of lightness (V) is usually related to the transmittance or reflectance of the object.

[0023] In some embodiments, the first image described above may specifically be an initial RGB image containing the target object.

[0024] The second image mentioned above can specifically be an HSV image containing the target object. The target image mentioned above can specifically be a processed RGB image containing the target object.

[0025] In some embodiments, after acquiring the first image, the data characteristics in the RGB space can be utilized to select appropriate channels for preset first processing based on the color of the target object in the first image and the background color of the adjacent area of ​​the target object. This can be done to specifically increase the brightness of the target object relative to the background, reduce image noise, and enhance the contrast of the details of the target object, so as to highlight the detailed features of the target object in the image.

[0026] Specifically, for example, in an abdominal cavity scene, considering that blood vessels in organs and tissues (i.e., the background of the target object's neighboring area) are both red (blood vessels are usually darker than tissues and organs), and that blood vessels are often located on the surface or inside tissues and organs; furthermore, the lighting in the abdominal cavity environment is relatively weak. Therefore, the R channel data in the first image can be kept unchanged, and preset first processing such as equalization, filtering, and detail enhancement can be performed on the G and B channel data in the first image to specifically improve the brightness and contrast of the target object relative to the background in the first image of the abdominal cavity scene, while reducing image noise, so as to highlight the detailed features of the target object in the image, resulting in the corresponding first-processed image.

[0027] Furthermore, the image after the first processing can be converted to HSV space to obtain a second image based on HSV space. Then, by utilizing the data characteristics in HSV space, the S channel data in the second image is efficiently selected and subjected to preset second processing such as global saturation adjustment, so as to selectively stretch the saturation of the image to meet the visual habits of the human eye and obtain a processed second image suitable for user observation.

[0028] Finally, the processed second image can be converted to RGB space to obtain a target image based on RGB space that is suitable for display to users and provides a better user experience.

[0029] This makes it well-suited for complex application scenarios, effectively reducing the interference and impact of background noise on the target object, resulting in a target image that clearly displays the detailed features of the target object, conforms to human visual habits, and has a better effect, thus improving the user experience.

[0030] In some embodiments, taking an application in the abdominal cavity as an example, see [reference]. Figure 3As shown, the image data processing method for the abdominal cavity described above can be specifically applied to an endoscope system. This endoscope system includes at least the following components: an endoscope, an illumination source unit, an image processing unit, and a display. The endoscope is connected to the image processing unit, and the image processing unit is connected to the display.

[0031] Specifically, the aforementioned lighting source unit can be used to provide lighting to the abdominal cavity environment. Specifically, the aforementioned lighting source can be a medical cold light source.

[0032] See Figure 4 As shown, the endoscope described above can specifically be a laparoscope. The endoscope may at least include structures such as an image sensor and an electrical signal transmission module (e.g., a communication cable). The endoscope may further include other structures such as a lens module (including a prism) and an adjustment handle. In specific implementation, the endoscope can be inserted into the abdominal cavity and, based on the illumination provided by the illumination source host, acquire image signals of the target object (e.g., blood vessels) within the abdominal cavity; and send the acquired image signals to the image processing host.

[0033] Specifically, for example, see Figure 4 As shown, the illumination light signal emitted by the illumination source provided by the illumination source host will be reflected after illuminating the object surface. The reflected light will pass through the left and right optical paths in the endoscope, through the lens module, and finally be captured by the image sensor to obtain the corresponding image signal (e.g., dual-channel sensor signal, etc.). The image signal is then sent to the image processing host for image processing via the communication cable.

[0034] The aforementioned image processing host can be used to process the acquired image signals to obtain corresponding images or videos; then, by applying the image processing methods provided in this specification, the images or videos can be processed to obtain target images or target videos that can highlight the detailed features of the target object and conform to the visual habits of the human eye; and the aforementioned target images or target videos can be sent to the display.

[0035] See Figure 5As shown, the aforementioned image processing host may at least include structures such as FPGA (Field Programmable Gate Array) and SOC (an integrated circuit that contains a compute engine, memory, and logic on a single chip). The aforementioned image processing host may further include other structures such as DDR (DDR SDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), a 458 serial port, a high-speed optoelectronic transmission module, and output interfaces.

[0036] Specifically, for example, see Figure 5 As shown, after receiving an image signal (e.g., a CMOS signal), the FPGA in the image processing host can first perform ISP processing on the RAW format image signal, outputting a corresponding color image with three RGB channels as the first image. Here, ISP (Image Signal Processing) specifically refers to image signal processing. During ISP processing, the image signal, image, or video stream can be buffered using a DDR connected to the FPGA.

