Method for inspecting an object

Abstract

A method for inspecting an object, the method comprising receiving or determining inspection image data, the inspection image data comprising an array of inspection image pixels, wherein at least one of the array of inspection image pixels has a pixel attribute associated therewith. The method comprises receiving, via a processor, a user input associated with a contiguous segment of the array of inspection image pixels. The method comprises determining an attribute of the object based on the pixel attributes associated with the contiguous segment of the array of inspection image pixels.

Description

Technical Field

[0001] This disclosure relates to a method for inspecting objects, such as a method for inspecting gas turbine engine components using a visual image recording device. Background Technology

[0002] Known methods for inspecting objects include using visual image recording devices (such as cameras) to generate one or more inspection images and using a 3D model of the object. In this way, these known inspection methods typically require access to the 3D model of the object to complete the inspection. Attached Figure Description

[0003] The specification with reference to the accompanying drawings sets forth a complete and feasible disclosure for those skilled in the art, including its best mode, wherein:

[0004] Figure 1A This is a perspective view of a three-dimensional (3D) model of an object and a virtual visual image recording device according to exemplary embodiments of the present disclosure.

[0005] Figure 1B This is based on exemplary embodiments of the present disclosure. Figure 1A 3D models of objects and stereoscopic images of virtual visual image recording devices.

[0006] Figure 1C This is based on exemplary embodiments of the present disclosure. Figure 1A 3D models of objects and stereoscopic images of virtual visual image recording devices.

[0007] Figure 2 It is part of a guide image pixel array according to an exemplary embodiment of the present disclosure.

[0008] Figure 3A This is a display of exemplary embodiments according to the present disclosure. Figure 2 A table of multiple pixel attributes of the guiding image pixels.

[0009] Figure 3B This is a display of exemplary embodiments according to the present disclosure. Figure 2 A table of pixel attributes for the guiding image pixels.

[0010] Figure 4 This is a visual depiction of an algorithm for determining one or more pixel attributes of a guide image pixel according to exemplary embodiments of the present disclosure.

[0011] Figure 5 This is a visual depiction of an algorithm for determining pixel attributes of a guide image pixel according to exemplary embodiments of the present disclosure.

[0012] Figure 6This is a visual depiction of an algorithm for determining pixel attributes of a guide image pixel according to exemplary embodiments of the present disclosure.

[0013] Figure 7 This is a visual depiction of an algorithm for determining pixel attributes of a guide image pixel according to exemplary embodiments of the present disclosure.

[0014] Figure 8 This describes exemplary embodiments according to the present disclosure. Figure 1A A simplified image of a 3D model of an object.

[0015] Figure 9 This is a flowchart illustrating a simplified image for determining pixel attributes and creating a 3D model according to an exemplary embodiment of the present disclosure.

[0016] Figure 10 It is an inspection image of an object according to an exemplary embodiment of the present disclosure.

[0017] Figure 11 This is based on exemplary embodiments of the present disclosure. Figure 10 A simplified image of the inspected image.

[0018] Figure 12 This is based on exemplary embodiments of the present disclosure. Figure 10 The inspected image is an array of pixels.

[0019] Figure 13 This is a method for estimating the orientation of an object according to exemplary embodiments of the present disclosure.

[0020] Figure 14 This is a flowchart illustrating a method for determining the properties of an object according to an exemplary embodiment of the present disclosure.

[0021] Figure 15 It is specified according to exemplary embodiments of this disclosure that has Figure 12 The inspected image is a portion of the inspected image's pixel array.

[0022] Figure 16 It is specified according to exemplary embodiments of this disclosure that has Figure 12 The inspected image is a portion of the inspected image's pixel array.

[0023] Figure 17 It is specified according to exemplary embodiments of this disclosure that has Figure 12 The inspected image is a portion of the inspected image's pixel array.

[0024] Figure 18 This is a flowchart illustrating a method for determining the properties of an object according to an exemplary embodiment of the present disclosure.

[0025] Figure 19 This is a flowchart illustrating a method for storing an inspection package of objects according to an exemplary embodiment of the present disclosure.

[0026] Figure 20 This is a flowchart illustrating a method for comparing a first attribute of an object with a second attribute of the object according to an exemplary embodiment of the present disclosure.

[0027] Figure 21 This is a block diagram of a computing system according to exemplary embodiments of the present disclosure.

[0028] Figure 22 This is a block diagram of an inspection system according to exemplary embodiments of the present disclosure. Detailed Implementation

[0029] Reference will now be made in detail to the present embodiments of this disclosure, one or more examples of which are illustrated in the accompanying drawings. The detailed description uses numerals and letter reference numerals to denote features in the drawings. Similar or analogous reference numerals in the drawings and description have been used to denote similar or analogous portions of this disclosure.

[0030] The term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any implementation described herein as "exemplary" is not necessarily to be construed as superior or better than other implementations. Furthermore, unless explicitly stated otherwise, all embodiments described herein should be considered exemplary.

[0031] Unless otherwise stated herein, the terms “connection,” “fixed,” “attached to,” etc., refer to both direct connection, fixation, or attachment, and indirect connection, fixation, or attachment via one or more intermediate components or features.

[0032] As used herein, the terms “first,” “second,” and “third” are used interchangeably to distinguish one component from another and are not intended to indicate the location or importance of the individual components.

[0033] Unless the context clearly indicates otherwise, the singular forms “a,” “one,” and “the” include plural references.

[0034] As used throughout the specification and claims, approximate language is applied to modify any quantitative expression that may allow for variation without altering its underlying function. Therefore, values ​​modified by terms such as “about,” “approximately,” and “substantially” are not limited to specified precise values. In at least some cases, approximate language may correspond to the precision of the instrument used to measure the value, or the precision of the method or machine used to construct or manufacture the component and / or system. For example, approximate language may refer to a margin of 1%, 2%, 4%, 10%, 15%, or 20%. These approximate margins may be applied to a single value, to either end of a range defining a numerical range, or to margins between two ends, and / or between the ends.

[0035] Throughout this specification and claims, scope limitations are combined and interchanged, and unless the context or language otherwise indicates otherwise, such scopes are identified and include all subscopes contained herein. For example, all scopes disclosed herein include endpoints, and endpoints may be combined independently of each other.

[0036] The inventors of this disclosure have discovered that it may be beneficial to inspect objects without accessing their 3D models. Improved inspection methods will be welcomed in the field of component inspection.

[0037] According to one or more embodiments described herein, a method for inspecting an object is provided. The method includes determining guide image data of the object from a determined orientation, the guide image data including a guide image pixel array and pixel attributes of at least one guide image pixel in the guide image pixel array. The method also includes receiving inspection image data indicative of an inspection image. The method further includes associating the inspection image data with the guide image data, and determining attributes of the object based on the guide image data and the associated inspection image data. Determining the object's attributes based on the guide image data and the associated inspection image data has several advantages.

[0038] First, for example, after the guide image data of an object has been determined, determining the object's properties based on the guide image data and associated inspection image data allows the object to be inspected without using a 3D model. For example, and as will be described in more detail, for determining the orientation of an object, the guide image data can be determined from the 3D model. Once the guide image data is determined, the 3D model is no longer needed to determine the object's properties. Therefore, if the guide image data is determined, the object can be inspected without using, viewing, or sharing a 3D model of the object.

[0039] Inspecting an object without using, viewing, or sharing its 3D model has several advantages. For example, information within the 3D model may be proprietary information that is not intended to be disclosed to third parties (such as the user inspecting the object). Furthermore, some countries may have export compliance laws that may prohibit the export of 3D models abroad without an export license. However, sharing guide image data, which is information related to the 3D model of the object, is acceptable.

[0040] Second, determining object attributes based on guide image data and associated inspection image data can reduce the amount of time required to perform object inspections. For example, known inspection methods involve overlaying inspection images onto a 3D model and manually matching features between the inspection images and the 3D model. This direct overlaying, comparison, and matching with the 3D model can be very time-consuming. Therefore, determining object attributes based on guide image data and associated inspection image data can reduce the amount of time required to perform inspections.

[0041] According to one or more embodiments described herein, a method for inspecting an object is provided. The method includes determining inspectable image data, the inspectable image data including an array of inspectable image pixels, wherein each inspectable image pixel in the array of inspectable image pixels has a pixel attribute associated therewith. The method also includes receiving user input associated with a consecutive segment of inspectable image pixels in the array of inspectable image pixels. The method further includes determining attributes of an object based on the pixel attributes associated with the consecutive segments of inspectable image pixels in the array of inspectable image pixels. Determining the attributes of an object based on the pixel attributes associated with the received user input associated with the consecutive segments of inspectable image pixels in the array of inspectable image pixels has numerous advantages.

[0042] First, determining object attributes based on pixel attributes associated with received user input and linked to consecutive segments of inspected image pixels in the inspected image pixel array can have the advantage of comparing object attributes to thresholds. For example, the received user input can be associated with features on the object. In some examples, this feature could be damage to the object, such as cracks or debris on the object, or the location of peeling coating on the object. Therefore, measuring the feature to determine whether it is within acceptable limits can be beneficial. For example, cracks below a certain length are acceptable. However, cracks exceeding a certain length may require repair or replacement of the object.

[0043] Second, determining object attributes based on pixel attributes associated with received user input and linked to consecutive segments of inspected image pixels in an array of inspected image pixels can have the benefit of tracking and comparing the location or measurement of certain characteristics (e.g., damage to the object) between different objects. For example, the object could be a rotor blade, and the user input could be associated with a crack on the rotor blade. The determined object attributes could be the length of the crack and the location of the crack on the rotor blade. In one or more other inspection events inspecting other rotor blades, the user input could also be associated with a crack on the rotor blade, and the determined object attributes could also be the length of the crack and the location of the crack on the rotor blade. Crack sizes and locations on different rotor blades can be analyzed to determine trends. For example, an analysis can be performed to determine the most likely location of a crack on a rotor blade.

