Method, system, device and storage medium for processing blade images

Abstract

The present invention discloses a method, system, device and storage medium for processing blade images. The present invention first performs different preprocessing on different types of blade images according to the flight attitude, which can improve the accuracy of the preprocessing and reduce the poor binarization effect caused by the imaging difference of the blades on the image. When determining the effective area, the blade tip segmentation is performed, which can improve the processing ability of the processing method of the present application for different blade images. In addition, shape matching of the effective area can further eliminate abnormal images with poor imaging effects due to obstacles or loss of blade tips. Through the processing method of the embodiment of the present application, the processing accuracy of the blade image can be effectively improved, which is conducive to obtaining more accurate blade geometric features, thereby facilitating the improvement of the accuracy of the rotor common taper calculation. The embodiment of the present application can be widely used in the field of image processing.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, system, device and storage medium for processing blade images. Background Art

[0002] In the rotor taper measurement method based on image processing, it is necessary to process the acquired blade image to obtain the geometric features of the blade in the image, so as to further calculate the rotor taper of the aircraft based on these geometric features. However, in the actual measurement process, the blade image taken by the camera is easily interfered by backgrounds such as trees, buildings and dark clouds. The background reconstruction and foreground / background segmentation technologies in related technologies are prone to blade recognition errors, resulting in low accuracy of the extracted blade geometric features, thereby affecting the measurement accuracy of the rotor taper. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the present application proposes a method, system, device and storage medium for processing blade images, which can improve the accuracy of blade image processing.

[0004] In a first aspect, an embodiment of the present application provides a method for processing a blade image, comprising: obtaining a flight attitude of an aircraft corresponding to the blade image; obtaining a background image corresponding to the blade image; preprocessing the blade image according to the flight attitude and the background image to determine a first image; wherein the first image is a binary image; performing blade tip segmentation on the first image to determine a valid area; when a shape match of the valid area is passed, determining geometric features of the blade tip according to the valid area, the geometric features including blade tip coordinates; when a boundary validity check of the blade tip coordinates is passed, determining an actual swinging height of the corresponding blade according to the blade tip coordinates.

[0005] Optionally, the flight attitude includes a ground small-pitch attitude, a hovering attitude and a level flight attitude, and the pre-processing of the blade image according to the flight attitude and the background image to determine the first image includes: when the flight attitude is the ground small-pitch attitude or the hovering attitude, pre-processing the blade image according to the background image and a first processing mode to determine the first image; when the flight attitude is a level flight attitude, pre-processing the blade image according to a second processing mode to determine the first image.

[0006] Optionally, the preprocessing of the blade image according to the background image and the first processing mode includes: performing background subtraction on the blade image according to the background image to determine a first processed image; performing gamma correction on the first processed image to determine a second processed image; and performing global adaptive binarization on the second processed image to determine the first image.

[0007] Optionally, the processing method further includes: performing a brightness check on the first processed image; when the brightness of the first processed image is lower than a preset first threshold, performing image enhancement on the first processed image.

[0008] Optionally, the preprocessing of the blade image according to the second processing mode includes: performing local adaptive binarization on the blade image to determine the first image.

[0009] Optionally, the root performs blade tip segmentation on the first image to determine a valid area, including: performing dilation and corrosion processing on the first image to determine a third processed image; performing contour extraction on the third processed image to determine an initial area of ​​the blade; when a validity check of the initial area passes, determining that the area between the blade tip and a specified boundary in the initial area is a valid area; wherein the number of pixels in the area between the blade tip and the specified boundary is a preset second threshold; wherein the validity check includes an area validity check and a boundary validity check.

[0010] Optionally, the shape matching step includes: performing convex shape fitting on the effective area to determine the confidence of the effective area; when the confidence is greater than or equal to a preset third threshold, the shape matching is passed.

[0011] In the second aspect, an embodiment of the present application provides a blade image processing system, comprising: a first module, a second module, a third module, a fourth module, a fifth module and a sixth module; the first module is used to obtain the flight attitude of the aircraft corresponding to the blade image; the second module is used to obtain the background image corresponding to the blade image; the third module is used to pre-process the blade image according to the flight attitude and the background image to determine the first image; the fourth module is used to perform blade tip segmentation on the first image to determine the effective area; the fifth module is used to determine the geometric features of the blade tip according to the effective area when the shape matching of the effective area is passed, and the geometric features include blade tip coordinates; the sixth module is used to determine the actual swinging height of the corresponding blade according to the blade tip coordinates when the boundary validity check of the blade tip coordinates is passed.

