[go: up one dir, main page]

CN110379000B - Method and device for detecting aircraft air inlet, storage medium and electronic equipment - Google Patents

Method and device for detecting aircraft air inlet, storage medium and electronic equipment Download PDF

Info

Publication number
CN110379000B
CN110379000B CN201910551364.1A CN201910551364A CN110379000B CN 110379000 B CN110379000 B CN 110379000B CN 201910551364 A CN201910551364 A CN 201910551364A CN 110379000 B CN110379000 B CN 110379000B
Authority
CN
China
Prior art keywords
air inlet
aircraft
image
dimensional model
determining whether
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910551364.1A
Other languages
Chinese (zh)
Other versions
CN110379000A (en
Inventor
车建强
林义闽
廉士国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Cloudminds Robotics Co Ltd
Original Assignee
Cloudminds Shanghai Robotics Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Cloudminds Shanghai Robotics Co Ltd filed Critical Cloudminds Shanghai Robotics Co Ltd
Priority to CN201910551364.1A priority Critical patent/CN110379000B/en
Publication of CN110379000A publication Critical patent/CN110379000A/en
Application granted granted Critical
Publication of CN110379000B publication Critical patent/CN110379000B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Chemical & Material Sciences (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Analysis (AREA)

Abstract

The disclosure relates to a method, a device, a storage medium and an electronic device for detecting an aircraft air inlet, wherein the method comprises the following steps: and acquiring a plurality of continuous surface images of the target aircraft air inlet, wherein the surface images of the adjacent two aircraft air inlet pipelines have overlapping areas, determining whether the surface of the target aircraft air inlet is damaged according to the plurality of surface images and the preset surface standard image, and performing visual inspection by ground staff without the need of the ground staff, so that the detection efficiency is greatly improved, the problem that visual inspection is easy to miss under the condition that the damage degree of the surface of the aircraft air inlet is smaller is avoided, and the detection result is more accurate.