[0044] According to one or more embodiments described herein, a method for inspecting an object is provided. The method includes invoking a first inspection package, the first inspection package including a first inspected image of the object and a first designation. The method also includes receiving data instructing a second inspection package, the second inspection package including a second inspected image of the object and a second designation. The method further includes receiving, invoking, or receiving and invoking one or more attribute maps of the object. The method also includes determining a first attribute of the object based on the first inspected image of the object, the one or more attribute maps of the object, and the first designation. The method also includes determining a second attribute of the object based on the second inspected image of the object, the one or more attribute maps of the object, and the second designation. The method further includes displaying the first attribute and the second attribute and / or comparing the first attribute with the second attribute.

[0045] In some aspects, the method includes receiving or invoking a first attribute map and receiving or invoking a second attribute map. In this case, the method can determine a first attribute of the object based on the first attribute map, and similarly, can determine a second attribute of the object based on the second attribute map.

[0046] In some respects, the method includes receiving or invoking a second attribute map. In this case, the method can determine the first attribute of the object based on the second attribute map, and similarly, can determine the second attribute of the object based on the second attribute map.

[0047] The method also includes displaying or comparing the first attribute with the second attribute. Displaying or comparing the first attribute with the second attribute has several advantages.

[0048] First, displaying or comparing a first attribute with a second attribute allows for the inspection of an object without using a 3D model of the object. For example, the first attribute is determined based on a first or second attribute mapping of the object, and the second attribute is similarly determined based on the same mapping. For a given orientation of the object, the first and second attribute mappings can be determined from the 3D model. Once the first and / or second attribute mappings are determined, the 3D model is no longer needed to determine the object's first or second attribute.

[0049] Inspecting an object without using, viewing, or sharing its 3D model has several advantages. For example, information within the 3D model may be proprietary information that is not intended to be disclosed to third parties (such as the user inspecting the object). Furthermore, some countries may have export compliance laws that may prohibit the export of 3D models abroad without an export license. However, sharing pixel attributes, which are information related to the object's 3D model, is acceptable.

[0050] Second, displaying or comparing the first attribute with the second attribute can reduce the amount of time required to perform an object inspection. For example, known inspection methods involve overlaying the inspection image onto a 3D model and manually matching features between the inspection image and the 3D model. This direct overlaying, comparison, and matching with the 3D model can be very time-consuming. Therefore, since the first and second attributes are determined based on the object's first attribute mapping or the object's second attribute mapping rather than the 3D model, comparing the first attribute with the second attribute can reduce the amount of time required to perform the inspection.

[0051] Third, displaying or comparing the first attribute with the second attribute allows for the measurement of features on an object over time. In some examples, this feature could be damage to the object, such as cracks or debris, or the location of a coating peeling off. Therefore, measuring the size of the feature to determine if it is within acceptable limits can be beneficial. For example, cracks below a certain length are acceptable. Furthermore, measuring a feature at two different points in time (e.g., at least three months apart and up to 20 years apart) can be beneficial to determine if the feature is growing and to predict when it will grow beyond an acceptable size. In yet another example, features (such as cracks) can be measured and compared on different objects, allowing for trend analysis. For example, analyzing the data to determine the most likely crack location or the most likely crack size can be useful.

[0052] Fourth, in some examples, both the first and second attributes of an object are determined based on the object's second attribute mapping. This ensures a comparable comparison between the first and second attributes. This can be important when the algorithm used to determine the first attribute mapping differs from the algorithm used to determine the second attribute mapping. Because algorithms may change over time due to optimization or improvement, the first attribute mapping may differ from the second attribute mapping. Since the first attribute mapping may differ from the second attribute mapping, it may be beneficial to redetermine the first attribute using the object's second attribute mapping (using the first inspection image and the first specification) to ensure a comparable comparison with the second attribute. It is worth noting that in this case, a 3D model is not required.

[0053] Referring to the accompanying drawings, the same numbers indicate the same elements in all the drawings. Figure 1A A perspective view of a three-dimensional (3D) model 200 (also referred to as a “computer model”) of an object 100 and a virtual visual image recording device 230 according to exemplary embodiments of the present disclosure is provided. As used herein, an “object” can be a component, a part of a component, an assembly comprising multiple components, or a part of an assembly. Although shown in black and white in the figures, it should be understood that the 3D model 200 can be a shaded 3D model (e.g., a 3D model 200 with a grayscale color scheme) to provide additional visual detail, such as the curvature of a component. In one example, the 3D model 200 can be created using 3D modeling software. For example, the 3D model 200 can be created using computer-aided design (CAD) software. In another example, the 3D model 200 can be created by 3D scanning a real-world object (e.g., a control object). The control object can be a sample with known dimensions and / or mass. The virtual visual image recording device 230 can represent any suitable imaging device, including any optical sensor capable of capturing still or moving images, such as a camera. Suitable types of cameras can be CMOS cameras, CCD cameras, digital cameras, video cameras, or any other type of device capable of capturing images. Further consideration could be the use of a endoscopic camera or a portal camera. Additionally, the visual image recording device could be a monocular or binocular camera.

[0054] The 3D object 100 can be positioned in front of the virtual visual image recording device 230 in a "pose". More specifically, the 3D object 100 can be positioned in a defined orientation. As used herein, "orientation" refers to the physical position of object 100. For example, "orientation" can refer to the relative position of one object 100 with respect to another object 100. For example, as referenced... Figure 1AThe orientation used here refers to the relative physical position of the 3D object 100 with respect to the virtual visual image recording device 230. Alternatively or additionally, "orientation" may refer to the positioning of six degrees of freedom—position on the X-axis (surge), position on the Y-axis (sway), position on the Z-axis (undulation), tilt on the X-axis (roll), tilt on the Y-axis (pitch), and tilt on the Z-axis (yaw).

[0055] refer to Figure 1B According to exemplary embodiments of this disclosure, a 3D model 200 of object 100 is provided and Figure 1A A perspective view of the virtual visual image recording device 230. As shown, multiple rays 235 can be projected from a position associated with the virtual visual image recording device 230. Although the virtual visual image recording device 230 is depicted, it should be understood that the virtual visual image recording device 230 is not required. For example, rays 235 can be projected from a specific point 232 located at a specific position relative to the object 100.

[0056] refer to Figure 1C According to exemplary embodiments of this disclosure, a 3D model 200 of object 100 is provided and Figure 1A A stereoscopic view of the virtual visual image recording device 230. Multiple rays 235 projected onto the object 100. Figure 1B An array of guide image pixels 251, guide image pixel array 250, is created. Each guide image pixel 251 is a subdivision of the surface of object 100 created by ray 235. It should be understood that, for clarity, the size of each guide image pixel 251 is exaggerated in the figure. For example, the size of the guide image pixel 251 can range from about 0.05 mm to about 5 mm.

[0057] As seen in this view, at least some, and sometimes all, of the guide image pixels 251 can be irregularly shaped, such that they have edges and angles of any shape and size. Furthermore, the shape and size of the edges and angles can differ among the guide image pixels 251 of the guide image pixel array 250. For example, the shape of each guide image pixel 251 can depend on the position and shape of the surface of the object 100 on which the corresponding ray 235 is projected.

[0058] refer to Figure 2A portion of a guide image pixel array 250 is provided according to an exemplary embodiment of the present disclosure. The guide image pixel array 250 may include a plurality of guide image pixels 251. Although only nine guide image pixels 251 are shown in this view, the guide image pixel array 250 may include any number of guide image pixels 251. For example, the guide image pixel array 250 may include more than half a million guide image pixels 251, such as more than one million guide image pixels 251, such as more than two million guide image pixels 251, and up to one hundred million guide image pixels 251. The number of guide image pixels 251 within the guide image pixel array 250 may depend on a variety of factors, such as user preference, computing power, screen resolution, the size of object 100, the projection position of ray 235, and / or the number of rays 235.

[0059] Each guide image pixel 251 within the guide image pixel array 250 may have another guide image pixel 251 adjacent to it, which is an adjacent guide image pixel 253. An adjacent guide image pixel 253 is a guide image pixel 251 that shares a common edge with another guide image pixel 251. For example, in... Figure 2 In the example, the guide image pixel 251', which is the guide image pixel B2 (column, row position), has eight adjacent guide image pixels 253: A1, A2, A3, B1, B3, C1, C2, and C3 (column, row positions).

[0060] refer to Figure 3A An exemplary embodiment of the present disclosure provides a display Figure 2 Table 260 shows the multiple pixel attributes 252 of the guide image pixel 251'. Specifically, for Figure 3A As an example, Table 260 is Figure 2Multiple pixel attributes 252 of the guide image pixel 251' at position B2. One or more pixel attributes 252 of at least one of the guide image pixels 251 within the guide image pixel array 250 can be determined. In some examples, one or more pixel attributes 252 of each guide image pixel 251 within the guide image pixel array 250 can be determined. As used herein, "attribute mapping" refers to one or more pixel attributes 252 of at least one of the guide image pixels 251 within the guide image pixel array 250 of object 100. Pixel attributes 252 can be determined, for example, by deciding, calculating, estimating, or measuring. As will be explained in more detail, pixel attributes 252 can be information associated with the guide image pixel 251. For example, pixel attributes 252 can be size, distance, position, feature, color, surface tilt, classification, threshold, criticality, etc. When pixel attribute 252 is distance, the distance can be Euclidean distance or geodesic distance. When pixel attribute 252 is distance or size, the measurement, calculation, or estimation can take into account the topology of the 3D object 100. For example, pixel attribute 252 can be a numerical value, a text value, a binary value, a quantitative value, a qualitative value, a categorical value, a symbolic value, or a combination thereof. In some examples, pixel attribute 252 of guide image pixel 251 may be unavailable or nonexistent. For example, when pixel attribute 252 is unavailable or nonexistent, pixel attribute 252 may be represented as "0" or "Nan". Although this document describes determining pixel attributes for each guide image pixel 251, it should be understood that this is not necessarily the case. Pixel attributes can be determined for any group of guide image pixels 251 that includes only a single guide image pixel. It should also be understood that pixel attributes can be determined for a subset of guide image pixels, and such guide image pixels do not need to be adjacent.