[0012] In a third aspect, an embodiment of the present application provides a device, comprising: at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor implements the method for processing a blade image as described in the first aspect.

[0013] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the method for processing the blade image as described in the first aspect.

[0014] The beneficial effects of the embodiments of the present application are as follows: The embodiments of the present application provide a method for processing a blade image, first obtaining the flight attitude of the aircraft corresponding to the blade image and the background image corresponding to the blade image, performing different preprocessing on the blade image according to different flight attitudes, and generating a first image after preprocessing; then performing blade segmentation on the first image to obtain a valid area; performing shape matching on the valid area, and when the shape matching passes, extracting the geometric features of the blade tip in the valid area; when the boundary validity check of the blade tip coordinates passes, determining the actual swing height of the blade according to the blade tip coordinates in the geometric features. After processing the images of different blades of the aircraft according to the processing method proposed in the present application and obtaining the actual swing height of the corresponding blade, the rotor common taper of the aircraft can be calculated.

[0015] The method for processing blade images in the present application first performs different preprocessing on different types of blade images according to the flight attitude, which can improve the accuracy of the preprocessing and reduce the poor binarization effect caused by the imaging difference of the blades on the image. The implementation of blade tip segmentation when determining the effective area can improve the processing ability of the processing method of the present application for different blade images. In addition, shape matching of the effective area can further eliminate abnormal images with poor imaging effects due to obstacles or missing blade tips. Through the processing method of the embodiment of the present application, the processing accuracy of the blade image can be effectively improved, which is conducive to obtaining more accurate blade geometric features, thereby facilitating the improvement of the accuracy of the rotor common taper calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0017] Figure 1 is a flowchart of the first step of the method for processing a blade image provided by an embodiment of the present application;

[0018] Figure 2A flowchart of the steps of the pretreatment method provided in the embodiment of the present application;

[0019] Figure 3 A flowchart of the steps of preprocessing the blade image according to the background image and the first processing mode provided in an embodiment of the present application;

[0020] Figure 4 A flowchart of the steps for determining the effective area provided in an embodiment of the present application;

[0021] Figure 5 A schematic diagram of a blade image processing system provided in an embodiment of the present application;

[0022] Figure 6 A schematic diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0024] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0025] The embodiments of the present application are further described below in conjunction with the accompanying drawings.

[0026] refer to Figure 1 , Figure 1 1 is a flowchart of the first step of the method for processing a blade image provided in an embodiment of the present application, the method including but not limited to steps S100-S150:

[0027] S100, obtaining the flight attitude of the aircraft corresponding to the blade image;

[0028] Specifically, the blade image in the embodiment of the present application is taken during the flight of the aircraft. By acquiring the geometric features in the blade image, the rotor taper of the aircraft during the flight can be determined. During the flight of the aircraft, its flight attitude will change, resulting in different types of blade images. Therefore, the related art uses background reconstruction, foreground / background segmentation and other technologies to perform similar processing on all blade images, which may lead to inaccurate segmentation results for some blades.

[0029] In this step, the flight attitude of the aircraft corresponding to the blade image is first obtained. The flight attitude can be recorded when the camera is shooting, or the image features of multiple blade images are extracted (the image features can be the position of the blade tip in the image, etc.), and the multiple blade images are clustered according to the image features to obtain different types of blade images, and the blade images are matched with the flight attitude to obtain the flight attitude corresponding to the blade image.

[0030] S110, obtaining a background image corresponding to the blade image;

[0031] Specifically, since the blade image is generally taken from the bottom of the blade looking up, compared with other images, the blade image mostly contains obstructions such as clouds, flying birds, and leaves. Therefore, the background image corresponding to the position of the aircraft blade can be obtained to help segment the blade.