[0037] After the FPGA completes the ISP processing, it can transmit the first image to the SOC for further processing via a high-speed optoelectronic transmission module. The SOC can then execute relevant instruction programs to perform corresponding image data processing on the input first image to enhance the detailed features of the target object in the image, thereby obtaining a target image (or a target video) that meets the requirements. During image processing, the DDR connected to the SOC can be used to buffer the image or video stream, as well as other intermediate data.

[0038] After obtaining the target image that meets the requirements, the target image can be output in formats such as HDMI, SDI, DP, Ethernet through the output interface and then transmitted to devices such as monitors.

[0039] In addition, the aforementioned 485 serial port can provide a hardware interface for communication with peripheral devices (such as lighting source hosts). The FPGA also supports external key outputs to meet diverse user requirements.

[0040] The aforementioned display can be used to show users target images or videos, allowing them to extract detailed features of the target object. Users can then perform specific data processing based on these detailed features, such as anomaly detection based on the detailed features of blood vessels.

[0041] In some embodiments, the acquisition of the first image described above may include the following: acquiring an image signal containing the target object; and generating a corresponding RGB image as the first image by performing ISP processing on the image signal.

[0042] In some embodiments, the aforementioned preset first processing may include at least: equalization processing (e.g., CLAHE processing, etc.) and detail enhancement processing. Furthermore, the aforementioned preset first processing may also include: filtering processing, etc.

[0043] In some embodiments, see Figure 2 As shown, the above-described first processing is performed on the G channel data and B channel data in the first image to obtain the first-processed image. In specific implementation, it may include the following: S1: Perform histogram equalization processing based on contrast limitation on the G channel data and B channel data in the first image respectively to obtain equalized G channel data and equalized B channel data. S2: Perform detail enhancement processing on the equalized G channel data and the equalized B channel data respectively to obtain the detail-enhanced G channel data and the detail-enhanced B channel data; S3: Combine the R channel data in the first image, the G channel data with enhanced detail (e.g., G_o), and the B channel data with enhanced detail (e.g., B_o) to obtain the first processed image.

[0044] Based on the above embodiments, the data characteristics of the RGB space can be effectively utilized. Through equalization processing, the brightness of the target object relative to the background can be improved in a targeted manner. At the same time, through detail enhancement processing, the contrast of the target object relative to the background can be improved in a targeted manner, thereby better highlighting the texture details of the target object.

[0045] In some embodiments, see Figure 6 As shown, the above-described histogram equalization processing based on contrast limitation of the G channel data in the first image can, in specific implementation, include the following: S1: Divide the G channel data in the first image into blocks to obtain multiple sub-data blocks (e.g., divide into m blocks). (n sub-data blocks) S2: Calculate the probability density of each sub-block of data in the G channel (e.g., P). G ); S3: Based on the probability density of each sub-data block of the G-channel data, and combined with contrast constraints, further calculate the cumulative histogram distribution of the G-channel data (e.g., C). G ); S4: Based on the cumulative distribution of the histogram of the G channel data, perform a cumulative function transformation to obtain the corresponding transformation result (e.g., T). G ); S5: Map the transformation result to obtain the equalized G channel data (e.g., G_c).

[0046] This effectively enhances the brightness of the G channel in the first image.

[0047] When performing block processing, the appropriate number of blocks can be flexibly set according to the complexity of the target object and the background, while taking into account the overall computational efficiency and the edge differences between different sub-data blocks.

[0048] When calculating the cumulative histogram distribution of the G channel data, the corresponding cumulative histogram distribution can be calculated using the following formula: ( )= Where k takes values ​​from 0, 1, ..., L-1. L = 2^m, where m is the maximum number of bits.

[0049] When performing the cumulative function transformation, the following transformation function can be used: ( )= ( ).

[0050] See Figure 6 As shown, similarly, histogram equalization based on contrast constraints can also be performed on the B channel data in the first image. Specifically, the B channel data in the first image is divided into blocks to obtain multiple sub-data blocks (e.g., divided into m blocks). (n sub-data blocks); calculate the probability density of each sub-data block of the B channel data (e.g., P0). B Based on the probability density of each sub-data block of the B-channel data, and combined with contrast constraints, the cumulative histogram distribution of the B-channel data is further calculated (e.g., C). B Based on the cumulative distribution of the histogram of the B channel data, a cumulative function transformation is performed to obtain the corresponding transformation result (e.g., T). B The transformation result is then mapped to obtain the equalized B channel data (e.g., B_c). This effectively enhances the brightness of the B channel in the first image.