[0061] In this example, pixel attribute 252 is a set of distances 263. This set of distances can be the distance from guide image pixel 251 to the adjacent guide image pixel 253. Distance 263 can be determined by calculation, estimation, or measurement. In this example, distance 263 is from the center of guide image pixel 251' at position B2 to the center of each adjacent guide image pixel 253 (pixels at positions A1-A3, B1, B3, and C1-C3). Therefore, in Figure 3A In one embodiment, the pixel attribute 252 of the guide image pixel 251' at position B2 includes eight distances.

[0062] refer to Figure 3B An exemplary embodiment of the present disclosure provides a display Figure 2Table 260 shows the additional pixel attributes 252 of the guide image pixel 251' at position B2. In this example, object 100 is a rotor blade of a gas turbine engine, and the pixel attributes 252 of the guide image pixel 251' can include other information or data. The area, surface tilt, and surface color of the guide image pixel 251' can be included in pixel attributes 252. The angle and length of the ray 235 to the center of the guide image pixel 251' can be included in pixel attributes 252. Furthermore, information about whether the guide image pixel 251' includes cooling holes for the rotor blade and the location of the guide image pixel 251' can be included in pixel attributes 252. For example, when object 100 is a rotor blade of a gas turbine engine, this location can be classified as leading edge, trailing edge, airfoil, platform, etc. Other calculations, estimates, or measurements can also be included in pixel attributes 252. For example, in this example, the distances from each location of the guide image pixel 251' to other locations of the guide image pixel 251' are included in pixel attributes 252. Although only a few examples of data that can be included in the guide image pixel attribute 252 are provided, it should be understood that other data can be included in the guide image pixel attribute 252. For example, the angle of each corner, the angle of ray 235 to each corner, the angle of ray 235 to the middle of each edge, the distance 263 from each corner, etc.

[0063] refer to Figure 4 A visual depiction of an algorithm 259 for determining one or more pixel attributes 252 of a guide image pixel 251 is provided according to exemplary embodiments of the present disclosure. As used herein, an "algorithm" refers to a set of instructions for achieving a specific objective. For example, there are various ways to achieve the objective of determining the distance between one guide image pixel 251 and another guide image pixel 251. An algorithm for achieving the objective of determining the distance between guide image pixels 251 can be a specific set of instructions regarding how to determine the distance between guide image pixels 251.

[0064] Still referencing Figure 4 Pixel attribute 252 can be a set of distances 263, which can be determined as mentioned. For example, this set of distances 263 could be the distance 263 from guide image pixel 251 to its neighboring guide image pixel 253. Figure 4 In the example, the distance 263 from the center of the guide image pixel 251 to each adjacent guide image pixel 253 is calculated, estimated, or measured. The distance, represented as the distance of a straight line from the center of the guide image pixel 251 to the center of the adjacent guide image pixel 253, can be stored as a numerical value in table 260 (e.g., ...). Figure 3A or Figure 3B In Table 260).

[0065] refer to Figure 5A visual depiction of an algorithm 259 for determining pixel attributes 252 of a guide image pixel 251 is provided according to an exemplary embodiment of the present disclosure. More specifically, an algorithm 259 for determining a set of distances 263 is provided according to an exemplary embodiment of the present disclosure. In this example, the distance 263 from the center of the guide image pixel 251 to the nearest region of an adjacent guide image pixel 253 can be calculated, estimated, or measured. This can be repeated for each adjacent guide image pixel 253 to determine a set of distances 263. The distance 263, represented as a straight line from the center of the guide image pixel 251 to the nearest region of an adjacent guide image pixel 253, can be stored as a numerical value in a table 260 (e.g., Figure 3A or Figure 3B (in the table).

[0066] refer to Figure 6 A visual depiction of an algorithm 259 for determining pixel attributes 252 of a guide image pixel 251 is provided according to an exemplary embodiment of the present disclosure. More specifically, an algorithm 259 for determining a set of distances 263 is provided according to an exemplary embodiment of the present disclosure. In this example, the distance 263 from the first adjacent guide image pixel 253a to the second adjacent guide image pixel 253b can be calculated, estimated, or measured by constructing a straight line from the middle of the edge or corner of the first adjacent guide image pixel 253a, through the guide image pixel 251, to the middle of the edge or corner of the second adjacent guide image pixel 253b. This can be repeated for each adjacent guide image pixel 253 to determine a set of distances. Pixel attribute 252 is represented as the distance 263 of the straight line traveling through the guide image pixel 251, and pixel attribute 252 can be stored as a value in a table 260 (e.g., Figure 3A or Figure 3B (in the table).

[0067] refer to Figure 7 A visual depiction of an algorithm 259 for determining pixel attributes 252 of a guide image pixel 251 is provided according to an exemplary embodiment of the present disclosure. More specifically, an algorithm 259 for determining a set of distances 263 is provided according to an exemplary embodiment of the present disclosure. In this example, the distance 263 from the first adjacent guide image pixel 253a to the second adjacent guide image pixel 253b can be calculated, estimated, or measured by constructing the shortest straight-line path from the first adjacent guide image pixel 253a to the center of the guide image pixel 251, and then constructing the shortest straight-line path from the center of the guide image pixel 251 to the second adjacent guide image pixel 253b. This can be repeated for each adjacent guide image pixel 253 to determine a set of distances. Pixel attribute 252 is represented as the distance 263 of a straight line traveling through the guide image pixel 251, and pixel attribute 252 can be stored as a value in a table 260 (e.g., Figure 3A or Figure 3B (in the table).

[0068] As will be further understood from the discussion below, one or more of the above-described algorithms 259 can be used to determine a distance or area on an inspected image in response to a user input selection associated with a continuous segment of inspected image pixels. However, it is worth noting that, in order to utilize the pixel attributes 252 of the guide image pixels 251 of the guide image, the inspected image may need to be associated with the guide image so that the pixel attributes 252 of the guide image pixels 251 are used in response to user input. These aspects are described in more detail below.

[0069] Now for reference Figure 8 An exemplary embodiment of the present disclosure is provided, depicting... Figure 1A A simplified image 210 of a 3D model 200 of object 100. As shown, the simplified image 210 may be a two-dimensional (2D) line drawing of the 3D model 200 in a defined orientation. In other examples, the simplified image 210 is a 2D image that realistically depicts the 3D model 200. For example, the simplified image 210 may be a 2D grayscale image or a 2D color image. In at least one example, the simplified image 210 is an image that makes it look like a photograph of the object. For example, the simplified image 210 may have the same or similar appearance, style, color, shading, etc., as a photograph of the object. The simplified image 210 may depict only key features 220. Key features 220 may be the most relevant and / or prominent features. For example, and referring to... Figure 8 An example, which provides Figure 1A A simplified image 210 of the 3D model 200 of the rotor blades may include lines representing the shape of the outer periphery 220a, the tip 220b, the shape of the blade platform 220c, and the dovetail root 220d. However, other features, such as cooling holes, may be represented. As will be explained in more detail, creating the simplified image 210 can help determine the orientation of the object 100 and associated pixel attributes 252.

[0070] refer to Figure 9According to exemplary embodiments of the present disclosure, a method 300 is provided for determining pixel attributes 252 and creating a simplified image 210 of a 3D model 200. Method 300 may include step 310 of creating a 3D model 200 of an object 100 in a determined orientation. Method 300 may include step 320 of creating a guide image pixel array 250. Method 300 may include step 330 of determining pixel attributes 252 (attribute mapping) of at least one guide image pixel 251 in the guide image pixel array 250. Attributes may include, but are not limited to, size attributes, area attributes, depth information, etc. Method 300 may include step 340 of creating a simplified image 210 of the 3D model 200 in a determined orientation. In some examples, method 300 does not include step 340. As will be further explained, steps of other methods may be performed using a 3D model instead of the simplified image 210 of the 3D model 200. Furthermore, the timing of step 340 is not affected by the timing of when other steps of method 300 are performed.

[0071] Method 300 can be repeated multiple times. For example, it may be beneficial to perform method 300 for various determined orientations of 3D model 200. For example, method 300 can be repeated up to two hundred times (e.g., fifty to one hundred and fifty times), each time for a different determined orientation of 3D model 200. Thus, for each determined orientation of 3D model 200, one or more pixel attributes 252 of at least one guide image pixel 251 in guide image pixel array 250 can be determined. Furthermore, for each determined orientation of 3D model 200, a simplified image 210 of 3D model 200 of object 100 can be created on the determined orientation. As will be explained later, the determined orientation can be associated with 3D model 200, the simplified image 210 of 3D model 200, or an inspection image.

[0072] Each of the various defined orientations can vary slightly. For example, the various defined orientations can vary up to 2 mm on the X, Y and / or Z axes, and / or tilt within 2 degrees on the X, Y and Z axes.

[0073] refer to Figure 10An inspection image 400 of an object 100 is provided according to an exemplary embodiment of the present disclosure. The inspection image 400 may be a picture of the object 100, in this example, the object 100 is a real-world object. The inspection image may be generated using a visual image recording device (e.g., the visual image recording device 230 described above). Inspection image data indicative of the inspection image may be generated. The inspection image data may include the inspection image 400, the capture date (the date or date and time on which the inspection image 400 was generated), the number of cycles, the number of operating hours, the location where the inspection image 400 was generated, an identifier of the object 100 being inspected, an identifier of the user operating the visual image recording device when the inspection image 400 was generated, the positioning of the visual image recording device when the inspection image 400 was generated, etc.