[0032] S120, pre-processing the blade image according to the flight attitude and the background image to determine a first image;

[0033] Specifically, the flight attitude of the aircraft includes the ground small pitch attitude, the hovering attitude and the level flight attitude. In the ground small pitch and hovering attitude, the background corresponding to the blade part of the aircraft changes little, so the foreground / background related technology can be applied to help the blade segmentation; in the level flight state, due to the large movement distance of the aircraft, the background corresponding to the blade part is constantly changing. If the foreground / background related technology in the related technology is used for image segmentation, a large number of background images corresponding to the foreground need to be obtained to ensure the accuracy of the blade segmentation, which is obviously difficult to do in actual situations. Therefore, it is not appropriate to use the background image to assist the blade segmentation. In an embodiment of the present application, it is proposed to perform different preprocessing on different blade images according to the flight attitude, so as to improve the effectiveness of image preprocessing and the accuracy of blade segmentation. The first image is the preprocessed blade image, and the subsequent steps are implemented on the basis of the first image.

[0034] S130, performing blade tip segmentation on the first image to determine a valid area;

[0035] Specifically, it is mentioned in the above content that the types of blade images are different due to different flight attitudes. This is mainly because the focal length, setting position, etc. of the camera in the prior art are limited. For different flight attitudes, the size and position of the blade image in the camera will be different; in addition, when the aircraft changes its flight attitude, the various parts of the blade are adjusted accordingly, which will also affect the imaging of the blade in the camera.

[0036] However, in order to better capture the image of the blade in motion, a general camera can at least capture the tip of the blade and a portion of the blade. Therefore, in order to improve the generalization of the blade image processing method proposed in this application, the first image in this application is segmented by the blade tip, that is, a portion of the blade area including the tip of the blade is determined to be the valid area.

[0037] S140, performing shape matching on the effective area;

[0038] Specifically, shape matching is performed on the effective area determined in step S130. As mentioned above, when shooting the blade image, there will inevitably be obstacles such as flying birds, leaves, and even raindrops. When constructing the effective area in step S130, these obstacles may also be regarded as part of the blade, thereby affecting the subsequent geometric feature extraction of the blade. In addition, in other cases, due to camera parameter settings or failures, the camera may not be able to capture the high-speed rotating propeller tip well, resulting in the missing propeller tip in the blade image, or the propeller tip is overexposed. This kind of blade image will obviously also affect the geometric feature extraction.

[0039] Therefore, in this step, the effective area is first shape matched, which can effectively identify the abnormal images mentioned above that are blocked by obstacles or have missing blade tips. In this application, the calculation of the common taper of the aircraft rotor blade using blade images is taken as an example. The calculation of the common taper requires processing a lot of blade images. In this step, blade images that have not been shape matched and are identified as abnormal images will be discarded and will not participate in subsequent processing, thereby improving the calculation accuracy of the common taper.

[0040] It is understandable that the above content explains that different flight postures will result in different imaging positions of the blades on the image. Therefore, in the shape matching process of this step, different standard blade tip shapes corresponding to the flight postures will also be used to match the blade images.

[0041] In some embodiments, the shape matching can be a convex shape fitting. When the effective area is determined, a convex shape fitting is performed on the effective area; specifically, it is to detect whether the blade shape of the blade tip part meets the blade shape standard of the aircraft under the corresponding flight attitude. Due to the influence of factors such as the camera shooting angle, weather, and blade rotation speed, it is difficult for the shape of the blade in the captured blade image to completely match the standard blade shape. Therefore, the confidence of the result of the convex shape fitting can be determined by the algorithm in the relevant technology. When the confidence is greater than or equal to the preset third threshold, it means that the effective area is similar to the standard blade image, and the shape matching is judged to be passed. If the confidence is less than the third threshold, it is judged that the shape matching fails, and the current blade image is discarded.

[0042] S150, when the shape matching of the effective area is passed, determining the geometric features of the blade tip according to the effective area, the geometric features including the blade tip coordinates;

[0043] Specifically, when the shape matching in step S140 is passed, the geometric features of the blade tip can be extracted according to the effective area. The geometric features may include blade tip coordinates, contour perimeter, convex shape perimeter, blade tip perimeter ratio, blade area, convex shape area, blade tip area ratio, etc.

[0044] S150: When the boundary validity check of the blade tip coordinates passes, the actual flapping height of the corresponding blade is determined according to the blade tip coordinates.