Description

Method and device for detecting aircraft air inlet, storage medium and electronic equipment
Technical Field
The disclosure relates to the field of computer technology, and in particular relates to a method and a device for detecting an aircraft air inlet, a storage medium and electronic equipment.
Background
In the aircraft inspection work, the inspection of the aircraft air inlet is one of the key points of ground service inspection, and the inspection of whether the surface of the aircraft air inlet is damaged mainly comprises the inspection of whether a rivet is complete, whether a part is loose, whether foreign matters exist and the like, so that accidents are avoided after the rivet is inhaled by an engine.
At present, the surface inspection of an aircraft air inlet mainly depends on the visual inspection of ground service staff, namely, according to the regulations of related maintenance manuals, short-stature personnel are arranged before taking off according to the flight time requirements, work clothes without static electricity and additional objects (in order to avoid people from bringing things in) are worn on the personnel, a flashlight is worn on the personnel or held on the personnel, the personnel climbs into the aircraft air inlet to perform the visual inspection, namely, whether the surface of the aircraft air inlet is damaged or not is checked through eyes, and after the inspection is completed, related forms are filled in, and inspection results are recorded. Therefore, the conventional visual inspection method is time-consuming and labor-consuming, the inspection efficiency is low, and when the surface damage degree of the air inlet channel of the aircraft is small, the visual inspection is difficult to find, omission is easy to occur, and the inspection result is inaccurate.
Disclosure of Invention
In order to solve the problems, the disclosure provides a method, a device, a storage medium and electronic equipment for detecting an aircraft air inlet.
To achieve the above object, in a first aspect, an embodiment of the present disclosure provides a method for detecting an aircraft intake duct, including:
acquiring a plurality of continuous surface images of a target aircraft air inlet, wherein the surface images of two adjacent aircraft air inlet pipelines have overlapping areas;
and determining whether the surface of the air inlet channel of the target aircraft is damaged or not according to the surface images and the preset surface standard image.
Optionally, the damage includes deformation damage, and determining whether the surface of the air inlet of the target aircraft is damaged according to the plurality of surface images and a preset surface standard image includes:
carrying out three-dimensional reconstruction on the surface of the air inlet of the aircraft according to the plurality of surface images to obtain a three-dimensional model image of the surface of the air inlet of the aircraft, wherein the three-dimensional model image comprises a three-dimensional model of the surface of the air inlet of the aircraft;
and determining whether deformation damage exists on the surface of the air inlet passage of the airplane according to the three-dimensional model image and the surface standard image.
Optionally, the determining whether deformation damage exists on the surface of the aircraft air inlet according to the three-dimensional model image and the surface standard image includes:
acquiring a first point cloud corresponding to the three-dimensional model image and a second point cloud corresponding to the surface standard image;
calculating Hausdorff distance of the first point cloud and the second point cloud by utilizing an iterative closest point ICP algorithm;
and if the Haoskov distance is greater than or equal to a preset distance threshold, determining that deformation damage exists on the surface of the aircraft air inlet.
Optionally, the damage includes a surface burn, and determining whether the target aircraft inlet surface is damaged according to the plurality of surface images and a preset surface standard image includes:
acquiring a first reference point image corresponding to a preset reference imaging point on a target surface image; the target surface image is any image in a plurality of surface images;
acquiring a second reference point image corresponding to the reference imaging point on the surface standard image;
performing super-pixel segmentation on the first reference point image to obtain a plurality of first sub-areas;
performing super-pixel segmentation on the second reference point image to obtain a second sub-region corresponding to each first sub-region;
and determining whether surface burn exists on the surface of the air inlet channel of the target aircraft according to the first subarea and the second subarea.
Optionally, the determining whether the surface of the air inlet of the target aircraft has a surface burn according to the first subarea and the second subarea includes:
acquiring a first color histogram of each first sub-region and a second color histogram of the corresponding second sub-region;
calculating the difference value of the pixel frequency of each first color histogram and the pixel frequency of each second color histogram to obtain a plurality of pixel frequency difference values;
calculating root mean square values of a plurality of pixel frequency differences;
and if the root mean square value is greater than or equal to a first root mean square threshold value, determining that the surface of the aircraft air inlet is burnt.
In a second aspect, an embodiment of the present disclosure provides an apparatus for detecting an aircraft intake, comprising:
the acquisition module is used for acquiring a plurality of continuous surface images of the air inlet channel of the target aircraft, wherein the surface images of the air inlet channel of two adjacent aircraft have overlapping areas;
and the determining module is used for determining whether the surface of the air inlet channel of the target aircraft is damaged according to the plurality of surface images and the preset surface standard image.
Optionally, the damage includes deformation damage, and the determining module is specifically configured to:
carrying out three-dimensional reconstruction on the surface of the air inlet of the aircraft according to the plurality of surface images to obtain a three-dimensional model image of the surface of the air inlet of the aircraft, wherein the three-dimensional model image comprises a three-dimensional model of the surface of the air inlet of the aircraft;
and determining whether deformation damage exists on the surface of the air inlet passage of the airplane according to the three-dimensional model image and the surface standard image.
Optionally, the determining module is further specifically configured to:
acquiring a first point cloud corresponding to the three-dimensional model image and a second point cloud corresponding to the surface standard image;
calculating Hausdorff distance of the first point cloud and the second point cloud by utilizing an iterative closest point ICP algorithm;