[0074] A visual image recording device can be a component of an inspection tool assembly. The inspection tool assembly helps the operator take photographs in a desired orientation. Therefore, images (such as...) can be taken in the desired orientation. Figure 10 (Image). However, due to various factors, there may be variations in the image orientation associated with the visual image recording device. These factors may include tolerances (e.g., component tolerances, assembly tolerances, and mounting tolerances), and / or mechanical wear in the inspection tool assembly. Thus, the actual orientation of object 100 relative to the visual image recording device may deviate from the desired orientation.

[0075] In some examples, a “stream” of inspection images 400 can be created, such as images of real-world objects. For instance, when the real-world object is a rotor blade of a gas turbine engine, a rotor system with the rotor blade mounted on it can rotate, and a series of images can be taken with a pipe-scope camera to create an image stream. In some cases, the inspection tool assembly may include a mounting structure configured to mount the pipe-scope camera to the gas turbine engine and through a pipe-scope opening (or other opening) to facilitate consistent positioning and orientation of the pipe-scope camera across multiple inspections of the same engine, and across multiple inspections of different engines of the same or similar models, to capture images of components (e.g., rotor blades) with consistent positioning and orientation.

[0076] For a more detailed explanation, an image of the orientation of the 3D model 200 or a simplified image 210 of the 3D model 200 can be selected for further analysis.

[0077] In some examples, images can be corrected. For instance, images can be corrected for any optical distortion to address lens and manufacturing variations in visual image recording devices and / or inspection tool components. Additionally or alternatively, images can be corrected to address relatively minor inconsistencies in the orientation of objects in the image relative to the orientation of 3D model 200 or a simplified image 210 of 3D model 200.

[0078] refer to Figure 11 Exemplary embodiments provided according to this disclosure Figure 10 The simplified image 410 of the inspection image 400 is shown. In this example, the simplified image 410 is displayed as a line drawing, and the object 100 is a rotor blade of a gas turbine engine. In other examples, the simplified image 410 of the object 100 may be a 2D grayscale image or a 2D color image. For example, the simplified image 410 may be a photograph of the object 100.

[0079] The simplified image 410 may depict key features 420. Key features 420 may be the most relevant and / or prominent features. For example, key features 420 may be the outer periphery 420a of the simplified image, the shape of the tip 420b, the blade platform 420c, or the adjoining portion 420d of a rotor blade with an adjacent rotor blade. However, other features may be represented, such as cooling holes in a non-limiting example.

[0080] Filters (such as the Canny edge detection filter or the Sobel filter) can be applied to images to help extract key features.420 However, other machine learning techniques (such as deep learning-based segmentation techniques) can be used to provide learned representations of the most prominent features.

[0081] refer to Figure 12 Exemplary embodiments provided according to this disclosure Figure 10 The inspection image 400 is an inspection image pixel array 450. As shown, the inspection image 400 of object 100 can be subdivided into inspection image pixels 451 to create the inspection image pixel array 450. In another example, a simplified image 410 of object 100 can be subdivided into an array of inspection image pixels 451 to form the inspection image pixel array 450. It should be understood that, for clarity, the size of each inspection image pixel 451 in the figure is exaggerated. Each inspection image pixel 451 can be of any size, and there can be any number of inspection image pixels 451 within the inspection image pixel array 450. The number of inspection image pixels 451 and / or the size of each inspection image pixel 451 can depend on the size and / or resolution of the inspection image 400. As will be explained in more detail, the inspection image pixel array 450 and / or the inspection image pixels 451 can be associated with the guide image pixel array 250 and / or the guide image pixels 251.

[0082] refer to Figure 13 An exemplary embodiment of the present disclosure provides a method 500 for estimating the orientation of an object 100. The method 500 may include obtaining the orientation of the object 100 (e.g., Figure 10 Step 510 involves creating an inspection image 400 of the object 100. Method 500 may include creating a simplified image 410 of the inspection image 400 (e.g., [image of the object]). Figure 11The simplified image 410) is used as a step 520. The method 500 may include a step 530 of estimating the orientation of the object 100. In at least one example, the method 500 includes steps 510, 520, and 530. In other examples, the method 500 does not include step 520, but includes steps 510 and 530.

[0083] The orientation of object 100 can be estimated by inputting an inspection image 400 or a simplified image 410 of object 100 into a pose recovery regression, which can be a machine learning network, such as a deep learning network. This network can be trained with synthetic data and can estimate the orientation of a real-world object based on the 2D inspection image 400 and / or the simplified image 410 of the inspection image 400. The synthetic data can be multiple training images with known external data. For example, the synthetic data can be multiple training images with known determined orientations. The training images can be simplified images 210, which can be 2D images that realistically depict the 3D model 200 or 2D images that only show the key features 220 of the 3D model 200. In some examples, the training images are images designed to resemble the inspection image 400. For example, the training images can have the same or similar appearance, style, color, shading, etc., as the inspection image 400.

[0084] The orientation of object 100 can be estimated by “matching” an inspection image 400 of object 100 or a simplified image 410 of object 100 with a simplified image 210 of 3D model 200. For example, as mentioned, a number of simplified images 210 of 3D model 200 can be created, each depicting 3D model 200 with a different, defined orientation. The simplified image 410 or inspection image 400 can be compared with one or more simplified images 210 of 3D model 200. The simplified image 210 of 3D model 200 that best matches the simplified image 210 of 3D model 200 can be selected by a person or by a computing system. The orientation of object 100 can then be estimated to be the same as or similar to the defined orientation of the 3D model 200 of the selected simplified image. For example, the estimated orientation of object 100 can be estimated within a specific tolerance of the defined orientation of the 3D model 200 of the selected simplified image. For example, specific tolerances may be within 3 mm on the X, Y, and Z axes, and within 5 degrees of tilt on the X, Y, and Z axes. When the orientation of the 3D model 200 is determined based on a 3D scan of a control object, additional tolerances may be considered due to the inherent potential tolerances of the 3D scanning machine and / or the tolerances of the control object.

[0085] In at least one example, the inspection image 400 or its simplified image 410 may be transformed. The inspection image 400 or its simplified image 410 may be transformed to correct residuals between the simplified image 210 of the 3D model 200 and the inspection image 400 or its simplified image 410. Transformations may include linear and rotational offsets, scaling, shearing, pinching / punching, distortion, tombstone correction, etc. The transformation may reduce the difference between the simplified image 410 of the inspection image 400 and the simplified image 210 of the 3D model 200, or it may reduce the difference between the inspection image 400 and the simplified image 210 of the 3D model. The transformation may occur before or after matching with the simplified image 210 of the 3D model 200.

[0086] Transformation data can be generated to record the amount and location of transformations performed to reduce the residuals between the simplified image 210 of the 3D model 200 and the inspection image 400 or the simplified image 410 of the inspection image 400. For example, the transformation data can be quantitative and / or qualitative values ​​describing the transformations. The transformation data can include six-degree-of-freedom orientation transformations. The transformation data can include information indicating a defined orientation of the inspection image 400 relative to guide image data associated with the object 100. For example, the transformation data can include information indicating six-degree-of-freedom orientation corrections performed to reduce the differences between the simplified image 210 of the 3D model 200 and the inspection image 400 or the simplified image 410 of the inspection image 400.

[0087] Generating transformation data has several benefits. For example, inspection image 400 or subsequent inspection image 400 (e.g., second inspection image 400) can be transformed using the transformation data at a later date or time. Furthermore, the transformation data can be used to transform guide image data.

[0088] Pixel attributes 252 created from the 3D model 200 of object 100 can be associated with inspection image 400. Pixel attributes 252 can be associated based on inspection image 400 (transformed or untransformed), a simplified image 410 of inspection image 400 (transformed or untransformed), an estimated orientation of inspection image 400, or a combination thereof.

[0089] For example, as previously described, the orientation of the inspection image 400 can be determined by matching an inspection image 400 of object 100 or a simplified image 410 of object 100 with a simplified image 210 of 3D model 200. The matching simplified image 210 of 3D model 200 may have an associated guide image pixel array 250, each of the guide image pixels 251 having one or more pixel attributes 252. The guide image pixel array 250, along with their pixel attributes 252, may be associated with the inspection image 400 of object 100 or the simplified image 410 of object 100. More specifically, at least one guide image pixel 251 of the simplified image 210 of 3D model 200 may be associated with at least one inspection image pixel 451 of the inspection image 400 of object 100 or the simplified image 410 of object 100.

[0090] In some examples, the association ratio between guide image pixel 251 and inspection image pixel 451 is 1:1. However, in another example, there is an uneven ratio, making the association ratio not 1:1. For example, more than one guide image pixel 251 may be associated with one inspection image pixel 451. In another example, more than one inspection image pixel 451 may be associated with one inspection image pixel 451. The higher or lower resolution of the visual image recording device used to generate the inspection image 450 compared to the resolution of the simplified image 210 of the 3D model 200 may result in an uneven ratio.

[0091] There are various ways to associate the guide image pixel 251 of the simplified image 210 of the 3D model 200 with the inspection image 400 or the simplified image 410 of the object 100. For example, the guide image pixel 251 can be “mapped” to the corresponding inspection image pixel 451. For example, the X and Y coordinates of the boundary of each guide image pixel 251 of the simplified image 210 of the 3D model 200 can be generated. The X and Y coordinates of the boundary of each inspection image pixel 451 of the inspection image 400 can be generated. Because the inspection image 400 or the simplified image 410 can be “matched” with the simplified image 210 of the 3D model 200, the X and Y coordinates of the inspection image 400 can be matched with the X and Y coordinates of the simplified image 210 of the 3D model 200. In fact, the inspection image 400 can be “overlapped” with the guide image pixel 251 of the simplified image 210 of the 3D model 200. Therefore, each guide image pixel 251 can be mapped to, or associated with, the corresponding inspection image pixel 451.