[0045] Specifically, according to the specific parameters of the camera that photographs the blades, an optical model of camera imaging can be constructed, so that the corresponding relationship between the number of pixels between two points in the image and a certain distance in reality can be determined. For example, according to the blade tip coordinates obtained in the above step S150, the number of pixels between the coordinates and another reference point of the optical model can be determined, and then according to the focal length, elevation angle and other parameters of the camera, the height difference between the blade tip and the reference point in reality can be determined, so as to determine the actual swinging height of the corresponding blade, and the rotor common taper of the blade can be determined by the height difference of different blades of the aircraft.

[0046] Through steps S100-S150, the embodiment of the present application first performs different preprocessing on different types of blade images according to the flight attitude, which can improve the accuracy of the preprocessing and reduce the poor binarization effect caused by the imaging difference of the blades in the image. The implementation of blade tip segmentation when determining the effective area can improve the processing ability of the processing method of the present application for different blade images. In addition, shape matching of the effective area can further eliminate abnormal images with poor imaging effects due to obstacles or missing blade tips. Through the processing method of the embodiment of the present application, the processing accuracy of the blade image can be effectively improved, which is conducive to obtaining more accurate blade geometric features, thereby facilitating the improvement of the accuracy of the rotor common taper calculation.

[0047] In some embodiments, the specific implementation process of the above step S120 can be Figure 2 The method steps are explained in detail, referring to Figure 2 , Figure 2 A flowchart of the steps of the preprocessing method provided in the embodiment of the present application, the method includes but is not limited to steps S200-S220:

[0048] S200, determining the flight attitude corresponding to the current blade image;

[0049] Specifically, as mentioned in the above content, the blade images taken under different flight attitudes are different. The present application adopts different preprocessing methods for different blade images. Therefore, it is necessary to first determine the flight attitude corresponding to the current blade image and determine different preprocessing methods according to different flight attitudes.

[0050] S210, when the flight attitude is a ground small pitch attitude or a hovering attitude, pre-processing the blade image according to the background image and the first processing mode to determine a first image;

[0051] Specifically, when the flight attitude is a ground small pitch attitude or a hovering attitude, since the background corresponding to the blade changes little in these two flight attitudes, the background image can be used to preprocess the blade image according to the preset first processing mode, and generate the first image after the preprocessing is completed.

[0052] Specifically, this step S210 can be combined with Figure 3 The method steps in the following are explained in detail. Figure 3 , Figure 3 A flowchart of the steps of preprocessing a blade image according to a background image and a first processing mode provided in an embodiment of the present application, wherein the method includes but is not limited to steps S211-S213:

[0053] S211, performing background difference on the blade image according to the background image to determine a first processed image;

[0054] Specifically, background difference is mainly used to segment the background part of the foreground image to obtain an image containing only the specified target. In the embodiment of the present application, for example, if the aircraft is collecting blade images outdoors, the background image does not contain the blades, but only contains the sky above the blades. The background difference technology is used to extract the blade part of the blade image, which is called the first processed image.

[0055] S212, performing gamma correction on the first processed image to determine a second processed image;

[0056] Specifically, gamma correction is performed on the first processed image to generate the second processed image.

[0057] In other embodiments, before performing gamma correction on the first processed image, a brightness check is also performed on the first processed image. When the brightness of the first processed image is relatively low, lower than a preset first threshold, image enhancement is performed on the first processed image to improve the accuracy of binarization in subsequent steps.

[0058] S213: Perform global adaptive binarization on the second processed image to determine the first image.

[0059] Specifically, the global adaptive binarization method mainly needs to select different global thresholds according to different grayscale images, and perform binarization processing on the image according to the global threshold to obtain a first image in a binary form.

[0060] Through steps S211 - S213 , the embodiment of the present application proposes a solution for pre-processing the blade image according to the background image and the first processing mode.

[0061] pass Figure 3 , the above step S210 has been explained clearly, and step S220 will be explained below.

[0062] S220: When the flight attitude is a level flight attitude, pre-process the blade image according to the second processing mode to determine the first image.

[0063] Specifically, when the flight attitude is a level flight attitude, the movement of the aircraft will cause the background corresponding to the blades to change rapidly. Therefore, it is no longer appropriate to use the background image to assist in image preprocessing, and other preprocessing modes should be used to process such blade images. In an embodiment of the present application, the second processing mode is used to preprocess the blade images taken in a level flight attitude, and because the global adaptive binarization method is greatly affected by the background, a local adaptive binarization method is used to process such blade images. That is to say, the second processing mode is specifically: local adaptive binarization is performed on the blade image to determine the first image.