[0051] In some embodiments, see Figure 7 As shown, the above-described detail enhancement processing is performed on the equalized G-channel data to obtain detail-enhanced G-channel data. In specific implementations, this may include the following: S1: Perform bilateral filtering on the equalized G channel data (e.g., G_c) to obtain the first type of filtered G channel data (e.g., G_f). S2: Perform Gaussian filtering on the equalized G channel data to obtain the second type of filtered G channel data (e.g., G_g). S3: Based on the equalized G-channel data, the first type of filtered G-channel data, and the second type of filtered G-channel data, perform detail enhancement processing to obtain the detail-enhanced G-channel data (e.g., G_o).

[0052] In some embodiments, the above-described detail enhancement processing is performed on the equalized G-channel data, the first type of filtered G-channel data, and the second type of filtered G-channel data to obtain the detail-enhanced G-channel data. In specific implementations, this may include the following: S1: Determine the linear adjustment coefficient (e.g., k); S2: Calculate the difference between the G-channel data after equalization and the G-channel data after the second type of filtering; and add the product of the difference and the linear adjustment coefficient to the G-channel data after the first type of filtering to obtain the sum as the G-channel data after detail enhancement.

[0053] Specifically, the range of the aforementioned linear adjustment coefficient can be greater than or equal to 1 and less than or equal to 2. In practice, an appropriate value within this range can be selected as the matching linear adjustment coefficient based on the relative brightness of the target object in the first image compared to the background of its neighboring area. For example, if the target object in the first image is darker than the background of its neighboring area, a larger value can be selected from the range as the matching linear adjustment coefficient. Conversely, if the target object in the first image is brighter than the background of its neighboring area, a smaller value can be selected from the range as the matching linear adjustment coefficient. The specific range of the linear adjustment coefficient can be obtained beforehand through extensive experimental testing.

[0054] Specifically, the enhanced G-channel data can be calculated using the following formula: G_o = G_f + k (G_c-G_g).

[0055] See in a similar manner Figure 8As shown, specifically based on the B-channel data after equalization, detail enhancement processing is performed to obtain the B-channel data with enhanced details, which may include: S1: Perform bilateral filtering on the equalized B-channel data (e.g., B_c) to obtain the first type of filtered B-channel data (e.g., B_f). S2: Perform Gaussian filtering on the equalized B-channel data to obtain the second type of filtered B-channel data (e.g., B_g). S3: Based on the B-channel data after equalization, the B-channel data after the first type of filtering, and the B-channel data after the second type of filtering, perform detail enhancement processing to obtain the B-channel data after detail enhancement (e.g., B_o).

[0056] Specifically, the enhanced B-channel data can be calculated using the following formula: B_o = B_f + k (B_c-B_g).

[0057] In some embodiments, the aforementioned preset second processing may include at least saturation adjustment processing, etc.

[0058] In practice, the image after the first processing can be converted from the original RGB space to the HSV space. Then, by utilizing the data characteristics of the HSV space, the global saturation can be adjusted efficiently by performing a preset second processing on the S channel data in the image, which can then conform to the visual habits of the human eye.

[0059] In some embodiments, the above-mentioned second processing of the S-channel data in the second image to obtain a target image that meets the requirements may include the following: S1: Perform a preset second processing on the S-channel data in the second image to obtain the processed image; S2: Convert the second processed image to RGB space to obtain the target image that meets the requirements.

[0060] Based on the above embodiments, the second processed image can be converted from HSV space back to RGB space to obtain a target image that meets the requirements for subsequent display and use.

[0061] In some embodiments, the above-described second processing of the S-channel data in the second image to obtain the processed image may specifically include the following: S1: Perform global saturation adjustment on the S channel data (e.g., S) in the second image to obtain the adjusted S channel data; S2: Combine the H channel data, V channel data, and adjusted S channel data from the second image to obtain the second processed image.