[0092] It should be noted that the inspection image pixel 451 may have a different size than the associated guide image pixel 251. For example, the guide image pixel 251 may be larger than the inspection image pixel 451 relative to the object 100. Therefore, two or more inspection image pixels 451 may be associated with the guide image pixel 251.

[0093] In another example, guide image pixels 251 of a simplified image 210 of 3D model 200 are "transferred" to inspection image 400. Information about the boundaries of each guide image pixel 251 can be stored within inspection image 400. For example, information about the boundaries of each guide image pixel 251 can be stored as metadata of inspection image 400.

[0094] In yet another example, a table 260 can be created that associates the X and Y coordinates of the inspection image 400 with the corresponding guide image pixels 251 of the simplified image 210 of the 3D model 200.

[0095] Once the guide image pixels 251 of the simplified image 210 of the 3D model 200 are associated with the image of the object 100 or the simplified image 210 of the object 100, the pixel attribute 252 of each guide image pixel 251 can also be associated with the image of the object 100 or the simplified image 210 of the object 100. For example, because each guide image pixel 251 can have a corresponding pixel attribute 252, the guide image pixels 251 together with their pixel attributes 252 can be associated with the image of the object 100 or the simplified image 210 of the object 100.

[0096] refer to Figure 14 A method 600 for determining attributes of an object 100 is provided according to exemplary embodiments of the present disclosure. Method 600 includes a step 610 of determining guide image data of the object 100 from a determined orientation. The guide image data may include a guide image pixel array 250 and pixel attributes 252 (attribute mapping) of at least one guide image pixel 251 in the guide image pixel array 250. The guide image data may also include a simplified image 210 of a 3D model 200 of the object 100. As previously described, guide image pixels 251, pixel attributes 252, and simplified image 210 of the 3D model 200 of the object 100 can be created from the 3D model 200 of the object 100.

[0097] Method 600 includes step 620 of receiving or determining inspection image data instructing inspection image 400. The inspection image data may include inspection image 400 of object 100, simplified image 410 of object 100, estimated orientation of object 100, inspection image pixel array 450, or a combination thereof.

[0098] Method 600 includes a step 630 of associating inspection image data with guide image data. As explained, there are various ways to associate guide image pixels 251 of a simplified image 210 of 3D model 200 with an image of object 100 or a simplified image 410 of object 100.

[0099] Method 600 includes a step 640 of determining attributes of object 100 based on guide image data and associated inspection image data. As explained, once guide image pixels 251 of a simplified image 210 of 3D model 200 are associated with an image of object 100 or a simplified image 410 of object 100, pixel attributes 252 of each guide image pixel 251 can also be associated with the image of object 100 or the simplified image 410 of object 100. For example, pixel attributes 252 of each guide image pixel 251 in the guide image pixel array can be associated with a corresponding inspection image pixel 451 in the array of inspection image pixels 451.

[0100] More specifically, one or more attributes of object 100 can be determined based on the guide image data and the associated inspection image data for each inspection image pixel 451 in the inspection image pixel array 450. Therefore, one or more attributes of object 100 can be determined. The one or more attributes of object 100 can be any information, including but not limited to size, distance, location, features, color, surface tilt, classification, mass, criticality, etc. When the attribute is distance, the distance can be Euclidean distance or geodesic distance. When the attribute is distance or size, measurement, calculation, or estimation can interpret the topology of the object. For example, the attribute can be a numerical value, a text value, a binary value, a quantitative value, a qualitative value, a categorical value, a symbolic value, or a combination thereof. Other calculations, estimations, or measurements can also be attributes of the object.

[0101] refer to Figure 15 According to exemplary embodiments of this disclosure, a method with specified... Figure 12 The inspection image 400 is a portion 700 of the inspection image pixel array 450. In this example, seven inspection image pixels 451 of the inspection image pixel array 450 have been specified. The inspection image pixels 451 can be specified by the user. For example, the user can specify one or more inspection image pixels 451 using a peripheral device. The peripheral device can be a touch screen, stylus, mouse, ball, etc.

[0102] The image 400 and the image pixel array 450 can be displayed to the user via a peripheral device. The peripheral device can be an auxiliary device of a computing system capable of displaying images to the user. For example, the peripheral device can be a computer monitor or a touchscreen monitor.

[0103] A user can specify a continuous segment 710 of inspected image pixels 451 within an inspected image pixel array 450. As used herein, a "continuous segment" refers to a plurality of inspected image pixels 451 within the inspected image pixel array 450 that are specified and adjacent to at least one other specified inspected image pixel. As used herein, "specified" refers to a continuous segment 710 of inspected image pixels 451 within the inspected image pixel array 450 specified by a user or computing system. For example, a user can specify one or more inspected image pixels 451 by drawing a line 720, as shown. The line 720 drawn by the user can also be displayed to the user via a peripheral device. The user can draw straight lines, curves, lines without a specific geometry or contour, or combinations thereof. The inspected image pixels 451 through which the line 720 passes can be specified, thereby creating a linear continuous segment 710 of inspected image pixels. The linear continuous segment 710 of inspected pixels can represent a curve or a straight line 720. In the region where the line 720 is perpendicular to or parallel to the X-axis, the line 720 can specify a portion of the inspected image pixel array 450 that is one pixel wide or one pixel high. In regions where line 720 is tilted or at an acute angle relative to the X-axis, line 720 can specify a portion of the inspected image 400 that is at least two pixels wide or at least two pixels high, or one pixel wide and one pixel high. For example, in regions where line 720 is at a 30-degree angle to the X-axis, line 720 can specify a portion that is one pixel high and five pixels wide. As another example, in regions where line 720 is at a 45-degree angle to the X-axis, line 720 can specify a portion that is one pixel wide and one pixel high, such that the corners of the pixels within this portion have adjacent corners. Anti-aliasing methods can be used to illustrate user-specified subpixel interpolation. For example, anti-aliasing methods can be used to improve the appearance of continuous segments 710 of inspected image pixels 451 in the inspected image pixel array 450.

[0104] In another example, the computing system can specify a continuous segment 710 of inspected image pixels 451 in the inspected image pixel array 450. For example, machine learning can teach the computing system to analyze the inspected image 400 to identify certain key features. These key features can be specified automatically.

[0105] Users can specify continuous closed segments 710' of inspected image pixels 451. For example, one or more inspected image pixels 451 can be specified by drawing lines 720' that partially or completely enclose an area of ​​inspected image 400. The area of ​​inspected image 400 partially or completely enclosed by lines 720' can be automatically specified, thereby creating closed segments 710' of inspected image pixels 451.

[0106] refer to Figure 16 According to exemplary embodiments of this disclosure, a method with specified... Figure 12 The inspection image 400 is a portion of the inspection image pixel array 450. Inspection image pixel 451 can be... Figure 15 The example embodiments are specified in the same or similar manner. However, in this example, the image pixel array 450 is not displayed to the user.

[0107] refer to Figure 17 According to exemplary embodiments of this disclosure, a method with specified... Figure 12 The inspection image 400 is a portion of the inspection image pixel array 450. Inspection image pixel 451 can be... Figure 15 The example embodiments are specified in the same or similar manner. However, in this example, neither the image pixel array 450 nor the designated portion 700 of the image pixel array 450 is shown to the user.

[0108] refer to Figure 18 A method 800 for determining properties of an object 100 is provided according to exemplary embodiments of the present disclosure. As described above, method 800 may include one or more steps of method 300. For example, method 800 may include step 310 of creating a 3D model 200 of the object 100 in a determined orientation. Method 800 may include step 320 of creating a guide image pixel array 250. Method 800 may include step 330 of determining pixel attribute 252 of at least one guide image pixel 251 in the guide image pixel array 250. Method 800 may include step 340 of creating a simplified image 410 of the 3D model 200 in a determined orientation.

[0109] Steps 310, 320, 330, and 340 can be repeated multiple times. For example, it may be beneficial to perform these steps for various defined orientations of the 3D model 200. For example, method 300 can be repeated up to 10,000 times (e.g., up to 5,000 times, up to 1,000 times, up to 200 times), each time for a different defined orientation of the 3D model 200. Thus, for each defined orientation of the 3D model 200, one or more pixel attributes 252 of at least one guide image pixel 251 in the guide image pixel array 250 can be determined. Furthermore, for each defined orientation of the 3D model 200, a simplified image 210 of the 3D model 200 of the object 100 can be created on the defined orientation. The defined orientation of each of the various defined orientations can vary only slightly. For example, the various defined orientations can vary only by up to 2 mm on the X, Y, and / or Z axes, and / or tilt within 2 degrees on the X, Y, and Z axes.

[0110] Method 800 may include one or more steps of method 500, as described above. For example, method 800 may include obtaining object 100 (e.g., Figure 10 Step 510 of inspecting image 400 of object 100. Method 800 may include creating a simplified image 410 of inspecting image 400 (e.g., object 100). Figure 11Step 520 (simplified image 410). Method 800 may include step 530 of estimating the orientation of object 100. As explained, the orientation of object 100 can be estimated by “matching” an image of object 100 or a simplified image 410 of object 100 with a simplified image 210 of 3D model 200.

[0111] Method 800 may include one or more steps of method 600, as described above. For example, method 800 may include step 610 of determining guide image data of object 100 from a determined orientation. The guide image data may include guide image pixel array 250 and pixel attribute 252 of at least one guide image pixel 251 in guide image pixel array 250. As previously described, guide image pixel 251 and pixel attribute 252 may be created from 3D model 200 of object 100.

[0112] Method 800 may include step 620 of receiving or determining inspection image data instructing inspection image 400. The inspection image data may include inspection image 400 of object 100, simplified image 410 of object 100, estimated orientation of object 100, inspection image pixel array 450, or a combination thereof.