[0064] In some embodiments, a local window of a fixed size may be set, a local threshold within the local window may be calculated for binarization, and these slidable local windows may be used to complete the binarization of the entire blade image.

[0065] Through steps S200 - S220 , the embodiment of the present application provides different pre-processing solutions for the blade image according to different flight attitudes.

[0066] In some embodiments, the specific implementation process of the above step S130 can be Figure 4 The method steps are explained in detail, referring to Figure 4 , Figure 4 A flowchart of steps for determining a valid area provided in an embodiment of the present application, the method includes but is not limited to steps S400-S420:

[0067] S400, performing dilation and corrosion processing on the first image to determine a third processed image;

[0068] Specifically, both dilation and erosion are morphological operations, which are generally performed on binary images. Dilation is to add pixels to the boundary of a specified object to expand the scope of the specified object, while erosion is the opposite. This operation removes pixels along the boundary of the specified object to reduce the scope of the specified object. By repeatedly dilating and eroding the specified object in the image, the features of the object can be enhanced. In an embodiment of the present application, the first image is subjected to dilation and erosion processing, and the shape features of the blades are enhanced by repeatedly dilating and eroding the blades in the first image, thereby generating a processed third processed image.

[0069] S410, performing contour extraction on the third processed image to determine an initial area of ​​the blade;

[0070] Specifically, the third processed image is subjected to contour extraction, that is, the blades are extracted according to their boundaries, so as to determine the extracted portion as the initial region. The initial region refers to the portion of all blades imaged on the image.

[0071] S420, when the validity check of the initial area passes, determining the area between the blade tip and the designated boundary in the initial area as a valid area;

[0072] Specifically, the initial area extracted in step S410 is subjected to a validity check, which includes but is not limited to an area validity check and a boundary validity check. As mentioned in the above content, the size of the blade imaged on the image is different under different flight attitudes, so the area validity check can be to check whether the area of ​​the initial area meets the area range of the blade under the corresponding flight attitude. Since the initial area is obtained by contour extraction, it is necessary to check whether the initial area has obvious boundary missing. If the above validity check fails, the currently processed blade image is discarded to ensure the accuracy of subsequent blade tip segmentation.

[0073] In an embodiment of the present application, when the validity check of the initial area passes, the area between the blade tip and the specified boundary in the initial area is extracted as the valid area. As mentioned above, since the imaging size of the blade in the image is different under different flight attitudes, in order to facilitate unified shape matching, part of the blade including the blade tip is taken as the valid area. In this step, the number of pixels in the area between the blade tip and the specified boundary is the preset second threshold, that is, for example, if the second threshold is determined to be 150, the area of ​​150 pixels above the blade tip is intercepted as the valid area.

[0074] Through steps S400 - S420 , the embodiment of the present application provides a method for determining a valid area.

[0075] Through the combination of one or more of the above embodiments, the present application proposes a method for processing blade images. First, different types of blade images are preprocessed differently according to the flight attitude, which can improve the accuracy of the preprocessing and reduce the poor binarization effect caused by the imaging difference of the blades in the image. When determining the effective area, the tip segmentation is performed, which can improve the processing ability of the processing method of the present application for different blade images. In addition, shape matching of the effective area can further eliminate abnormal images with poor imaging effects due to obstacles or missing blade tips. Through the processing method of the embodiment of the present application, the processing accuracy of the blade image can be effectively improved, which is conducive to obtaining more accurate blade geometric features, thereby facilitating the improvement of the accuracy of the rotor common taper calculation.

[0076] Reference Figure 5 , Figure 5 A schematic diagram of a blade image processing system provided in an embodiment of the present application, the system 500 includes a first module 510, a second module 520, a third module 530, a fourth module 540, a fifth module 550 and a sixth module 560; the first module is used to obtain the flight attitude of the aircraft corresponding to the blade image; the second module is used to obtain the background image corresponding to the blade image; the third module is used to pre-process the blade image according to the flight attitude and the background image to determine the first image; the fourth module is used to perform blade tip segmentation on the first image to determine the effective area; the fifth module is used to determine the geometric features of the blade tip according to the effective area when the shape matching of the effective area passes, the geometric features including the blade tip coordinates; the sixth module is used to determine the actual swinging height of the corresponding blade according to the blade tip coordinates when the boundary validity check of the blade tip coordinates passes.