[0062] In some embodiments, see Figure 9 As shown, the above-described global saturation adjustment of the S-channel data in the second image yields the adjusted S-channel data. In specific implementation, this may include the following: S1: Calculate the average value (e.g., s_m) of the S channel based on the S channel data in the second image. S2: Calculate the first intermediate auxiliary parameter (e.g., a) and the second intermediate auxiliary parameter (e.g., b) based on the average value of the S channel above. S3: Calculate the saturation adjustment coefficient (e.g., p) based on the first intermediate auxiliary parameter and the second intermediate auxiliary parameter; S4: Using the saturation adjustment coefficient, adjust the S-channel data in the second image to obtain the adjusted S-channel data (e.g., S_o).

[0063] Specifically, the first intermediate auxiliary parameter can be calculated using the following formula: a = 3 (s_m^2) - 2 (s_m^3). The second intermediate auxiliary parameter can be calculated using the following formula: b = 2 (s_m^2) - 3 (s_m^3).

[0064] Specifically, the saturation adjustment coefficient can be calculated using the following formula: p = a / b.

[0065] Specifically, the S-channel data in the second image can be adjusted according to the following formula to obtain the adjusted S-channel data: S_o = 1 / (1+p ((1 / S-1)^2)).

[0066] In some embodiments, the target object may specifically include blood vessels. Of course, the target objects listed above are merely illustrative. In specific implementations, depending on the specific application scenario and processing requirements, the target object may also include suitable observation objects from other application scenarios. This specification does not limit this.

[0067] Specifically, taking blood vessels as the target object as an example. See also... Figure 10As shown, the image on the left is a first image containing blood vessels, unprocessed using the image data processing method for the abdominal cavity scene provided in this manual. The image on the right is the target image obtained after processing using the image data processing method for the abdominal cavity scene provided in this manual. The comparison shows that, compared to the first image, the processed target image clearly displays the detailed texture features of the blood vessels, the lighting environment is brighter, the image contrast is higher, and the blurry areas are significantly reduced. Consequently, based on this target image, doctors can more accurately distinguish blood vessels and tissues within the abdominal cavity, thus enabling more precise surgical procedures and reducing operational errors.

[0068] In some embodiments, after obtaining the target image that meets the requirements, the method may further include the following: S1: Based on the target image, identify and extract the image features of the target object; S2: Detect whether there is any abnormality in the target object based on the preset target object reference template and the image features of the target object.

[0069] Specifically, the preset target object reference template can be constructed in advance by extracting and organizing image features from a large number of sample images containing normal target objects. The aforementioned preset target object reference template contains image features common to normal target objects.

[0070] In practice, the image features of the target object can be accurately extracted from the target image first; then the image features of the target object can be compared with the preset target object reference template to obtain the corresponding comparison results; based on the comparison results, it can be determined whether the difference between the image features of the target object and the preset target object reference template is greater than the preset difference threshold.

[0071] If the difference between the image features of the target object and the preset target object reference template is greater than a preset difference threshold, it can be determined that the target object is abnormal. Conversely, if the difference between the image features of the target object and the preset target object reference template is less than or equal to the preset difference threshold, it can be determined that the target object is not abnormal.

[0072] In some embodiments, after acquiring the first image, the method may further include the following: detecting whether the image quality of the first image meets preset quality requirements; and if it is determined that the image quality of the first image does not meet the preset quality requirements, triggering the application of the image processing method provided in this specification to process the first image.

[0073] In specific detection, the target area where the target object is located and the background area where the background of the target object is located can be identified and located in the first image. By comparing the degree of difference between the target area and the background area, it can be determined whether it is difficult to extract the image information of the target object from the first image. If it is determined that it is difficult to extract the image information of the target object from the first image, it is determined that the image quality of the first image does not meet the preset quality requirements.

[0074] As can be seen from the above, the image data processing method in the abdominal cavity scene provided in the embodiments of this specification, after obtaining a first image containing the target object and based on RGB space, can first perform a preset first processing on the G channel data and B channel data in the first image in RGB space to obtain a first processed image; then convert the first processed image to HSV space to obtain a corresponding second image; and then perform a preset second processing on the S channel data in the second image in HSV space to obtain a target image that meets the requirements. By effectively utilizing the data characteristics of the RGB space, and based on the color of the target object in the first image and the background color of the adjacent area, the G and B channel data in the first image are subjected to preset first processing. This targeted approach increases the brightness of the target object relative to the background, reduces image noise, and enhances the contrast of the target object's details, thereby better highlighting the detailed features of the target object in the image. Simultaneously, by effectively utilizing the data characteristics of the HSV space, the image processed in the RGB space is first converted into a second image in the HSV space. Then, the S channel data in the second image is globally saturated to make the image conform to human visual habits. This results in an interactive and visually pleasing target image, improving the user experience.