[0113] Method 800 may include step 630 of associating inspection image data with guide image data. As explained, there are various ways to associate guide image pixels 251 of a simplified image 210 of 3D model 200 with an image of object 100 or a simplified image 410 of object 100.

[0114] Method 800 may include step 640 of determining attributes of object 100 based on guide image data and associated inspection image data. As explained, once guide image pixels 251 of a simplified image 210 of 3D model 200 are associated with an image of object 100 or a simplified image 410 of object 100, pixel attributes 252 of each guide image pixel 251 may also be associated with the image of object 100 or the simplified image 410 of object 100. For example, pixel attributes 252 of each guide image pixel 251 in the guide image pixel array may be associated with a corresponding inspection image pixel 451 in the inspection image pixel array 450.

[0115] Method 800 may include step 810 of receiving user input (specification) associated with a continuous segment of inspection image pixels 451 in the inspection image pixel array 450. As explained, the user may specify one or more inspection image pixels 451 using a peripheral device.

[0116] Method 800 may include step 820 of determining attributes of object 100 based on pixel attributes 252 associated with consecutive segments of inspection image pixels 451 in the inspection image pixel array 450. As explained with reference to step 640, one or more attributes of object 100 may be determined based on guide image data and associated inspection image data for each inspection image pixel 451 in the inspection image pixel array 450. Therefore, one or more attributes of object 100 may be determined based on one or more inspection image pixels 451 specified by the user.

[0117] One or more attributes of object 100 can be any information relating to a continuous segment of inspected image pixels 451. For example, one or more attributes can be size, distance, location, features, color, surface slope, classification, mass, criticality, etc. When the attribute is distance, the distance can be Euclidean distance or geodesic distance. When the attribute is distance or size, the measurement, calculation, or estimation can interpret the object's topology. As examples, the attribute can be a numerical value, a text value, a binary value, a quantitative value, a qualitative value, a categorical value, a symbolic value, or a combination thereof. Other calculations, estimations, or measurements can also be attributes of the object.

[0118] In at least one example, the user can specify a continuous segment 710 of inspection image pixels 451 representing a feature of the object. The feature of object 100 can be any part of object 100 that the user is interested in. For example, the feature could be the location of cooling holes on a gas turbine engine blade. In other examples, the feature could be damage to object 100 visible to the user in inspection image 400. More specifically, the feature could be a crack on the object, debris on the object, or the location of peeling coating on the object.

[0119] In at least one example, a user can use line 720 to "trace" a crack on an inspection image 400 of object 100 (e.g., an inspection image 400 of a gas turbine engine). The inspection image pixels 451 through which the line passes can be specified. Therefore, various information and data about the crack can be determined. For example, the length of the crack can be determined. (Brief Reference) Figures 4 to 7 The example provided allows for the determination of a set of distances 263. Distances 263 can be the distances 263 from guide image pixel 251 to its adjacent guide image pixel 253. These distances 263 can be associated with the inspected image pixel 451. To determine the length of the crack, for each specified pixel in a continuous segment, the distance 263 between the specified pixel and its adjacent specified pixels is determined. The distances 263 between each specified pixel and its adjacent specified pixels are then added together to determine the total length of the crack.

[0120] In at least one example, the user can select a region on an inspection image 400 of object 100 (e.g., an inspection image 400 of a gas turbine engine rotor blade), specifying a closed segment 710' of the inspection image pixel 451 with a line 720. Therefore, various information and data about that region can be determined. For example, the total area of ​​that region can be determined. (Brief Reference) Figure 3B In the example provided, the pixel attribute 252 of the guide image pixel 251 can be the area of ​​the guide image pixel 251. The guide image pixel attribute 252 can be associated with the inspection image pixel 451. Therefore, the guide image pixel attribute 252 (e.g., the area of ​​a pixel) can be associated with a specified pixel. To determine the area of ​​a specified closed segment 710' of the inspection image pixel 451, the areas of each specified pixel within the closed segment 710' are summed.

[0121] Method 800 may include providing a user with indications corresponding to the attributes of an object. For example, attributes of object 100 based on guide image data and associated inspection image data may be displayed to the user via a peripheral device of the computing system, such as a computer monitor. In another example, attributes of object 100 based on pixel attributes 252 associated with consecutive segments of inspection image pixels 451 in the inspection image pixel array 450 may be displayed to the user via a peripheral device of the computing system, such as a computer monitor. As another example, an indication of whether an object's attribute exceeds a threshold may be displayed to the user via a peripheral device of the computing system. For example, a first attribute of the object may be a specified length, which may correspond to the length of a crack on the object. A second attribute of the object may be a threshold for the length of the crack on the object. If the length of the crack exceeds the threshold, an indication that the length of the crack exceeds the threshold may be displayed to the user. If the length of the crack does not exceed the threshold, an indication that the length of the crack is within acceptable tolerance may be displayed to the user.

[0122] In yet another example, the first attribute of the object could be a specified length, which could correspond to the length of a crack on object 100. The second attribute of the object could be a specified location, which could correspond to the location of a crack on object 100. The third attribute of object 100 could be a threshold value for the length of the crack at the corresponding location on the object. If the length of the crack exceeds the threshold value for the corresponding location, an indication that the crack length exceeds the threshold value can be displayed to the user. If the length of the crack does not exceed the threshold value, an indication that the crack length is within acceptable tolerances can be displayed to the user. In this way, one or more attributes of object 100 (such as a specified location and length) can be compared with another attribute (such as a threshold value for the length of a crack at a specified location). The result of the comparison can be displayed to the user.

[0123] In another example, the first attribute of object 100 could be the first size of a feature on object 100 (e.g., a crack), and the second attribute of object 100 could be the second size of a feature on object 100. The first size and the second size of a feature on object 100 can be compared to determine the growth of the feature on the object. The growth of the feature on object 100 can be compared to a threshold. An indication can be displayed regarding whether the growth of the feature on object 100 exceeds the threshold.

[0124] In addition to providing users with indications of the properties corresponding to an object, other information can also be displayed to users, such as predictions about when the properties of object 100 will exceed a threshold.

[0125] Some properties of an object (such as thresholds) can be stored in a location other than the property map. For example, one or more properties of an object can be stored in the memory device of a computing system.

[0126] Method 800 may include initiating maintenance actions on object 100 in response to determining properties of object 100. For example, maintenance actions on object 100 may be initiated if a property of object 100 (such as the size of a crack, debris, or spalling location) exceeds a threshold. Other factors may be considered in response to determining whether to initiate maintenance actions on object 100 in response to determining properties of object 100. For example, when object 100 is a rotor blade of a gas turbine engine, the length of time between the next scheduled maintenance or overhaul event may be considered. Maintenance actions on object 100 may be initiated if a property of object 100 (such as the length of a crack) is expected to grow to exceed a threshold before the next scheduled maintenance or overhaul event. A “maintenance action” may be an inspection of object 100 that can be scheduled based on operating parameters of object 100. For example, when object 100 is a component of a gas turbine engine, the inspection may be based on thrust limits, temperature limits, time limits, cycle limits, etc. In some examples, a “maintenance action” may be an operational constraint imposed on a component. For example, when object 100 is a component of a gas turbine engine, object 100 can be downgraded to reduce its rated thrust, which can reduce the rated thrust power of the aircraft on which the gas turbine engine is mounted for takeoff and / or climb. "Maintenance action" can also be a material ordering action (procuring replacement parts), an overhaul scheduling action, a preventative maintenance action, or a repair action.

[0127] refer to Figure 19A method 900 for storing an inspection package of an object 100 is provided according to exemplary embodiments of the present disclosure. Method 900 may be similar to method 800 and may include methods 300, 500, and 600. However, in this example, method 900 includes a step 830 of storing a first inspection package, which includes an inspection image 400 of the object 100 and user input (specification) associated with a consecutive segment 710 of inspection image pixels 451 in an inspection image pixel array 450. The first inspection package may also include one or more pixel attributes 252 (attribute mapping) of at least one guide image pixel 251 in a guide image pixel array 250 using a first algorithm, and / or transformation data, and / or orientation determination. The first inspection package may be stored on a computing system.

[0128] One benefit of storing the inspection package is that step 820, which determines the attributes of object 100 based on pixel attributes associated with consecutive segments 710 of inspection image pixels 451 in the inspection image pixel array 450, can be redefined using a second algorithm, a second attribute mapping, or a second name. For example, the algorithm may change over time, which could also change the attribute mapping, and the method used for specification may change over time, which could also change the attributes of object 100. The specified algorithm or method can change due to optimization or improvement. Therefore, it can be useful to redefined past attributes of object 100 based on a newer second algorithm, a newer second attribute mapping, or a newer second specified method. This ensures that similar comparisons of object 100, its attributes, or its characteristics over time (using the same algorithm, attribute mapping, or specification) are possible, which will be explained in more detail even if the algorithm used to determine the attribute mapping changes or the specified method changes.

[0129] In at least one example, instead of storing the inspection package of object 100, or in addition to storing the inspection package of object 100, other inspection data may be stored. For example, the inspection data may include specified, estimated orientation of object 100, or attributes based on specified object 100.

[0130] refer to Figure 20 An exemplary embodiment of the present disclosure provides a method 1000 for comparing a first attribute of an object 100 with a second attribute of the object 100. The method 1000 may include the step 1010 of invoking a first inspection package, the first inspection package including a first inspection image 400 of the object 100 and a first designation. The first inspection image 400 package may further include a first attribute mapping of the object 100. (See reference...) Figure 19As described in method 900, the first check package may be stored on a computing system. Therefore, the first check package can be retrieved from the computing system later. Method 1000 may include step 1015, receiving, invoking, or receiving and invoking one or more attribute maps of object 100. Step 1015 may include receiving or invoking the first attribute map, and receiving or invoking the second attribute map.