[0077] refer to Figure 6 , Figure 6 A schematic diagram of a device provided in an embodiment of the present application, the device 600 includes at least one processor 610 and at least one memory 620 for storing at least one program; Figure 6 A processor and a memory are taken as an example.

[0078] The processor and the memory may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0079] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0080] Another embodiment of the present application further provides a device, which can be used to execute the control method in any of the above embodiments, for example, to execute the control method described above. Figure 1 The method steps in .

[0081] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] The embodiment of the present application further discloses a computer storage medium, in which a program executable by a processor is stored, characterized in that the program executable by the processor is used to implement the processing method proposed in the present application when executed by the processor.

[0083] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0084] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present application. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for processing a blade image, characterized in that: include: Obtain the flight attitude of the aircraft corresponding to the blade image; Get the background image corresponding to the blade image; Preprocessing the blade image according to the flight attitude and the background image to determine a first image; wherein the first image is a binary image; Performing blade tip segmentation on the first image to determine a valid area; When the shape matching of the effective area is passed, the geometric features of the blade tip are determined according to the effective area, and the geometric features include the blade tip coordinates; When the boundary validity check of the blade tip coordinates passes, determining the actual flapping height of the corresponding blade according to the blade tip coordinates; The flight attitude includes a ground small pitch attitude, a hovering attitude, and a level flight attitude, and preprocessing the blade image according to the flight attitude and the background image to determine the first image includes: When the flight attitude is the ground small-pitch attitude or the hovering attitude, pre-processing the blade image according to the background image and the first processing mode to determine the first image; When the flight attitude is a level flight attitude, the blade image is preprocessed according to a second processing mode to determine the first image.

2. The method for processing blade images according to claim 1, characterized in that: The preprocessing of the blade image according to the background image and the first processing mode includes: According to the background image, performing background difference on the blade image to determine a first processed image; performing gamma correction on the first processed image to determine a second processed image; Perform global adaptive binarization on the second processed image to determine the first image.

3. The method for processing blade images according to claim 2, characterized in that: The processing method also includes: Performing a brightness check on the first processed image; When the brightness of the first processed image is lower than a preset first threshold, image enhancement is performed on the first processed image.

4. The method for processing blade images according to claim 1, characterized in that: The preprocessing of the blade image according to the second processing mode includes: The blade image is locally adaptively binarized to determine the first image.

5. The method for processing blade images according to claim 1, characterized in that: The performing blade tip segmentation on the first image to determine a valid area includes: Performing dilation and corrosion processing on the first image to determine a third processed image; Performing contour extraction on the third processed image to determine an initial area of ​​the blade; When the validity check of the initial area passes, determining the area between the blade tip and the designated boundary in the initial area as a valid area; The number of pixels in the area between the blade tip and the designated boundary is a preset second threshold; The validity check includes an area validity check and a boundary validity check.

6. The method for processing blade images according to claim 1, characterized in that: The shape matching step comprises: Performing convex shape fitting on the effective area to determine the confidence of the effective area; When the confidence level is greater than or equal to a preset third threshold, the shape matching is successful.

7. A blade image processing system, characterized in that: include: The first module, the second module, the third module, the fourth module, the fifth module and the sixth module; The first module is used to obtain the flight attitude of the aircraft corresponding to the blade image; The second module is used to obtain a background image corresponding to the blade image; The third module is used to pre-process the blade image according to the flight attitude and the background image to determine the first image; The fourth module is used to perform blade tip segmentation on the first image to determine a valid area; The fifth module is used for determining the geometric features of the blade tip according to the effective area when the shape matching of the effective area is passed, and the geometric features include the blade tip coordinates; The sixth module is used for determining the actual flapping height of the corresponding blade according to the blade tip coordinates when the boundary validity check of the blade tip coordinates passes; The third module is specifically used for: when the flight attitude is a ground small pitch attitude or a hovering attitude, pre-processing the blade image according to the background image and the first processing mode to determine the first image; When the flight attitude is a level flight attitude, the blade image is preprocessed according to a second processing mode to determine the first image.

8. A blade image processing device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method for processing a blade image according to any one of claims 1 to 6.

9. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method for processing a blade image according to any one of claims 1 to 6 when executed by the processor.

Images