Aircraft windshield icing detection method and device, aircraft and storage medium

Abstract

The invention provides an aircraft windshield icing detection method and device, an aircraft and a storage medium. The aircraft windshield icing detection method comprises the following steps: acquiring an initial image of a target area in an aircraft windshield; preprocessing the initial image to obtain a target image; performing edge detection on the target image, and extracting a first icing edge image in the target image; according to the first icing edge image, determining a target icing number and a target icing density corresponding to the target image; detecting whether the target ice accumulation quantity and the target ice accumulation density meet ice accumulation alarm conditions or not; and if the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm condition, generating and displaying ice accumulation alarm information. Based on the scheme, automatic detection of icing of the windshield glass of the aircraft is realized, naked eye detection of a pilot is not needed, the visual inspection burden is eliminated, interference to the driving process is avoided, and the accuracy of icing detection can also be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aircraft detection, and in particular to an aircraft windshield icing detection method and device, an aircraft, and a storage medium. BACKGROUND

[0002] During flight, an aircraft encounters icing conditions, and supercooled large droplets impact the non-protected area of the aircraft, forming ice accumulation. The irregular shape of the ice accumulation can significantly change the aerodynamic shape of the aircraft, and if ice accumulation occurs on the lift surface of the aircraft, it will seriously affect flight safety. Therefore, timely detection of supercooled large droplet icing conditions and issuing an alarm are crucial to flight safety.

[0003] In related technologies, the pilot in the cabin usually visually identifies and detects icing conditions, which can cause a visual inspection burden on the pilot during the driving process, distract the pilot's attention, and interfere with the driving process. SUMMARY

[0004] Embodiments of the present application provide an aircraft windshield icing detection method and device, an aircraft, and a storage medium to solve the technical problem of supercooled large droplet icing detection relying on manual identification and affecting the driving process.

[0005] To achieve the above-mentioned purpose, according to a first aspect of the present application, an aircraft windshield icing detection method is provided, comprising:

[0006] obtaining an initial image of a target region in an aircraft windshield;

[0007] preprocessing the initial image to obtain a target image;

[0008] performing edge detection on the target image to extract a first ice accumulation edge image in the target image;

[0009] determining a target ice accumulation quantity and a target ice accumulation density corresponding to the target image according to the first ice accumulation edge image;

[0010] detecting whether the target ice accumulation quantity and the target ice accumulation density satisfy an ice accumulation alarm condition;

[0011] if the target ice accumulation quantity and the target ice accumulation density satisfy the ice accumulation alarm condition, generating and displaying ice accumulation alarm information.

[0012] In some embodiments, obtaining an initial image of a target region in an aircraft windshield comprises:

[0013] capturing a visible light image of the target region;

[0014] obtaining light intensity information of the visible light image;

[0015] detecting whether the light intensity indicated by the light intensity information is greater than a first preset value;

[0016] in a case where it is determined that the light intensity indicated by the light intensity information is greater than the first preset value, obtaining an initial image; the initial image is the visible light image.

[0017] In some embodiments, after detecting whether the light intensity indicated by the light intensity information is greater than a first preset value, the method further comprises:

[0018] in a case where it is determined that the light intensity indicated by the light intensity information is less than or equal to the first preset value, acquiring an infrared light image of the target region as an initial image.

[0019] In some embodiments, the initial image is preprocessed to obtain a target image, comprising:

[0020] segmenting the initial image to obtain a first image;

[0021] performing brightness equalization processing on the first image to obtain a target image.

[0022] In some embodiments, the target ice accumulation density is the maximum value among the ice accumulation densities corresponding to all pixel points.

[0023] In some embodiments, the area of the ice accumulation edge in the second ice accumulation edge image is greater than a second preset value.

[0024] In some embodiments, the target ice accumulation quantity is the number of ice accumulations in the second ice accumulation edge image.