[0131] Method 1000 may include step 1020 of receiving data instructing a second inspection package, the second inspection package including a second inspection image 400 of object 100 and a second designation. As described in step 510 of reference method 500, the inspection image 400 of object 100 may be obtained. As described in step 810 of reference method 800, user input (designation) associated with a consecutive segment 710 of inspection image pixels 451 in the inspection image pixel array 450 may be received.

[0132] Step 1020 may also include displaying a first designation from the first inspection package to the user. The first designation may be overlaid on the second inspection image of the second inspection package. Overlaying the first designation on the second inspection image can provide the user with a prompt, guidance, or instruction that can assist the user in performing the inspection.

[0133] Method 1000 may include step 1030 of determining a first attribute of object 100 based on a first inspection image 400 of the object, one or more attribute maps of the object, and a first specification. As described in step 820 of reference to method 800, the attribute of object 100 may be determined based on guide image data including attribute maps and specifications. Method 1000 may include step 1040 of determining a second attribute of object 100 based on a second inspection image 400 of the object, one or more attribute maps of the object, and a second specification. As briefly mentioned, the algorithm used to determine the attribute maps may change over time. Therefore, it may be advantageous to determine the first attribute and the second attribute of object 100 based on the same attribute map. However, in other examples, it may be advantageous to determine the first attribute and the second attribute of object 100 based on different attribute maps.

[0134] Method 1000 may include step 1050 of comparing a first attribute with a second attribute. Comparing the first attribute with the second attribute may include determining differences between features on object 100. For example, comparing the first attribute with the second attribute may include determining the growth of a feature on object 100. As mentioned, this feature may be damage to object 100 visible to the user in the inspected image 400. In some examples, this feature may be a crack on object 100, debris on object 100, or the location of a peeling coating on object 100. Therefore, comparing the first attribute with the second attribute may include determining the growth or variation of cracks, debris, or peeling coating.

[0135] In some examples, the first inspection image 400 defines a first capture date, and the second inspection image 400 defines a second capture date. The second capture date may be after the first capture date. For example, the second capture date may be at least one month later than the first capture date (e.g., at least six months later, at least one year later, at least three years later), and at most twenty years later than the first capture date (e.g., up to fifteen years later, at least ten years later, at least five years later). In at least one example, the first inspection image 400 defines a first usage-related metric (e.g., number of hours or periods), and the second inspection image 400 defines a second usage-related metric. The second usage-related metric may be greater than the first usage-related metric. For example, the second usage-related metric may be at least ten periods greater than the first usage-related metric (e.g., at least twenty periods greater, at least fifty periods greater, at least one hundred periods greater, at least one thousand periods greater), and at most one thousand periods greater (e.g., up to five hundred periods greater, at least one hundred periods greater).

[0136] In some examples, it may be beneficial to periodically determine the growth or changes in cracks, debris, or coating peeling. For instance, when object 100 is a rotor blade for a gas turbine engine, it may be beneficial to compare properties such as the length of cracks on the rotor blade when arranging for maintenance or inspection of the engine on which the rotor blade is mounted.

[0137] In some examples, determining the first attribute of object 100 includes determining the first attribute of object 100 that is close to the second capture date. For example, the first attribute of object 100 can be determined on a date closer to the second capture date than the first capture date (i.e., the "determined date"). As mentioned, when the attributes of an object were previously determined using an older algorithm, it may be beneficial to redetermine the attributes of object 100 based on a newer algorithm so that similar comparisons can be made. Therefore, the first attribute of object 100 can have a determined date that is closer to the second capture date than the first capture date.

[0138] refer to Figure 21A block diagram of a computing system 2000, which can be used to implement the methods and systems of the present disclosure, is provided according to exemplary embodiments of the present disclosure. The computing system 2000 can be used to implement the inspection system 3000. Figure 22 As will be described herein. However, it should be understood that the computing system 2000 is an example of a suitable computing system for implementing the inspection system and other computing elements described herein.

[0139] As shown in the figure, computing system 2000 may include one or more computing devices 2005. The one or more computing devices 2005 may include one or more processors 2015 and one or more memory devices 2020. The one or more processors 2015 may include any suitable processing device, such as a microprocessor, microcontroller, integrated circuit, logic device, or other suitable processing device. The one or more memory devices 2020 may include one or more computer-readable media, including but not limited to non-transitory computer-readable media, RAM, ROM, hard disk drives, flash drives, or other memory devices. The one or more memory devices 2020 may include remote storage devices or internet storage devices, such as cloud storage devices.

[0140] One or more memory devices 2020 may store information accessible by one or more processors 2015, including computer-readable instructions 2025 executable by one or more processors 2015. The computer-readable instructions 2025 may be any set of instructions that, when executed by one or more processors 2015, cause one or more processors 2015 to operate. The computer-readable instructions 2025 may be written in any suitable programming language or may be software that can be implemented in hardware. In some embodiments, the computer-readable instructions 2025 may be executed by one or more processors 2015 to cause one or more processors 2015 to operate, for example, to control the operation of an inspection system, and / or any other operation or function of one or more computing devices 2005.

[0141] The memory device 2020 may further store data 2030 that can be accessed by the processor 2015. For example, the data 2030 may include pixel attributes 252 as described herein, guide image pixel array 250, transformation data, etc. According to an example embodiment of this disclosure, the data 2030 may include one or more tables (e.g., table 260), functions, algorithms (e.g., algorithm 259), images (e.g., simplified images 210 and 410), equations, etc.

[0142] One or more computing devices 2005 may also include a communication interface 2040 for, for example, communicating with other components of the system. The communication interface 2040 may include any suitable component for interfacing with one or more networks, including, for example, a transmitter, receiver, port, controller, antenna, or other suitable component.

[0143] The techniques discussed herein refer to computer-based systems, actions taken by computer-based systems, information sent to computer-based systems, and information received from computer-based systems. Those skilled in the art will recognize that the inherent flexibility of computer-based systems allows for a wide variety of possible configurations, combinations, and divisions of tasks and functions between and within components. For example, the methods and processes discussed herein can be implemented using a single computing device or multiple computing devices working in combination. Databases, memories, instructions, and applications can be implemented on a single system or distributed across multiple systems. Distributed components can operate sequentially or in parallel.

[0144] refer to Figure 22 This document provides a block diagram of an inspection system 3000 according to exemplary embodiments of the present disclosure. The inspection system 3000 may include one or more computing devices 2005, one or more peripheral devices 3010, and one or more visual image recording devices 3020. As mentioned, the peripheral device 3010 may be a device that a user can use to specify one or more inspection image pixels 451 of an inspection image 400. The peripheral device 3010 may be a touchscreen, stylus, mouse, ball, etc. Furthermore, as described above, the peripheral device 3010 may be a device capable of displaying images to a user. For example, the peripheral device 3010 may be a computer monitor and may be a touchscreen monitor.

[0145] As described above, the visual image recording device 3020 can be a camera, such as a duct endoscope camera or an endoscope camera. The visual image recording device 3020 can be a monocular camera or a binocular camera. Compared to a binocular camera, using a monocular camera can help reduce cost and complexity, and improve reliability and accuracy. Furthermore, although not depicted, the visual image recording device 3020 can also be a component of an inspection tool assembly. The inspection tool assembly can assist the operator in taking photographs in the desired orientation.

[0146] Although this disclosure has periodically mentioned gas turbine engines, it should be understood that the described methods can be used to inspect objects on other devices, such as wind turbines, automobiles, hydrogen engines, steam engines, etc.

[0147] This written description uses examples to disclose this disclosure, including best practices, and also enables any person skilled in the art to practice this disclosure, including making and using any device or system and methods of making any combination. The patent scope of this disclosure is defined by the claims, but may include other examples that would occur to a person skilled in the art. Such other examples are intended to fall within the scope of the claims if they include structural elements that are not indistinguishable from the literal language of the claims, or if they include equivalent structural elements that are not substantially different from the literal language of the claims.

[0148] Further details are provided by the following topics:

[0149] 1. A method for inspecting an object, the method comprising: receiving or determining inspection image data, the inspection image data including an inspection image pixel array, wherein at least one inspection image pixel in the inspection image pixel array has a pixel attribute associated therewith; receiving user input associated with a continuous segment of inspection image pixels in the inspection image pixel array via a processor; and determining attributes of the object based on the pixel attribute associated with the continuous segment of inspection image pixels in the inspection image pixel array.

[0150] 2. The method according to any of the preceding clauses, wherein receiving the user input includes receiving the user input via a peripheral device operatively connected to the processor.

[0151] 3. The method according to any of the preceding clauses, wherein the continuous segment of inspected image pixels is a linear segment of inspected image pixels, and wherein determining the attribute of the object includes determining the length.

[0152] 4. The method according to any of the preceding clauses, wherein the pixel attribute includes distance measurement.

[0153] 5. The method according to any of the preceding clauses, wherein the continuous segment of the inspected image pixels is a closed segment of the inspected image pixels, and wherein determining the attribute of the object includes determining the area of ​​the closed segment.

[0154] 6. The method according to any of the preceding clauses, wherein the continuous segment of the inspected image pixels is a closed segment of the inspected image pixels, and wherein determining the attribute of the object comprises: determining the attribute of the object based on the pixel attribute associated with the closed segment of the inspected image pixels in the inspected image pixel array and further based on the pixel attribute associated with the inspected image pixels surrounded by the closed segment of the inspected image pixels in the inspected image pixel array.

[0155] 7. The method according to any of the preceding clauses, wherein the pixel attribute includes area measurement.

[0156] 8. The method according to any of the preceding clauses includes displaying an inspection image and an array of pixels of the inspection image to a user.

[0157] 9. The method according to any of the preceding clauses, wherein determining the attribute of the object based on the pixel attribute associated with a continuous segment of the inspected image pixels in the inspected image pixel array comprises: determining a plurality of attributes of the object based on the pixel attribute associated with the continuous segment of the inspected image pixels in the inspected image pixel array.