and if the Haoskov distance is greater than or equal to a preset distance threshold, determining that deformation damage exists on the surface of the aircraft air inlet.
Optionally, the damage includes a surface burn, and the determining module is specifically configured to:
acquiring a first reference point image corresponding to a preset reference imaging point on a target surface image; the target surface image is any image in a plurality of surface images;
acquiring a second reference point image corresponding to the reference imaging point on the surface standard image;
performing super-pixel segmentation on the first reference point image to obtain a plurality of first sub-areas;
performing super-pixel segmentation on the second reference point image to obtain a second sub-region corresponding to each first sub-region;
and determining whether surface burn exists on the surface of the air inlet channel of the target aircraft according to the first subarea and the second subarea.
Optionally, the determining module is further specifically configured to:
acquiring a first color histogram of each first sub-region and a second color histogram of the corresponding second sub-region;
calculating the difference value of the pixel frequency of each first color histogram and the pixel frequency of each second color histogram to obtain a plurality of pixel frequency difference values;
calculating root mean square values of a plurality of pixel frequency differences;
and if the root mean square value is greater than or equal to a first root mean square threshold value, determining that the surface of the aircraft air inlet is burnt.
In a third aspect, the disclosed embodiments provide a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the method of the first aspect of the disclosed embodiments.
In a fourth aspect, an embodiment of the present disclosure provides an electronic device, including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method according to the first aspect of the embodiments of the present disclosure.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:
the method can acquire a plurality of continuous surface images of the target aircraft air inlet, wherein two adjacent aircraft air inlet pipeline surface images have overlapping areas, whether the surface of the target aircraft air inlet is damaged is determined according to the plurality of surface images and the preset surface standard image, ground staff is not needed to carry out visual inspection, the detection efficiency is greatly improved, the problem that visual inspection is easy to miss under the condition that the damage degree of the surface of the aircraft air inlet is small is avoided, and the detection result is more accurate.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a flow chart illustrating a method of detecting an aircraft inlet according to an embodiment of the disclosure;
FIG. 2 is a flow chart illustrating another method of detecting an aircraft inlet according to an embodiment of the disclosure;
FIG. 3 is a flow chart illustrating a third method of detecting an aircraft inlet according to an embodiment of the disclosure;
FIG. 4 is a schematic structural view of an apparatus for detecting an aircraft inlet according to an embodiment of the disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
In the aircraft inspection work, whether the surface of an aircraft air inlet is damaged or not is one of the key points of ground inspection, and mainly comprises the step of inspecting whether a rivet is complete, whether a part is loose, whether foreign matters exist or not and the like so as to avoid accidents after the rivet is sucked by an engine.
At present, the surface inspection of an aircraft air inlet mainly depends on the visual inspection of ground service staff, namely, according to the regulations of related maintenance manuals, short-stature personnel are arranged before taking off according to the flight time requirement, work clothes without static electricity and additional objects (in order to avoid people from bringing things in) are worn on the head or held by a flashlight, the aircraft air inlet is climbed, the aircraft air inlet is carefully inspected, the filling of related forms is completed, and the inspection result is recorded.
The air inlet of modern aircraft generally adopts a boundary layer-free partition in terms of structure, and is in a short S streamline shape as a whole. Because of large daily stress and large temperature change, structural distortion damage and surface damage occur at the outlet of the air inlet channel. The former is mainly deformation damage, and the latter is mainly surface burn. Deformation damage and surface burn are relatively easy to find by staff under the condition of relatively large degree, but under the condition of relatively small degree, particularly under the condition that a streamline structure generates integral micro-deflection, the visual inspection is difficult to find, and omission is easy to occur.
The inventor notices the problem and proposes a method for detecting an aircraft air inlet, which comprises the following steps:
fig. 1 is a flow chart illustrating a method for detecting an aircraft intake duct according to an embodiment of the disclosure, as shown in fig. 1, the method includes:
s101, acquiring a plurality of continuous surface images of a target aircraft air inlet, wherein the surface images of two adjacent aircraft air inlet pipelines have overlapping areas.
In this step, the surface image of the air inlet of the target aircraft may be acquired by an image acquisition device such as a mobile phone, a camera, or a video camera, for example, a worker may enter the air inlet of the target aircraft by holding the mobile phone, the camera, or the video camera, and shoot the surface of the air inlet of the target aircraft, thereby acquiring a plurality of continuous surface images of the air inlet of the target aircraft.
The surface image of the target aircraft air inlet comprises a surface image of the inner wall of the target aircraft air inlet, a surface image of the engine blade of the target aircraft and a surface image of the inner pipeline of the target aircraft air inlet.
Further, in order to ensure that a plurality of continuous surface images of the target aircraft air inlet can completely cover the whole target aircraft air inlet, an overlapping area exists between two adjacent surface images of the aircraft air inlet pipeline, and the overlapping ratio of the two adjacent surface images of the aircraft air inlet pipeline is not smaller than a preset overlapping ratio. For example, in this embodiment, the preset overlap ratio may be 50% to 80%, for example, may be 70%, that is, the overlap ratio of the surface images of the air inlet duct of two adjacent aircraft is not less than 70%.
S102, determining whether the surface of the air inlet channel of the target aircraft is damaged or not according to the plurality of surface images and a preset surface standard image.
The preset surface standard image is a surface standard model image of the aircraft air inlet, and comprises a surface standard model of the aircraft air inlet.