[0025] In some embodiments, detecting whether the target ice accumulation quantity and the target ice accumulation density satisfy the ice accumulation alarm condition comprises:

[0026] detecting whether the target ice accumulation quantity is greater than a third preset value;

[0027] in a case where it is determined that the target ice accumulation quantity is greater than the third preset value, detecting whether the target ice accumulation density is greater than a fourth preset value;

[0028] in a case where it is determined that the target ice accumulation density is greater than the fourth preset value, determining that the target ice accumulation quantity and the target ice accumulation density satisfy the ice accumulation alarm condition.

[0029] In some embodiments, after generating and displaying the ice accumulation alarm information, the method further comprises:

[0030] determining the target image corresponding to the ice accumulation alarm information, the target ice accumulation quantity, and the target ice accumulation density as an alarm information set;

[0031] store the alarm information set.

[0032] According to a second aspect of the present application, there is provided an aircraft windshield icing detection device, comprising:

[0033] An acquisition module is configured to acquire an initial image of a target region of an aircraft windshield.

[0034] A preprocessing module is configured to preprocess the initial image to obtain a target image.

[0035] An edge detection module is configured to perform edge detection on the target image to extract a first ice accumulation edge image in the target image.

[0036] A calculation module is configured to determine a target ice accumulation quantity and a target ice accumulation density corresponding to the target image according to the first ice accumulation edge image.

[0037] An alarm detection module is configured to detect whether the target ice accumulation quantity and the target ice accumulation density satisfy an ice accumulation alarm condition.

[0038] A display module is configured to generate and display ice accumulation alarm information if the target ice accumulation quantity and the target ice accumulation density satisfy the ice accumulation alarm condition.

[0039] According to a third aspect of the present application, there is provided an aircraft, which is provided with an electronic device, the electronic device comprising a processor and a memory for storing processor-executable instructions, the processor implementing the steps of any of the aircraft windshield icing detection methods described above when executing the instructions.

[0040] According to a fourth aspect of the present application, there is provided a storage medium having computer instructions stored thereon, the instructions being executed by a processor to implement the steps of any of the aircraft windshield icing detection methods described above.

[0041] According to a fifth aspect of the present application, there is provided a computer program product comprising computer programs / instructions, the computer programs / instructions being executed by a processor to implement the steps of any of the aircraft windshield icing detection methods described above.

[0042] The technical solutions of the present application can achieve the following beneficial effects: the aircraft windshield icing detection method provided by the embodiments of the present application realizes automatic detection of aircraft windshield icing, eliminates the need for pilots to perform visual detection, eliminates the burden of visual inspection by pilots, and avoids interference with the driving process; icing detection is performed from two dimensions of ice accumulation quantity and ice accumulation density, thereby improving the accuracy of icing detection.

[0043] Other features and advantages of the present application will be described in detail in the following specific embodiments section. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] To gain a more complete understanding of this application and its beneficial effects, the following description will be provided in conjunction with the accompanying drawings, wherein the same reference numerals in the following description denote the same parts.

[0046] Figure 1 A schematic flowchart illustrating a method for detecting icing on an aircraft windshield, provided in an embodiment of this application;

[0047] Figure 2 A schematic diagram showing the position of the acquisition module and the windshield provided in an embodiment of this application;

[0048] Figure 3 A target image provided for an embodiment of this application;

[0049] Figure 4 A schematic diagram of the structure of an aircraft windshield icing detection device provided in this application embodiment;

[0050] Figure 5 An initial image provided for an embodiment of this application. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0053] "A and / or B" includes the following three combinations: A only, B only, and a combination of A and B.

[0054] The use of “adapted to” or “configured to” in this application means open and inclusive language that is not to be construed as being limited to a particular device or step being adapted to or configured to perform an additional task or step. Additionally, the use of “based on” means open and inclusive, as a process, step, calculation, or other action that is “based on” one or more recited conditions or values may in practice be based on additional conditions or values beyond those recited.

[0055] In this application, the term “exemplary” is used to mean “serving as an example, instance, or illustration.” Any implementation described as “exemplary” in this application is not necessarily to be construed as preferred or advantageous over other implementations. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, for purposes of explanation, specific details are set forth. It is apparent to those skilled in the art that the present application can be practiced without using these specific details. In other instances, well-known structures and processes are not elaborated upon in order not to obscure the description of the present application with unnecessary details. Thus, the present application is not intended to be limited by the embodiments shown, but is to be accorded with the widest scope consistent with the principles and features disclosed.