[0075] See Figure 11 As shown in the embodiments of this specification, another image data processing method for abdominal cavity scenes is also provided. Specifically, this method may include the following: S1101: Obtain a first image; wherein the first image is an RGB image; the first image contains a target object; S1102: Based on the color of the target object in the first image and the color of the background of the adjacent area of ​​the target object, determine the matching first class channel in the RGB space; S1103: By performing a preset first processing on the first type of channel data in the first image, a first processed image is obtained; S1104: Based on the first processed image, a target image that meets the requirements is obtained.

[0076] In some embodiments, the above-described processing of the first processed image to obtain a target image that meets the requirements may specifically include: converting the first processed image to HSV space to obtain a corresponding second image; and performing a preset second processing on the S-channel data in the second image to obtain a target image that meets the requirements.

[0077] In some embodiments, the target object may specifically include at least one of the following: blood vessels in organ tissues, leaf veins in leaves, oil networks in strata, etc.

[0078] In some embodiments, specifically, when the target object is a blood vessel in an organ tissue, considering that the color of the target object in the first image and the background color of the adjacent area of ​​the target object are both red, corresponding to the R channel; and combined with the specific application scenario, the B channel and G channel other than the R channel can be determined from the RGB space as the first type of matching channel.

[0079] For example, when the target object is the veins in a leaf, considering that the color of the target object in the first image and the background color of the adjacent area of ​​the target object are both green, corresponding to the G channel; and combined with the specific application scenario, the B channel and R channel other than the G channel can be determined from the RGB space as the first type of matching channel.

[0080] Based on the above embodiments, the first type of channel with better effect and matching can be accurately determined from the RGB space according to the color of the target object in the first image and the background color of the adjacent area of ​​the target object. Then, by performing a preset first processing on the first type of channel in the first image, the interference and influence of background noise on the target object can be reduced in a targeted manner, and the image brightness and the contrast of the target object can be improved, so that the detailed features of the target object can be clearly displayed in the image.

[0081] This specification also provides an image data processing device, including a processor and a memory for storing processor-executable instructions. In a specific implementation, the processor can perform the following steps according to the instructions: acquiring a first image; wherein the first image is an RGB image; the first image contains a target object; obtaining a first-processed image by performing a preset first processing on the G channel data and B channel data in the first image respectively; and processing the first-processed image to obtain a target image that meets the requirements.

[0082] To execute the above instructions more accurately, please refer to... Figure 12As shown in the embodiments of this specification, another specific image processing device is also provided, which includes at least: a sensor, a processor, a memory, and a display; wherein, the sensor is specifically used to acquire image signals; the processor is used to implement the steps of the image data processing method in the abdominal cavity scene by executing relevant instructions stored in the memory, so as to generate a first image containing a target object according to the image signal; and to obtain a target image that meets the requirements by processing the first image; the display is used to display the target image.

[0083] This specification also provides a computer device. The computer device includes a network communication port, a processor, and a memory, all connected by internal cables to allow for data interaction between the components.

[0084] Specifically, the network communication port can be used to acquire a first image; wherein the first image is an RGB image; and the first image contains a target object.

[0085] Specifically, the processor can be used to perform a preset first processing on the G channel data and B channel data in the first image to obtain a first processed image; and to process the first processed image to obtain a target image that meets the requirements.

[0086] Specifically, the memory can be used to store the corresponding instruction program.

[0087] In this embodiment, the network communication port can be a virtual port bound to different communication protocols, thereby enabling the sending or receiving of different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM or CDMA; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.

[0088] In this embodiment, the processor can be implemented in any suitable manner. For example, the processor can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc. This specification is not limiting.

[0089] In this embodiment, the memory may include multiple layers. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with storage function but no physical form is also called a memory, such as RAM, FIFO, etc. In a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0090] This specification also provides a computer-readable storage medium based on the above-described image data processing method in the abdominal cavity scene. The computer-readable storage medium stores computer program instructions that, when executed, implement: acquiring a first image; wherein the first image is an RGB image; the first image contains a target object; obtaining a first-processed image by performing a preset first processing on the G channel data and B channel data in the first image respectively; and obtaining a target image that meets the requirements based on the first-processed image.

[0091] This specification also provides another computer-readable storage medium based on the above-described image data processing method in the abdominal cavity scene. The computer-readable storage medium stores computer program instructions that, when executed, implement: acquiring a first image; wherein the first image is an RGB image; the first image contains a target object; determining a matching first type channel from the RGB space based on the color of the target object in the first image and the background color of the adjacent area of ​​the target object; obtaining a first processed image by performing a preset first processing on the first type channel data in the first image; and obtaining a target image that meets the requirements based on the first processed image.