The aircraft inlet surface damage includes deformation damage and surface burn, so that whether the target aircraft inlet surface is damaged or not and whether the target aircraft inlet surface damage is deformation damage or surface burn can be determined according to a plurality of surface images and a surface standard model of the aircraft inlet.
For example, for the case that the surface damage is deformation damage, three-dimensional reconstruction may be performed on the surface of the air inlet of the target aircraft according to a plurality of continuous surface images, so as to obtain a three-dimensional model image, where the three-dimensional model image includes a three-dimensional model of the surface of the air inlet of the aircraft, then calculating a distance between the three-dimensional model of the surface of the air inlet of the aircraft and a surface standard model of the air inlet of the aircraft, and then determining whether deformation damage exists on the surface of the air inlet of the target aircraft according to the distance.
For the case that the surface damage is surface burn, the color difference between a plurality of continuous surface images and images corresponding to the three-dimensional model images can be calculated, and whether the surface of the air inlet channel of the target aircraft is burnt or not is determined according to the color difference.
By adopting the scheme, a plurality of continuous surface images of the target aircraft air inlet can be obtained, wherein the surface images of the two adjacent aircraft air inlet pipelines have the overlapping area, whether the surface of the target aircraft air inlet is damaged is determined according to the plurality of surface images and the preset surface standard image, the ground service staff is not required to perform visual inspection, the detection efficiency is greatly improved, and the problem that visual inspection is easy to miss under the condition that the damage degree of the surface of the aircraft air inlet is smaller is avoided, so that the detection result is more accurate.
In the following, in conjunction with the specific embodiment of fig. 2, a further detailed description of how the method for detecting an aircraft air inlet provided in the present disclosure determines whether deformation damage exists on the surface of the target aircraft air inlet is provided.
Fig. 2 is a flow chart illustrating another method for detecting an aircraft intake duct according to an embodiment of the disclosure, as shown in fig. 2, the method includes:
s201, acquiring a plurality of continuous surface images of a target aircraft air inlet, wherein the surface images of two adjacent aircraft air inlet pipelines have overlapping areas.
The S201 provided in this embodiment is similar to S101 provided in the embodiment of fig. 1, and will not be described here again.
S202, carrying out three-dimensional reconstruction on the surface of the air inlet of the aircraft according to a plurality of surface images to obtain a three-dimensional model image of the surface of the air inlet of the target aircraft, wherein the three-dimensional model image comprises a three-dimensional model of the surface of the air inlet of the target aircraft.
In order to make the three-dimensional reconstruction of the surface of the air intake of the target aircraft more accurate, the resolution of a plurality of the surface images may be greater than or equal to a preset resolution, for example, in this embodiment, the resolution of a plurality of the surface images is greater than or equal to 1280×1080 pixels.
In order to make the three-dimensional reconstruction of the surface of the air inlet channel of the target aircraft more accurate, the contact ratio of the surface images of the air inlet channel pipelines of two adjacent aircraft is not less than the preset contact ratio. For example, in this embodiment, the preset overlap ratio may be 50% to 80%, for example, may be 70%, that is, the overlap ratio of the surface images of the air inlet duct of two adjacent aircraft is not less than 70%.
It should be noted that, the three-dimensional reconstruction method may refer to a three-dimensional reconstruction scheme in the prior art, which is not described in detail in this embodiment.
Further, after the three-dimensional model image of the surface of the air inlet channel of the target aircraft is obtained, in order to ensure that the surface of the three-dimensional model meets the smoothness and uniformity, the aerodynamic design of the air inlet channel of the aircraft is more consistent, whether the surface of the obtained three-dimensional model meets the curvature continuity can be determined, if the surface of the three-dimensional model meets the curvature continuity, the subsequent step S203 is executed, so that the accuracy of the determination result is improved when the surface of the air inlet channel of the target aircraft is determined to be damaged according to the three-dimensional model image, and if the surface of the three-dimensional model does not meet the curvature continuity, the reconstruction of the three-dimensional model can be performed again until the surface of the established three-dimensional model meets the curvature continuity.
S203, acquiring a first point cloud corresponding to the three-dimensional model image and a second point cloud corresponding to the surface standard image.
Illustratively, if the surface of the three-dimensional model of the surface of the air inlet of the target aircraft meets the curvature continuity, the three-dimensional model of the surface of the air inlet of the target aircraft is subjected to discrete and up-sampling to obtain a first point cloud, and the surface standard model of the air inlet of the aircraft is subjected to discrete and up-sampling to obtain a second point cloud.
S204, calculating the Hausdorff distance of the first point cloud and the second point cloud by utilizing an ICP (Iterative Closest Point) algorithm.
Illustratively, the first point cloud and the second point cloud are used as inputs of an ICP algorithm, and then the unidirectional hausdorff distance from the first point cloud to the second point cloud and the unidirectional hausdorff distance from the second point cloud to the first point cloud are calculated respectively using the ICP algorithm. And finally, comparing the unidirectional Hausdorff distance from the first point cloud to the second point cloud with the unidirectional Hausdorff distance from the second point cloud to the first point cloud, and taking the maximum value as the Hausdorff distance.
Illustratively, the distances between each point in the first point cloud and the points in the second point cloud closest to the point are ordered, and then the maximum value in the distances is taken as the unidirectional hausdorff distance of the first point cloud to the second point cloud.
Accordingly, the distances between each point in the second point cloud and the point in the first point cloud closest to the point are ordered, and then the maximum value in the distances is taken as the unidirectional Hausdorff distance from the second point cloud to the first point cloud.