[0056] In one aspect, embodiments of the present application provide a method for detecting icing on a windshield of an aircraft. The method can be performed by the aircraft or a related component (e.g., a chip). As shown in FIG. 1, the method for detecting icing on a windshield of an aircraft includes the following steps: Figure 1

[0057] S101: Obtain an initial image of a target region of a windshield of an aircraft.

[0058] S102: Pre-process the initial image to obtain a target image.

[0059] S103: Perform edge detection on the target image to extract a first ice accumulation edge image in the target image.

[0060] S104: Determine a target ice accumulation quantity and a target ice accumulation density corresponding to the target image based on the first ice accumulation edge image.

[0061] S105: Detect whether the target ice accumulation quantity and the target ice accumulation density satisfy an ice accumulation alarm condition.

[0062] S106: If the target ice accumulation quantity and the target ice accumulation density satisfy the ice accumulation alarm condition, generate and display ice accumulation alarm information.

[0063] A method for detecting icing on a windshield of an aircraft provided by embodiments of the present application is described in detail below.

[0064] S101: Obtain an initial image of a target region of a windshield of an aircraft. ​

[0065] In some embodiments, the target region is a region where supercooled large droplet (SLD) icing is prone to occur, such as the outer surface of the windshield of an aircraft. The supercooled large droplet has a particle size greater than 100 μm. The icing of supercooled large droplets changes the aerodynamic shape of the aircraft, affecting the safety of the flight process.

[0066] In some embodiments, the initial image of the target region of the windshield of the aircraft is acquired, specifically comprising:

[0067] S1: collecting a visible light image of the target region;

[0068] S2: acquiring light intensity information of the visible light image;

[0069] S3: detecting whether the light intensity indicated by the light intensity information is greater than a first preset value;

[0070] S4: obtaining the initial image in a case where it is determined that the light intensity indicated by the light intensity information is greater than the first preset value; the initial image is the visible light image.

[0071] In some embodiments, the light intensity of the visible light image of the target region is collected as the light intensity information. If the light intensity indicated by the light intensity information is greater than the first preset value, it indicates that the light is sufficient, and at this time the visible light image is used as the initial image. The visible light image can provide rich color information and has high detail clarity, and can capture the tiny details of the object surface.

[0072] In some embodiments, the first preset value can be 10 lux.

[0073] In some embodiments, after detecting whether the light intensity indicated by the light intensity information is greater than the first preset value, the method further comprises: in a case where it is determined that the light intensity indicated by the light intensity information is less than or equal to the first preset value, turning on an infrared light source for light compensation, collecting an infrared light image of the target region as the initial image.

[0074] If the light intensity indicated by the light intensity information is less than or equal to the first preset value, it indicates that the light is insufficient, and at this time the infrared light source is turned on for light compensation and the infrared light image is collected, and the infrared light image is used as the initial image. In the case of insufficient light, such as at night, the visible light image is often not clear enough. The infrared light can penetrate the darkness and image in the absence of visible light or in the presence of weak visible light, making up for the defect of insufficient visible light.

[0075] Based on the above embodiments, all-weather detection can be supported, and icing detection can be performed under conditions of sufficient light and insufficient light, thereby improving the application range of the method.

[0076] In some embodiments, reference is made to Figure 2As shown, above the windshield in the cockpit of the aircraft, an acquisition module is arranged, which includes an infrared and visible light integrated camera and an infrared light source. The infrared and visible light integrated camera is used to acquire a "visible light image" and an "infrared light image". In the case that the light intensity information of the acquired visible light image is greater than a first preset value, the visible light image is taken as an initial image. In the case that the light intensity information of the visible light image is less than or equal to the first preset value, the infrared light source is turned on, infrared light is supplemented, an infrared light image is collected, and the infrared light image is taken as the initial image. The icing area is the target area, which is the outer surface of the windshield in this embodiment. The infrared and visible light integrated camera can also have other implementation manners, for example, the infrared camera and the visible light camera are arranged respectively.