[0092] In this embodiment, the storage medium includes, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured according to standards specified in the communication protocol for network connection communication.

[0093] In this embodiment, the specific functions and effects implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other embodiments, and will not be repeated here.

[0094] See Figure 13 As shown, at the software level, this specification also provides an image data processing device for an abdominal cavity scene, which may specifically include the following structural modules: The acquisition module 1301 is specifically used to acquire a first image; wherein the first image is an RGB image; and the first image contains a target object; The first processing module 1302 can be specifically used to perform a preset first processing on the G channel data and B channel data in the first image to obtain a first processed image. The second processing module 1303 can be used to process the first processed image to obtain a target image that meets the requirements.

[0095] In some embodiments, the second processing module 1303 may specifically include a conversion unit and a processing unit. Specifically, the conversion unit may be used to convert the first processed image to HSV space to obtain a corresponding second image; the processing unit may be used to perform a preset second processing on the S-channel data in the second image to obtain a target image that meets the requirements.

[0096] In some embodiments, when the first processing module 1302 is specifically implemented, it can perform a preset first processing on the G channel data and B channel data in the first image respectively to obtain a first processed image in the following manner: perform histogram equalization processing based on contrast limitation on the G channel data and B channel data in the first image respectively to obtain equalized G channel data and equalized B channel data; perform detail enhancement processing on the equalized G channel data and the equalized B channel data respectively to obtain detail-enhanced G channel data and detail-enhanced B channel data; combine the R channel data, the detail-enhanced G channel data, and the detail-enhanced B channel data in the first image to obtain the first processed image.

[0097] In some embodiments, when the first processing module 1302 is specifically implemented, it can perform detail enhancement processing on the equalized G-channel data in the following manner to obtain detail-enhanced G-channel data: perform bilateral filtering on the equalized G-channel data to obtain first-type filtered G-channel data; perform Gaussian filtering on the equalized G-channel data to obtain second-type filtered G-channel data; and perform detail enhancement processing on the equalized G-channel data, the first-type filtered G-channel data, and the second-type filtered G-channel data to obtain the detail-enhanced G-channel data.

[0098] In some embodiments, when the first processing module 1302 is specifically implemented, it can perform detail enhancement processing on the equalized G-channel data, the first type of filtered G-channel data, and the second type of filtered G-channel data in the following manner to obtain the detail-enhanced G-channel data: determining the linear adjustment coefficient; calculating the difference between the equalized G-channel data and the second type of filtered G-channel data; and adding the product of the difference and the linear adjustment coefficient to the first type of filtered G-channel data to obtain the sum as the detail-enhanced G-channel data.

[0099] In some embodiments, when the second processing module 1303 is specifically implemented, it can perform a preset second processing on the S-channel data in the second image in the following manner to obtain a target image that meets the requirements: perform a preset second processing on the S-channel data in the second image to obtain the image after the second processing; convert the image after the second processing to RGB space to obtain a target image that meets the requirements.

[0100] In some embodiments, when the second processing module 1303 is specifically implemented, it can perform a preset second processing on the S-channel data in the second image in the following manner to obtain the second processed image: perform global saturation adjustment on the S-channel data in the second image to obtain adjusted S-channel data; combine the H-channel data, V-channel data and adjusted S-channel data in the second image to obtain the second processed image.

[0101] In some embodiments, when the second processing module 1303 is specifically implemented, the global saturation adjustment of the S-channel data in the second image can be performed in the following manner to obtain the adjusted S-channel data: the average value of the S-channel is calculated based on the S-channel data in the second image; a first intermediate auxiliary parameter and a second intermediate auxiliary parameter are calculated based on the average value of the S-channel; a saturation adjustment coefficient is calculated based on the first intermediate auxiliary parameter and the second intermediate auxiliary parameter; and the S-channel data in the second image is adjusted using the saturation adjustment coefficient to obtain the adjusted S-channel data.

[0102] In some embodiments, the target object may specifically include blood vessels, etc.

[0103] In some embodiments, after obtaining a target image that meets the requirements, the device can also be used to: identify and extract image features of the target object based on the target image; and detect whether there is an anomaly in the target object based on a preset target object reference template and the image features of the target object.