The hausdorff distance of the first point cloud and the second point cloud is the greater of the one-way hausdorff distance of the first point cloud to the second point cloud and the one-way hausdorff distance of the second point cloud to the first point cloud, which measures the maximum degree of mismatch between the two point clouds.
S205, if the Haoskov distance is greater than or equal to a preset distance threshold, determining that deformation damage exists on the surface of the air inlet of the target aircraft.
If the Haoskov distance is smaller than the preset distance, determining that deformation damage does not exist on the surface of the air inlet channel of the target aircraft.
If the Haoskov distance is greater than or equal to the preset distance, determining that deformation damage exists on the surface of the air inlet channel of the target aircraft.
Further, in this embodiment, the location of deformation damage may be determined by a dichotomy.
Specifically, a three-dimensional model of the surface of an air inlet channel of a target aircraft is cut, and a first model and a second model are obtained. For example, three-dimensional animation software may be used to cut a three-dimensional model of the surface of the air scoop of the target aircraft.
And cutting the surface standard model of the aircraft air inlet by adopting the same mode to obtain a third model corresponding to the first model and a fourth model corresponding to the second model. And then acquiring a third point cloud corresponding to the first model, a fourth point cloud corresponding to the second model, a fifth point cloud corresponding to the third model and a sixth point cloud corresponding to the fourth model.
And calculating the Hausdorff distance of the third point cloud and the fifth point cloud, and determining whether the Hausdorff distance is larger than or equal to a preset distance.
If the hausdorff distance is smaller than the preset distance, deformation damage does not exist in the position area where the first model is located, deformation damage exists in the position area where the second model is located, at this time, in order to determine the more accurate position of deformation damage, the second model and the fourth model can be continuously divided according to the model division mode, the hausdorff distance of the corresponding models after division is calculated until the hausdorff distance is larger than or equal to the preset distance, and accordingly the deformation damage is determined to be located in the area corresponding to the model with the hausdorff distance larger than or equal to the preset distance.
If the hausdorff distance is greater than or equal to the preset distance, deformation damage exists in the position area where the first model is located, at this time, in order to determine the more accurate deformation damage position, the first model and the third model can be continuously divided, the hausdorff distance of the corresponding models after division is calculated until the hausdorff distance is greater than or equal to the preset distance, and therefore the deformation damage is determined to be located in the area corresponding to the model with the hausdorff distance greater than or equal to the preset distance. In addition, considering that deformation damage may exist in the location area where the second model is located, whether deformation damage exists in the location area where the second model is located may also be determined, and a specific determination manner is the same as the above, and is not repeated.
After determining the location area of the deformation damage, the model corresponding to the location area may be further divided, so that the location of the deformation damage is more accurately obtained, where the more the number of divisions, the more accurate the obtained location is, but the more the number of divisions, the higher the resource consumption of the system is, so that in practical application, the number of divisions may be determined by comprehensively considering the location accuracy and the consumption of system resources.
By adopting the scheme, whether deformation damage exists on the surface of the air inlet channel of the target aircraft can be determined according to a plurality of surface images, the position of the deformation damage is further determined through a dichotomy, ground staff is not needed to perform visual inspection, the detection efficiency is greatly improved, the problem that visual inspection is easy to miss under the condition that the damage degree of the surface of the air inlet channel of the aircraft is smaller is avoided, and the detection result is more accurate.
Further details of how the method for detecting an aircraft inlet provided by the present disclosure determines whether a surface burn exists on the surface of the target aircraft inlet are described below in connection with the specific embodiment of fig. 3.
Fig. 3 is a flow chart illustrating a third method for detecting an aircraft intake duct according to an embodiment of the disclosure, as shown in fig. 3, the method includes:
s301, acquiring a plurality of continuous surface images of a target aircraft air inlet, wherein the surface images of two adjacent aircraft air inlet pipelines have overlapping areas.
The S301 provided in this embodiment is similar to S101 provided in the embodiment of fig. 1, and will not be described here again.
S302, acquiring a first reference point image corresponding to a preset reference imaging point on a target surface image; the target surface image is any one of a plurality of the surface images.
In this step, a first reference point image corresponding to a preset reference imaging point on the target surface image can be acquired according to the preset reference imaging point.
S303, acquiring a second reference point image corresponding to the reference imaging point on the surface standard image.
Specifically, the second reference point image is an image corresponding to the first reference point image position on the surface standard image.
S304, performing super-pixel segmentation on the first reference point image to obtain a plurality of first sub-areas;
s305, performing super-pixel segmentation on the second reference point image to obtain a second sub-region corresponding to each first sub-region.
The super-pixel segmentation is a process of subdividing a digital image into a plurality of image sub-areas (sets of pixels) in the field of computer vision, and is a way of image segmentation. Super-pixels are sub-regions composed of a series of pixel points that are adjacent in position and similar in color, brightness, texture, etc. These sub-regions mostly retain the effective information for further image segmentation and do not generally destroy the boundary information of the objects in the image.
It should be noted that, in the present embodiment, the super-pixel segmentation may refer to the segmentation method of the super-pixel segmentation in the prior art, which is not described herein.
S306, determining whether surface burn exists on the surface of the air inlet of the target aircraft according to the first subarea and the second subarea.