[0077] Based on the above embodiment, the acquisition module is simple to implement and easy to integrate into the existing avionics system. The acquisition module is located in the cockpit of the aircraft and does not change the external contour of the aircraft, avoiding interference with the aerodynamic shape of the aircraft and reducing maintenance costs.

[0078] S102: The initial image is preprocessed to obtain a target image.

[0079] In some embodiments, the initial image is preprocessed to obtain a target image, specifically including:

[0080] S1: The initial image is regionally segmented to obtain a first image.

[0081] S2: The first image is subjected to brightness equalization processing to obtain a target image.

[0082] Specifically, brightness equalization processing is a method of changing the contrast of an image by adjusting the histogram of the image. It uniformly distributes the brightness values of the image within the entire brightness range, so that the pixel brightness values originally concentrated in a narrow range are dispersed.

[0083] In some embodiments, the initial image is a plurality of images arranged in ascending order of acquisition time, and the initial image is divided into a first image group and a second image group, the acquisition time of the first image group being earlier than that of the second image group, for example, the initial image is 1000 images arranged in order of acquisition time, the first 10 images are taken as the first image group, and the last 990 images are taken as the second image group. The first image group is used to obtain a segmentation mask image, which is a two-dimensional matrix or a three-channel image completely the same size as the initial image, used to accurately mark the category or instance to which each pixel belongs. Then, the second image group is regionally segmented using the segmentation mask image to obtain a first image.

[0084] Exemplarily, the initial image can be represented as Image; the first image can be represented as MaskedImage; and the target image subjected to the brightness equalization processing can be represented as Bright MaskedImage.

[0085] Based on the above embodiments, the initial image is subjected to image segmentation, and the segmented first images can be allocated to different processors or threads for parallel processing, thereby improving the processing efficiency. The brightness equalization processing is performed on the first image, and for some regions with uneven brightness distribution, such as low-contrast regions, overly bright regions, and overly dark regions, the brightness equalization processing can highlight the details that are originally covered, enhance these details, and be more conducive to subsequent edge detection, so that the edges are more prominent from the background.

[0086] S103: performing edge detection on the target image to extract a first ice accretion edge image in the target image.

[0087] Specifically, the edge detection algorithm such as the Sobel algorithm, the Prewitt algorithm, the Laplacian algorithm, or the Canny algorithm can be used to extract the edge image from the target image. The edge image is usually the edge of a small ice accretion, and the first ice accretion edge image is obtained.

[0088] Exemplarily, the first ice accretion edge image can be represented as Edges.

[0089] S103: determining the target ice accretion quantity and the target ice accretion density corresponding to the target image according to the first ice accretion edge image.

[0090] In some embodiments, the target ice accretion quantity and the target ice accretion density corresponding to the target image are determined according to the first ice accretion edge image, and specifically include:

[0091] S1: determining the area of each ice accretion edge in the first ice accretion edge image;

[0092] S2: selecting, as a second ice accretion edge image, the ice accretion edges with areas within a certain range according to the areas of the ice accretion edges in the first ice accretion edge image;

[0093] S3: determining the ice accretion quantity in a certain region around each pixel point in the target image as the ice accretion density corresponding to the pixel point;

[0094] S4: determining the target ice accretion density corresponding to the target image according to the ice accretion density; the target ice accretion density is the maximum value among the ice accretion densities of all pixel points;

[0095] S5: determining the quantity of ice accretions in the second ice accretion edge image as the target ice accretion quantity corresponding to the target image.

[0096] For example, the area of ​​the ice edge in the second ice edge image can be represented as Selected Edges; the target ice density can be represented as Density or Ice Density Num; the target ice quantity can be represented as Ice Num or Ice; and the area of ​​the ice edge in the first ice edge image can be represented as Edges Areas.

[0097] In some embodiments, based on the area of ​​each ice edge in the first ice edge image, ice edges with areas within a certain range are selected as the second ice edge image, specifically including:

[0098] S1: Compare the area of ​​each ice edge with the second preset value, and select the area that is greater than the second preset value as the target area;

[0099] S2: Determine the ice edge corresponding to the target area, and use it as the second ice edge image.