[0158] 10. The method according to any of the preceding clauses, wherein receiving the user input further comprises receiving a line drawn by the user and associating the line with a continuous segment of the inspected image pixels in the inspected image pixel array.

[0159] 11. An inspection system comprising: a visual image recording device configured to generate an inspection image of an object; and a computing system including a processor configured to: receive or determine inspection image data, the inspection image data including an array of inspection image pixels, wherein at least one inspection image pixel in the array of inspection image pixels has an associated pixel attribute; receive user input via the processor, the user input being associated with a consecutive segment of inspection image pixels in the array of inspection image pixels; and determine attributes of the object based on the pixel attribute associated with the consecutive segment of inspection image pixels in the array of inspection image pixels.

[0160] 12. The inspection system according to any of the preceding clauses, wherein the continuous segment of the inspected image pixels is a linear segment of the inspected image pixels, and wherein the attribute of the object is a length measurement.

[0161] 13. The inspection system according to any of the preceding clauses, wherein the pixel attribute includes distance measurement.

[0162] 14. The inspection system according to any of the preceding clauses, wherein the continuous segment of the inspected image pixels is a closed segment of the inspected image pixels, and wherein the attribute of the object is an area measurement.

[0163] 15. The inspection system according to any of the preceding clauses, wherein the continuous segments of the inspected image pixels are closed segments of the inspected image pixels, and wherein the attribute of the object is determined based on the pixel attribute associated with the closed segment of the inspected image pixels in the array of inspected image pixels, and the pixel attribute associated with the pixel surrounded by the closed segment of the inspected image pixels in the array of inspected image pixels.

[0164] 16. The inspection system according to any of the preceding clauses, wherein the pixel attribute includes area measurement.

[0165] 17. The inspection system according to any of the preceding clauses, wherein the inspection system includes peripheral means configured to display the inspection image and the pixel array of the inspection image to a user.

[0166] 18. The inspection system according to any of the preceding clauses, wherein each inspection image pixel is a subdivision of the inspection image.

[0167] 19. The inspection system according to any of the preceding clauses, wherein the user input is a line drawn by the user, and the computing system is configured to associate the line with consecutive segments of the inspected image pixels in the inspected image pixel array.

[0168] 20. The inspection system according to any of the preceding clauses, wherein the inspection image data comprises a simplified image of a 3D model of the object.

Claims

1. A method for inspecting an object, characterized in that, The method includes: Receive an inspection image, the inspection image comprising one or more inspection image pixel arrays, the one or more inspection image pixel arrays comprising at least one inspection image pixel and a corresponding position of each of the at least one inspection image pixel; The orientation of the object relative to the optical sensor is determined from the inspected image via attitude recovery regression; Guide image data is determined from a 3D model representing the object in the determined orientation, wherein the guide image data includes one or more guide image pixel arrays, and wherein the 3D model includes associated properties projected onto the one or more guide image pixel arrays; The one or more guide image pixel arrays are associated with one or more corresponding inspection image pixel arrays, wherein the one or more guide image pixel arrays further include at least one guide image pixel having a pixel attribute, wherein the pixel attribute is a value representing a physical property of the object determined for each guide image pixel in the one or more guide image pixel arrays associated with the at least one inspection image pixel displaying a portion of the object; An attribute map is generated by merging one or more guide image pixel arrays that include at least one guide image pixel having associated pixel attributes, wherein, in generating the attribute map, only the corresponding position of each of the at least one guide image pixel and the orientation of the object in the inspection image are used from the inspection image. The processor receives user input or computing system input, the input specifying a continuous segment of inspected image pixels in the one or more inspected image pixel arrays, wherein the continuous segment represents damage to engine components; and Based on the pixel attributes associated with the at least one inspection image pixel designated as the contiguous segment in the one or more inspection image pixel arrays, at least two attributes of the object associated with the contiguous segment of the inspection image pixel are determined from the attribute map, wherein the first attribute of the at least two attributes includes a distance, and wherein the second attribute of the at least two attributes includes the location of the designated contiguous segment, wherein the distance is calculated, estimated, or measured from a first neighboring pixel of the first inspection image pixel array to a second neighboring pixel of the first inspection image pixel array, wherein the distance is determined by drawing the shortest straight line from the midpoint of the first neighboring pixel to the second neighboring pixel, and wherein the distance represents the damaged length of the object.

2. The method according to claim 1, characterized in that, in, Receiving the user input includes receiving the user input via a peripheral device operatively connected to the processor.

3. The method according to claim 1, characterized in that, in, The continuous segment of inspected image pixels is a linear segment of inspected image pixels, and wherein determining the at least two attributes of the object further includes determining the length.

4. The method according to claim 3, characterized in that, in, The pixel attribute includes distance.

5. The method according to claim 1, characterized in that, in, The continuous segment of the inspected image pixels is a closed segment of the inspected image pixels, and wherein determining the at least two attributes of the object includes determining the area of ​​the closed segment.

6. The method according to claim 1, characterized in that, in, The continuous segment of the inspected image pixel is a closed segment of the inspected image pixel, and wherein determining the at least two attributes of the object further comprises: determining the attributes of the object based on the pixel attributes associated with the closed segments of the inspected image pixels in the one or more inspected image pixel arrays and further based on the pixel attributes associated with the inspected image pixels surrounded by the closed segments of the inspected image pixels in the one or more inspected image pixel arrays.

7. The method according to claim 6, characterized in that, in, The pixel attributes include area.

8. The method according to claim 1, characterized in that, This includes displaying the inspection image and the one or more inspection image pixel arrays to the user.

9. The method according to claim 1, characterized in that, in, Determining the at least two attributes of the object based on the pixel attributes associated with consecutive segments of the inspected image pixels in the one or more inspected image pixel arrays includes: determining multiple attributes of the object based on the pixel attributes associated with consecutive segments of the inspected image pixels in the one or more inspected image pixel arrays.

10. The method according to claim 1, characterized in that, in, Receiving the user input further includes receiving a line drawn by the user and associating the line with consecutive segments of the inspected image pixels in the one or more inspected image pixel arrays.

11. The method according to claim 1, characterized in that, in, Determining the orientation of the object further includes estimating the orientation of the object by creating a simplified image of the inspection image.

12. An inspection system, characterized in that, include: A visual image recording device configured to generate an inspection image of an object; as well as A computing system, comprising a processor, is configured such that: Receive the inspection image, the inspection image comprising one or more inspection image pixel arrays, the one or more inspection image pixel arrays comprising at least one inspection image pixel and a corresponding position of each of the at least one inspection image pixel; The orientation of the object relative to the optical sensor is determined from the inspected image via attitude recovery regression; Guide image data is determined from a 3D model representing the object in the determined orientation, wherein the guide image data includes one or more guide image pixel arrays, wherein the 3D model includes associated attributes that are projected onto the one or more guide image pixel arrays; The one or more guide image pixel arrays are associated with one or more corresponding inspection image pixel arrays, wherein the one or more guide image pixel arrays further include at least one guide image pixel having a pixel attribute, wherein the pixel attribute is a value representing a physical property of the object determined for each guide image pixel in the one or more guide image pixel arrays associated with the at least one inspection image pixel displaying a portion of the object; An attribute map is generated by merging one or more guide image pixel arrays, including at least one guide image pixel with associated pixel attributes, wherein the attribute map is generated from the inspection image using only the corresponding position of each of the at least one inspection image pixel and the orientation of the object in the inspection image; user input or computing system input is received via the processor, the input specifying a continuous segment of inspection image pixels in the one or more inspection image pixel arrays, wherein the continuous segment represents damage to engine components; and Based on the pixel attributes associated with the at least one inspection image pixel designated as the contiguous segment in the one or more inspection image pixel arrays, at least two attributes of the object associated with the contiguous segment of the inspection image pixel are determined from the attribute map, wherein the first attribute of the at least two attributes includes a distance, and wherein the second attribute of the at least two attributes includes the location of the designated contiguous segment, wherein the distance is calculated, estimated, or measured from a first neighboring pixel of the first inspection image pixel array to a second neighboring pixel of the first inspection image pixel array, wherein the distance is determined by drawing the shortest straight line from the midpoint of the first neighboring pixel to the second neighboring pixel, and wherein the distance represents the damaged length of the object.

13. The inspection system according to claim 12, characterized in that, in, The continuous segment of inspected image pixels is a linear segment of inspected image pixels, and wherein the at least two attributes of the object further include length.

14. The inspection system according to claim 13, characterized in that, in, The pixel attribute includes distance.

15. The inspection system according to claim 12, characterized in that, in, The continuous segment of the inspected image pixels is a closed segment of the inspected image pixels, and wherein the at least two attributes of the object further include area.

16. The inspection system according to claim 12, characterized in that, in, The continuous segment of the inspected image pixel is a closed segment of the inspected image pixel, and wherein the at least two attributes of the object are determined based on the pixel attributes associated with the closed segment of the inspected image pixel in the one or more inspected image pixel arrays, and the pixel attributes associated with the pixels surrounded by the closed segment of the inspected image pixel in the one or more inspected image pixel arrays.

17. The inspection system according to claim 16, characterized in that, in, The pixel attributes include area.

18. The inspection system according to claim 12, characterized in that, in, The inspection system includes peripheral devices configured to display the inspection images and one or more inspection image pixel arrays to a user.

19. The inspection system according to claim 12, characterized in that, in, Each pixel in the inspected image is a subdivision of the inspected image.

20. The inspection system according to claim 12, characterized in that, in, The user input is a line drawn by the user, and the computing system is configured to associate the line with consecutive segments of the inspected image pixels in the one or more inspected image pixel arrays.

21. The inspection system according to claim 12, characterized in that, in, The inspected image data includes a simplified image of the 3D model of the object.

Images