For example, first, a first color histogram of each of the first sub-regions and a second color histogram of the corresponding second sub-region may be acquired.
And secondly, determining whether the surface of the air inlet of the target aircraft has surface burn according to the difference between the first color histogram and the second color histogram.
In one possible implementation manner, a difference value between the pixel frequency of each first color histogram and the pixel frequency of the second color histogram may be calculated to obtain a plurality of pixel frequency difference values; calculating root mean square value of the pixel frequency difference values; and if the root mean square value is greater than or equal to a first root mean square threshold value, determining that the surface of the air inlet channel of the target aircraft has surface burn, wherein the surface burn is positioned in the first subarea.
By adopting the scheme, whether the surface of the air inlet channel of the target aircraft is burnt or not can be determined according to a plurality of surface images, the ground staff is not required to perform visual inspection, the detection efficiency is greatly improved, and the problem that visual inspection is easy to miss under the condition that the damage degree of the surface of the air inlet channel of the aircraft is smaller is avoided, so that the detection result is more accurate.
Fig. 4 is a schematic structural diagram of an apparatus for detecting an air inlet of an aircraft according to an embodiment of the disclosure. Referring to fig. 4, the apparatus 40 includes an acquisition module 401 and a determination module 402 connected to the acquisition module.
An acquisition module 401, configured to acquire a plurality of continuous surface images of a target aircraft air inlet, where two adjacent surface images of air inlet pipelines have overlapping areas;
a determining module 402, configured to determine whether the surface of the air intake passage of the target aircraft is damaged according to the plurality of surface images and a preset surface standard image.
Optionally, the determining module 402 is configured to: carrying out three-dimensional reconstruction on the surface of the air inlet of the aircraft according to a plurality of surface images to obtain a three-dimensional model image of the surface of the air inlet of the aircraft, wherein the three-dimensional model image comprises a three-dimensional model of the surface of the air inlet of the aircraft; and if the surface of the three-dimensional model meets the curvature continuity, determining whether deformation damage exists on the surface of the air inlet channel of the aircraft according to the three-dimensional model image and the surface standard image.
Optionally, the determining module 402 is further configured to: acquiring a first point cloud corresponding to the three-dimensional model image and a second point cloud corresponding to the surface standard image; calculating Hausdorff distance of the first point cloud and the second point cloud by utilizing an iterative closest point ICP algorithm; and if the Haoskov distance is greater than or equal to a preset distance threshold value, determining that deformation damage exists on the surface of the air inlet channel of the aircraft.
Optionally, the determining module 402 is configured to: acquiring a first reference point image corresponding to a preset reference imaging point on a target surface image; the target surface image is any image in a plurality of surface images; acquiring a second reference point image corresponding to the reference imaging point on the surface standard image; performing super-pixel segmentation on the first reference point image to obtain a plurality of first sub-areas; performing super-pixel segmentation on the second reference point image to obtain a second sub-region corresponding to each first sub-region; and determining whether the surface of the air inlet of the target aircraft has surface burn or not according to the first subarea and the second subarea.
Optionally, the determining module 402 is further configured to: acquiring a first color histogram of each first sub-region and a second color histogram of the corresponding second sub-region; calculating the difference value of the pixel frequency of each first color histogram and the pixel frequency of each second color histogram to obtain a plurality of pixel frequency difference values; calculating root mean square values of a plurality of pixel frequency differences; and if the root mean square value is greater than or equal to a first root mean square threshold value, determining that the surface of the aircraft air inlet is burnt.
By adopting the device, a plurality of continuous surface images of the target aircraft air inlet can be obtained, wherein the surface images of two adjacent aircraft air inlet pipelines have a superposition area, whether the surface of the target aircraft air inlet is damaged is determined according to the surface images and the preset surface standard image, the ground service staff is not required to perform visual inspection, the detection efficiency is greatly improved, and the problem that visual inspection is easy to miss under the condition that the damage degree of the surface of the aircraft air inlet is smaller is avoided, so that the detection result is more accurate.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
By way of example, fig. 5 is a block diagram of an electronic device 50 shown in an embodiment of the present disclosure. For example, the electronic device 50 may be provided as a terminal. Referring to fig. 5, the electronic device 50 comprises a processor 501, which may be one or more in number, and a memory 502 for storing a computer program executable by the processor 501. The computer program stored in memory 502 may include one or more modules each corresponding to a set of instructions. Further, the processor 501 may be configured to execute the computer program to perform the method of detecting an aircraft inlet described above.
In addition, the electronic device 50 may further include a power supply component 503 and a communication component 504, the power supply component 503 may be configured to perform power management of the electronic device 50, and the communication component 504 may be configured to enable communication of the electronic device 50, e.g., wired or wireless communication. In addition, the electronic device 50 may also include an input/output (I/O) interface 505. The electronic device 50 may operate based on an operating system stored in the memory 502, such as Windows Server, mac OS XTM, unixTM, linuxTM, or the like.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the above-described method of detecting an aircraft inlet. For example, the computer readable storage medium may be the memory 502 described above including program instructions executable by the processor 501 of the electronic device 50 to perform the method of detecting aircraft air intake as described above.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (8)