[0104] At the software level, this specification also provides another image data processing device for abdominal cavity scenes, which may specifically include the following structural modules: The acquisition module can specifically be used to acquire a first image; wherein the first image is an RGB image; and the first image contains a target object; The determination module can be used to determine the matching first type channel in the RGB space based on the color of the target object in the first image and the color of the background of the adjacent area of ​​the target object. The first processing module can be specifically used to obtain a first-processed image by performing a preset first processing on the first type of channel data in the first image; The second processing module can be used to process the first processed image to obtain a target image that meets the requirements.

[0105] In some embodiments, the second processing module may be implemented as follows: converting the first processed image to HSV space to obtain a corresponding second image; and performing a preset second processing on the S-channel data in the second image to obtain a target image that meets the requirements.

[0106] It should be noted that the units, devices, or modules described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above devices are described by dividing them into various modules according to their functions. Of course, in implementing this specification, the functions of each module can be implemented in one or more software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection between the devices or units shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0107] As can be seen from the above, the image data processing device for the abdominal cavity scene provided in the embodiments of this specification, after obtaining a first image containing the target object and based on RGB space, can first perform a preset first processing on the G channel data and B channel data in the first image in RGB space to obtain a first processed image; then convert the first processed image to HSV space to obtain a corresponding second image; and then perform a preset second processing on the S channel data in the second image in HSV space to obtain a target image that meets the requirements. By effectively utilizing the data characteristics of the RGB space, and based on the color of the target object in the first image and the background color of the adjacent area, the G and B channel data in the first image are subjected to preset first processing. This targeted approach increases the brightness of the target object relative to the background, reduces image noise, and enhances the contrast of the target object's details, thereby better highlighting the detailed features of the target object in the image. Simultaneously, by effectively utilizing the data characteristics of the HSV space, the image processed in the RGB space is first converted into a second image in the HSV space. Then, the S channel data in the second image is globally saturated to make the image conform to human visual habits. This results in an interactive and visually pleasing target image, improving the user experience.

[0108] While this specification provides the steps of operation for the methods described in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible order of execution among many steps and does not represent the only possible order. In actual device or client product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. The terms "first," "second," etc., are used to denote names and do not indicate any particular order.

[0109] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0110] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer-readable storage media, including storage devices.

[0111] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this specification can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions of this specification can essentially be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments of this specification.

[0112] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. This specification can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices, etc.

[0113] Although this specification has been described by way of examples, those skilled in the art will recognize that many variations and modifications are possible without departing from the scope of this specification, and it is intended that the appended claims cover such variations and modifications without departing from the scope of this specification.

Claims

1. A method for image data processing in an abdominal cavity scene, characterized in that, include: Acquire a first image; wherein the first image is an RGB image; the first image contains a target object; the first image is an image acquired based on a cold light source in an abdominal cavity scene; the target object includes blood vessels of organs and tissues in the abdominal cavity; By performing a preset first processing on the G channel data and B channel data in the first image respectively, a first-processed image is obtained; wherein, the G channel and B channel are matching channels determined according to the color of the target object in the first image and the background color of the neighboring area of ​​the target object; the preset first processing includes at least: equalization processing and detail enhancement processing; The first processed image is converted to HSV space to obtain the corresponding second image; the S channel data in the second image is subjected to a preset second processing to obtain the target image that meets the requirements. The detail enhancement processing for the equalized G channel data includes: performing bilateral filtering on the equalized G channel data to obtain first-type filtered G channel data; performing Gaussian filtering on the equalized G channel data to obtain second-type filtered G channel data; determining a matching linear adjustment coefficient based on the brightness of the target object relative to the background of the neighboring area in the first image; calculating the difference between the equalized G channel data and the second-type filtered G channel data; and adding the product of the difference and the linear adjustment coefficient to the first-type filtered G channel data to obtain the sum as the G channel data after detail enhancement.

2. The image data processing method in the abdominal cavity scene according to claim 1, characterized in that, By performing a preset first process on the G channel data and B channel data in the first image, a first-processed image is obtained, including: The G channel data and B channel data in the first image are subjected to histogram equalization based on contrast limitation to obtain equalized G channel data and equalized B channel data. Based on the equalized G-channel data and the equalized B-channel data, detail enhancement processing is performed to obtain detail-enhanced G-channel data and detail-enhanced B-channel data. The first processed image is obtained by combining the R channel data, the G channel data with enhanced detail, and the B channel data with enhanced detail from the first image.