[0100] In some embodiments, when the resolution of the target image is equal to 1080P, the second preset value is 40. The area of ​​each ice edge in the second ice edge image is greater than the second preset value.

[0101] In some embodiments, the amount of ice accumulation in a certain area around each pixel in the target image is calculated. By using a clustering density algorithm, such as the DBSCAN algorithm (density based spatial clustering of applications with noise), the amount of ice accumulation in a certain area around each pixel can be obtained as the ice accumulation density corresponding to that pixel. Then, the maximum value among the ice accumulation densities corresponding to all pixels is selected to obtain the target ice accumulation density.

[0102] In some embodiments, see Figure 3 As shown, Figure 3 This is a schematic diagram of the target image, where Ice represents the target ice quantity, 543.7 represents the specific value of the target ice quantity, Density represents the target ice density, and 29.3 represents the specific value of the target ice density. The target image includes a second ice edge image.

[0103] In some embodiments, see Figure 5 As shown, Figure 5 for Figure 3 The corresponding initial image, where Ice represents the target ice quantity, 543.7 represents the specific value of the target ice quantity, Density represents the target ice density, and 29.3 represents the specific value of the target ice density.

[0104] S104: Determine whether the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm condition.

[0105] In some embodiments, the determination of whether the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm condition specifically comprises:

[0106] S1: Determine whether the target ice accumulation quantity is greater than a third preset value;

[0107] S2: In a case where it is determined that the target ice accumulation quantity is greater than the third preset value, determine whether the target ice accumulation density is greater than a fourth preset value;

[0108] S3: In a case where it is determined that the target ice accumulation density is greater than the fourth preset value, determine that the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm condition.

[0109] In some embodiments, if the target ice accumulation quantity is less than or equal to the third preset value, and / or, the target ice accumulation density is less than or equal to the fourth preset value, it is determined that the target ice accumulation quantity and the target ice accumulation density do not meet the ice accumulation alarm condition, and no ice accumulation alarm information needs to be generated.

[0110] In some embodiments, in a case where the resolution of the target image is equal to 1080P, the third preset value is equal to 40, and the fourth preset value is equal to 8. It should be noted that, according to different environments around the aircraft, the third preset value and the fourth preset value can also be selected as other values, which are not limited in the present application.

[0111] Based on the above embodiments, the icing of the windshield of the aircraft is automatically detected, without the need for the pilot to detect by naked eye, the burden of visual inspection is eliminated, the driving process is avoided to be disturbed, the response time can be shortened compared with naked eye detection, and the detection response of a single image only needs 0.1 second; the icing detection accuracy is improved by detecting icing from two dimensions of ice accumulation quantity and ice accumulation density, and only in the case where the ice accumulation quantity is relatively large and the ice accumulation density is relatively large, the ice accumulation alarm condition is met.

[0112] In some embodiments, the ice accumulation alarm information can be displayed to the pilot through a display screen, and the ice accumulation alarm information can also be played in time and accurately through a loudspeaker in the cockpit, prompting the pilot to perform relevant operations as soon as possible to ensure the safety of flight.

[0113] In some embodiments, after the ice accumulation alarm information is generated and displayed, the method further comprises:

[0114] S1: Determine the target image, the target ice accumulation quantity and the target ice accumulation density corresponding to the ice accumulation alarm information as an alarm information set;

[0115] S2: Store the alarm information set.

[0116] In some embodiments, the alarm information set includes the associated target image, target ice accumulation quantity, and target ice accumulation density, the alarm information set can be used for post-flight data playback and algorithm optimization after the flight is finished, the third preset value and the fourth preset value can be adjusted and optimized by using the alarm information set, and if it is desired to identify the tiny ice accumulation in time, the third preset value and the fourth preset value can be reduced. The alarm information set can also be used for accident analysis. Encryption storage and rapid retrieval functions are also provided for the alarm information set, so as to ensure the integrity and security of the data.

[0117] In another aspect, referring to Figure 4 The embodiment of the present application provides a device for detecting icing on a windscreen of an aircraft, which comprises:

[0118] The acquisition module 401 is configured to acquire an initial image of a target region of a windscreen of an aircraft.