1. A method of detecting an aircraft inlet, comprising:
acquiring a plurality of continuous surface images of a target aircraft air inlet, wherein the surface images of two adjacent aircraft air inlet pipelines have overlapping areas;
determining whether the surface of the air inlet channel of the target aircraft is damaged or not according to the surface images and the preset surface standard image;
the damage comprises deformation damage, and the determining whether the surface of the air inlet channel of the target aircraft is damaged according to the surface images and the preset surface standard image comprises the following steps:
carrying out three-dimensional reconstruction on the surface of the air inlet of the aircraft according to the plurality of surface images to obtain a three-dimensional model image of the surface of the air inlet of the aircraft, wherein the three-dimensional model image comprises a three-dimensional model of the surface of the air inlet of the aircraft;
determining whether deformation damage exists on the surface of the aircraft air inlet according to the three-dimensional model image and the surface standard image;
the damage comprises surface burn, and the determining whether the surface of the air inlet of the target aircraft is damaged according to the surface images and the preset surface standard image comprises the following steps:
acquiring a first reference point image corresponding to a preset reference imaging point on a target surface image; the target surface image is any image in a plurality of surface images;
acquiring a second reference point image corresponding to the reference imaging point on the surface standard image;
performing super-pixel segmentation on the first reference point image to obtain a plurality of first sub-areas;
performing super-pixel segmentation on the second reference point image to obtain a second sub-region corresponding to each first sub-region;
determining whether surface burn exists on the surface of the air inlet channel of the target aircraft according to the first subarea and the second subarea;
the method further comprises the steps of:
determining whether a surface of the three-dimensional model of the aircraft inlet surface meets curvature continuity;
the determining whether deformation damage exists on the surface of the aircraft air inlet according to the three-dimensional model image and the surface standard image comprises the following steps:
and under the condition that the surface of the three-dimensional model of the surface of the aircraft air inlet meets the curvature continuity, determining whether deformation damage exists on the surface of the aircraft air inlet according to the three-dimensional model image and the surface standard image.
2. The method of claim 1, wherein said determining whether deformation damage exists to the aircraft inlet surface from the three-dimensional model image and the surface standard image comprises:
acquiring a first point cloud corresponding to the three-dimensional model image and a second point cloud corresponding to the surface standard image;
calculating Hausdorff distance of the first point cloud and the second point cloud by utilizing an iterative closest point ICP algorithm;
and if the Haoskov distance is greater than or equal to a preset distance threshold, determining that deformation damage exists on the surface of the aircraft air inlet.
3. The method of claim 1, wherein the determining whether a surface burn exists on the target aircraft inlet surface from the first sub-region and the second sub-region comprises:
acquiring a first color histogram of each first sub-region and a second color histogram of the corresponding second sub-region;
calculating the difference value of the pixel frequency of each first color histogram and the pixel frequency of each second color histogram to obtain a plurality of pixel frequency difference values;
calculating root mean square values of a plurality of pixel frequency differences;
and if the root mean square value is greater than or equal to a first root mean square threshold value, determining that the surface of the aircraft air inlet is burnt.
4. An apparatus for detecting an aircraft inlet, comprising:
the acquisition module is used for acquiring a plurality of continuous surface images of the air inlet channel of the target aircraft, wherein the surface images of the air inlet channel of two adjacent aircraft have overlapping areas;
the determining module is used for determining whether the surface of the air inlet channel of the target aircraft is damaged or not according to the surface images and the preset surface standard image;
the damage includes deformation damage, and the determining module is configured to:
carrying out three-dimensional reconstruction on the surface of the air inlet of the aircraft according to the plurality of surface images to obtain a three-dimensional model image of the surface of the air inlet of the aircraft, wherein the three-dimensional model image comprises a three-dimensional model of the surface of the air inlet of the aircraft;
determining whether deformation damage exists on the surface of the aircraft air inlet according to the three-dimensional model image and the surface standard image;
the damage includes a surface burn, and the determination module is to:
acquiring a first reference point image corresponding to a preset reference imaging point on a target surface image; the target surface image is any image in a plurality of surface images;
acquiring a second reference point image corresponding to the reference imaging point on the surface standard image;
performing super-pixel segmentation on the first reference point image to obtain a plurality of first sub-areas;
performing super-pixel segmentation on the second reference point image to obtain a second sub-region corresponding to each first sub-region;
determining whether surface burn exists on the surface of the air inlet channel of the target aircraft according to the first subarea and the second subarea;
the apparatus further comprises:
the curvature determining module is used for determining whether the surface of the three-dimensional model of the surface of the aircraft air inlet meets curvature continuity or not;
the determining module is specifically configured to:
and under the condition that the surface of the three-dimensional model of the surface of the aircraft air inlet meets the curvature continuity, determining whether deformation damage exists on the surface of the aircraft air inlet according to the three-dimensional model image and the surface standard image.
5. The apparatus of claim 4, wherein the means for determining is further for:
acquiring a first point cloud corresponding to the three-dimensional model image and a second point cloud corresponding to the surface standard image;
calculating Hausdorff distance of the first point cloud and the second point cloud by utilizing an iterative closest point ICP algorithm;
and if the Haoskov distance is greater than or equal to a preset distance threshold, determining that deformation damage exists on the surface of the aircraft air inlet.
6. The apparatus of claim 4, wherein the means for determining is further for:
acquiring a first color histogram of each first sub-region and a second color histogram of the corresponding second sub-region;
calculating the difference value of the pixel frequency of each first color histogram and the pixel frequency of each second color histogram to obtain a plurality of pixel frequency difference values;
calculating root mean square values of a plurality of pixel frequency differences;
and if the root mean square value is greater than or equal to a first root mean square threshold value, determining that the surface of the aircraft air inlet is burnt.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method of any of claims 1 to 3.
8. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 3.
CN201910551364.1A 2019-06-24 2019-06-24 Method and device for detecting aircraft air inlet, storage medium and electronic equipment Active CN110379000B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910551364.1A CN110379000B (en) 2019-06-24 2019-06-24 Method and device for detecting aircraft air inlet, storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910551364.1A CN110379000B (en) 2019-06-24 2019-06-24 Method and device for detecting aircraft air inlet, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN110379000A CN110379000A (en) 2019-10-25
CN110379000B true CN110379000B (en) 2023-06-30