3. The image data processing method in the abdominal cavity scene according to claim 1, characterized in that, By performing a preset second processing on the S-channel data in the second image to obtain a target image that meets the requirements, including: The S-channel data in the second image is subjected to a preset second processing to obtain the second processed image; The processed image is converted to RGB space to obtain the target image that meets the requirements.

4. The image data processing method in the abdominal cavity scene according to claim 3, characterized in that, The S-channel data in the second image undergoes a preset second processing to obtain the second processed image, including: Global saturation adjustment is performed on the S-channel data in the second image to obtain the adjusted S-channel data. The H channel data, V channel data, and adjusted S channel data in the second image are combined to obtain the second processed image.

5. The image data processing method in the abdominal cavity scene according to claim 4, characterized in that, Global saturation adjustment is performed on the S-channel data in the second image to obtain the adjusted S-channel data, including: Calculate the average value of the S channel based on the S channel data in the second image; The first intermediate auxiliary parameter and the second intermediate auxiliary parameter are calculated based on the average value of the S channel mentioned above. Calculate the saturation adjustment coefficient based on the first intermediate auxiliary parameter and the second intermediate auxiliary parameter; The S-channel data in the second image is adjusted using the saturation adjustment coefficient to obtain the adjusted S-channel data.

6. The image data processing method in the abdominal cavity scene according to claim 1, characterized in that, After obtaining the target image that meets the requirements, the method further includes: Based on the target image, identify and extract the image features of the target object; Based on a preset target object reference template and the image features of the target object, detect whether there are any anomalies in the target object.

7. A method for image data processing in an abdominal cavity scene, characterized in that, include: Acquire a first image; wherein the first image is an RGB image; the first image contains a target object; the first image is an image acquired based on a cold light source in an abdominal cavity scene; the target object includes blood vessels of organs and tissues in the abdominal cavity; Based on the color of the target object in the first image and the color of the background in the adjacent area of ​​the target object, a matching first class channel is determined from the RGB space; A first-processed image is obtained by performing a preset first processing on the first type of channel data in the first image; wherein the preset first processing includes at least: equalization processing and detail enhancement processing; The first processed image is converted to HSV space to obtain the corresponding second image; the S channel data in the second image is subjected to a preset second processing to obtain the target image that meets the requirements. The detail enhancement processing for the equalized G channel data includes: performing bilateral filtering on the equalized G channel data to obtain first-type filtered G channel data; performing Gaussian filtering on the equalized G channel data to obtain second-type filtered G channel data; determining a matching linear adjustment coefficient based on the brightness of the target object relative to the background of the neighboring area in the first image; calculating the difference between the equalized G channel data and the second-type filtered G channel data; and adding the product of the difference and the linear adjustment coefficient to the first-type filtered G channel data to obtain the sum as the G channel data after detail enhancement.

8. An image data processing device for an abdominal cavity scene, characterized in that, include: An acquisition module is used to acquire a first image; wherein the first image is an RGB image; the first image contains a target object; the first image is an image acquired based on a cold light source in an abdominal cavity scene; the target object includes blood vessels of organs and tissues in the abdominal cavity; The first processing module is used to perform a preset first processing on the G channel data and B channel data in the first image to obtain a first processed image; The second processing module is used to convert the image after the first processing to the HSV space to obtain the corresponding second image; and to obtain the target image that meets the requirements by performing a preset second processing on the S channel data in the second image. The detail enhancement processing for the equalized G channel data includes: performing bilateral filtering on the equalized G channel data to obtain first-type filtered G channel data; performing Gaussian filtering on the equalized G channel data to obtain second-type filtered G channel data; determining a matching linear adjustment coefficient based on the brightness of the target object relative to the background of the neighboring area in the first image; calculating the difference between the equalized G channel data and the second-type filtered G channel data; and adding the product of the difference and the linear adjustment coefficient to the first-type filtered G channel data to obtain the sum as the G channel data after detail enhancement.

9. An image data processing device, characterized in that, It includes at least: sensors, processors, memory, and displays; The sensor is used to acquire image signals; The processor is configured to implement the steps of the image data processing method in the abdominal cavity scene according to any one of claims 1 to 6 or 7 by executing relevant instructions stored in the memory, so as to generate a first image containing a target object according to the image signal; and to obtain a target image that meets the requirements by processing the first image. The display is used to show the target image.

10. A computer-readable storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the image data processing method in the abdominal cavity scene as described in any one of claims 1 to 6 or 7.

Images