[0119] The preprocessing module 402 is configured to pre-process the initial image to obtain a target image.

[0120] The edge detection module 403 is configured to perform edge detection on the target image to extract a first ice accumulation edge image in the target image.

[0121] The calculation module 404 is configured to determine a target ice accumulation quantity and a target ice accumulation density corresponding to the target image according to the first ice accumulation edge image.

[0122] The alarm detection module 405 is configured to detect whether the target ice accumulation quantity and the target ice accumulation density satisfy an ice accumulation alarm condition.

[0123] The display module 406 is configured to generate and display ice accumulation alarm information if the target ice accumulation quantity and the target ice accumulation density satisfy the ice accumulation alarm condition.

[0124] In some embodiments, the acquisition module 401 is specifically configured to: acquire a visible light image of the target region; acquire light intensity information of the visible light image; detect whether the light intensity indicated by the light intensity information is greater than a first preset value; obtain the initial image in a case where it is determined that the light intensity indicated by the light intensity information is greater than the first preset value; the initial image is the visible light image; and acquire an infrared light image of the target region as the initial image in a case where it is determined that the light intensity indicated by the light intensity information is less than or equal to the first preset value.

[0125] In some embodiments, the preprocessing module 402 is specifically configured to: perform region segmentation on the initial image to obtain a first image; and perform brightness equalization processing on the first image to obtain the target image.

[0126] In some embodiments, the computing module 404 is specifically configured to determine the areas of all ice accumulation edges in the first ice accumulation edge image; select ice accumulation edges with areas within a certain range as the second ice accumulation edge image according to the areas of all ice accumulation edges in the first ice accumulation edge image; determine the number of ice accumulation in a certain region around each pixel point in the target image as the ice accumulation density corresponding to the pixel point; determine the target ice accumulation density corresponding to the target image according to the ice accumulation density; the target ice accumulation density is the maximum value among the ice accumulation densities corresponding to all pixel points; and determine the number of ice accumulation in the second ice accumulation edge image as the target ice accumulation number corresponding to the target image.

[0127] In some embodiments, the alarm detection module 405 is specifically configured to detect whether the target ice accumulation number is greater than a third preset value; in the case where it is determined that the target ice accumulation number is greater than the third preset value, detect whether the target ice accumulation density is greater than a fourth preset value; in the case where it is determined that the target ice accumulation density is greater than the fourth preset value, determine that the target ice accumulation number and the target ice accumulation density satisfy the ice accumulation alarm condition.

[0128] In some embodiments, the aircraft windshield icing detection device further comprises a storage module, which is configured to store the alarm information set. The storage module can comprise a data storage module and an instruction storage module, the data storage module is configured to store the alarm information set. The instruction storage module is configured to store computer instructions, such as query instructions for the alarm information set.

[0129] In some embodiments, the aircraft windshield icing detection device can further comprise a real-time monitoring module, which is configured to run a multi-level algorithm, the multi-level algorithm comprises an algorithm for image segmentation and brightness equalization processing on the initial image, and further comprises an algorithm for extracting the first ice accumulation edge image and the second ice accumulation edge image, and further comprises an algorithm for calculating the target ice accumulation number and the target ice accumulation density.

[0130] In some embodiments, the acquisition module 401 comprises an infrared and visible light integrated camera, and the initial image of the target region in the aircraft can be acquired by using the infrared and visible light integrated camera.

[0131] Embodiments of the present application provide an aircraft, which is provided with an electronic device, the electronic device comprising a processor and a memory for storing processor-executable instructions, and the processor implements the steps of any of the aircraft windshield icing detection methods described above when executing the instructions.

[0132] Embodiments of the present application provide a storage medium having computer instructions stored thereon, and the instructions are executed by a processor to implement the steps of any of the aircraft windshield icing detection methods described above.

[0133] The embodiment of the present application provides a computer program product, comprising computer programs / instructions, which realize the steps of any of the aircraft windshield icing detection methods described above when executed by a processor.