Family

ID=68249228

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910551364.1A Active CN110379000B (en) 2019-06-24 2019-06-24 Method and device for detecting aircraft air inlet, storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN110379000B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114399694B (en) * 2022-01-14 2025-03-21 上海航空工业(集团)有限公司 A pre-flight detection method, device and equipment based on aircraft component status recognition
CN116310126B (en) * 2023-03-23 2023-11-03 南京航空航天大学 Three-dimensional reconstruction method and system for aircraft inlet based on cooperation goals

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108394426A (en) * 2017-02-02 2018-08-14 淡水河谷公司 Railway wheel monitors system and method
CN109754019A (en) * 2019-01-10 2019-05-14 燕山大学 A Method for Continuous Monitoring of Boiler Combustion Condition
CN109801374A (en) * 2019-01-14 2019-05-24 盾钰（上海）互联网科技有限公司 A kind of method, medium and system reconstructing threedimensional model by multi-angle image collection

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106558053B (en) * 2015-09-25 2019-06-21 株式会社理光 Object segmentation methods and Object Segmentation device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108394426A (en) * 2017-02-02 2018-08-14 淡水河谷公司 Railway wheel monitors system and method
CN109754019A (en) * 2019-01-10 2019-05-14 燕山大学 A Method for Continuous Monitoring of Boiler Combustion Condition
CN109801374A (en) * 2019-01-14 2019-05-24 盾钰（上海）互联网科技有限公司 A kind of method, medium and system reconstructing threedimensional model by multi-angle image collection

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"图像处理在彩色印刷品质量检测中的应用研究";张洋;《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》;20180115(第1期);第53-62页 *
基于三维激光扫描技术的变形监测方法研究;张小青;《北京测绘》;20160625(第03期);第53-56页 *

Also Published As

Publication number Publication date
CN110379000A (en) 2019-10-25

Similar Documents

Publication Publication Date Title
CN107480644B (en) Optic disc positioning and segmentation method, device and storage medium in fundus image
JP7150468B2 (en) Structural deterioration detection system
US12106438B2 (en) Point cloud annotation device, method, and program
CN107091636B (en) A method for measuring vegetation area and length by unmanned aerial vehicle
WO2006137438A1 (en) House displacement judging method, house displacement judging device
CN110379000B (en) Method and device for detecting aircraft air inlet, storage medium and electronic equipment
CN108364292B (en) Illumination estimation method based on multiple visual angle images
US20210110565A1 (en) Device, system, method, and program for cloud observation
JP6249508B2 (en) Change detection support device, change detection support method, and program
CN119091333B (en) Forest accumulation monitoring and analyzing method and system based on remote sensing technology
CN113190031B (en) Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle
CN110910379A (en) Incomplete detection method and device
CN112950565A (en) Method and device for detecting and positioning water leakage of data center and data center
EP3930306A2 (en) Method and apparatus for stabilizing image, roadside device and cloud control platform
CN102322864B (en) An Airborne Optical Robust Scene Matching Navigation and Positioning Method
CN110570929A (en) Structure display method and device, computer equipment and storage medium
CN113844674B (en) Fastener installation state detection method and device, electronic equipment and medium
CN110610492B (en) Method and system for identifying external damage of full-size blade of in-service fan, storage medium and terminal
US12067727B2 (en) Visibility determination system, visibility determination method, and non-transitory computer-readable medium
CN111985497A (en) Method and system for identifying crane operation under overhead transmission line
CN110349130B (en) Method and device for detecting aircraft air inlet and storage medium
CN119068096B (en) A method for 3D digitization of ancient buildings based on multi-source data fusion of surveying and mapping geographic information
CN119693351A (en) A transmission line icing early warning method and system based on image technology
Zeng et al. An improved extraction method of individual building wall points from mobile mapping system data
CN119579792A (en) Dynamic discharge channel three-dimensional self-adaptive reconstruction method and related device based on multiple high-speed cameras

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20210301

Address after: 201111 2nd floor, building 2, no.1508, Kunyang Road, Minhang District, Shanghai

Applicant after: Dalu Robot Co.,Ltd.

Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.)

Applicant before: CLOUDMINDS (SHENZHEN) ROBOTICS SYSTEMS Co.,Ltd.

CB02 Change of applicant information
CB02 Change of applicant information

Address after: 201111 Building 8, No. 207, Zhongqing Road, Minhang District, Shanghai

Applicant after: Dayu robot Co.,Ltd.

Address before: 201111 2nd floor, building 2, no.1508, Kunyang Road, Minhang District, Shanghai

Applicant before: Dalu Robot Co.,Ltd.

GR01 Patent grant
GR01 Patent grant