[0134] In the embodiment of the present application, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0135] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0136] The aircraft windshield icing detection method, device, aircraft, and storage medium provided by the embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples in this paper. The above embodiment descriptions are only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, the specific implementation manners and application ranges will be changed according to the idea of the present application. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for detecting icing on an aircraft windshield, characterized in that, include: Acquire an initial image of the target area in the aircraft's windshield; The initial image is preprocessed to obtain the target image; Edge detection is performed on the target image to extract the first ice edge image from the target image; Based on the first ice edge image, determine the target ice quantity and target ice density corresponding to the target image; Detect whether the target ice accumulation quantity and target ice accumulation density meet the ice accumulation alarm conditions; If the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm conditions, an ice accumulation alarm message is generated and displayed.

2. The method according to claim 1, characterized in that, Acquire an initial image of the target area in the aircraft's windshield, including: Acquire visible light images of the target area; Obtain the light intensity information of the visible light image; Detect whether the light intensity indicated by the light intensity information is greater than a first preset value; If the light intensity indicated by the light intensity information is greater than a first preset value, an initial image is obtained; the initial image is the visible light image.

3. The method according to claim 2, characterized in that, After detecting whether the light intensity indicated by the light intensity information is greater than a first preset value, the method further includes: If the light intensity indicated by the light intensity information is less than or equal to a first preset value, an infrared light image of the target area is acquired as an initial image.

4. The method according to claim 1, characterized in that, The initial image is preprocessed to obtain the target image, including: The initial image is segmented into regions to obtain a first image; The first image is subjected to brightness equalization processing to obtain the target image.

5. The method according to claim 1, characterized in that, Based on the first ice edge image, determine the target ice quantity and target ice density corresponding to the target image, including: Determine the area of ​​each ice edge in the first ice edge image; Based on the area of ​​each ice edge in the first ice edge image, select ice edges with areas within a certain range as the second ice edge image; The amount of ice in a certain area surrounding each pixel in the target image is determined as the ice density corresponding to that pixel. Based on the ice accumulation density, the target ice accumulation density corresponding to the target image is determined; the target ice accumulation density is the maximum value among the ice accumulation densities corresponding to all pixels. The number of ice deposits in the second ice edge image is determined as the target ice quantity corresponding to the target image.

6. The method according to claim 5, characterized in that, Based on the area of ​​each ice edge in the first ice edge image, ice edges with areas within a certain range are selected as the second ice edge image, including: The area of ​​each ice edge is compared with a second preset value, and the area that is greater than the second preset value is selected as the target area. The ice edge corresponding to the target area is determined as the second ice edge image.

7. The method according to claim 1, characterized in that, Detecting whether the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm conditions includes: Detect whether the target ice accumulation is greater than a third preset value; If the target ice accumulation is determined to be greater than a third preset value, it is detected whether the target ice accumulation density is greater than a fourth preset value. If the target ice density is determined to be greater than a fourth preset value, the target ice quantity and the target ice density are determined to meet the ice accumulation alarm conditions.

8. The method according to claim 5, characterized in that, After generating and displaying the icing alarm information, the method further includes: The target image, the amount of ice accumulation, and the density of ice accumulation corresponding to the ice accumulation alarm information are determined as the alarm information set; The alarm information set is stored.

9. A device for detecting icing on an aircraft windshield, characterized in that, include: The acquisition module is used to acquire an initial image of the target area in the aircraft's windshield; The preprocessing module is used to preprocess the initial image to obtain the target image; The edge detection module is used to perform edge detection on the target image and extract the first ice edge image in the target image; The calculation module is used to determine the target ice quantity and target ice density corresponding to the target image based on the first ice edge image; An alarm detection module is used to detect whether the target ice accumulation quantity and target ice accumulation density meet the ice accumulation alarm conditions. The display module is used to generate and display ice accumulation alarm information if the target ice accumulation quantity and the target ice accumulation density meet the ice accumulation alarm conditions.

10. An aircraft, characterized in that, The aircraft is equipped with electronic equipment, which includes a processor and a memory for storing processor-executable instructions. When the processor executes the instructions, it implements the steps of the method according to any one of claims 1 to 8.

11. A storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1 to 8.

Images