A METHOD AND SYSTEM FOR A STRUCTURAL HEALTH MONITORING OF AN OBJECT USING INFRARED THERMOGRAPHY

Abstract

The present subject matter discloses a method (900) for a structural health monitoring of an object. The method (900) includes receiving, by a receiving engine (208), a plurality of images comprising a first image and a second image as an input. The method (900) includes thresholding, by a thresholding engine (210), the first image to generate a plurality of binary images of a plurality of colors, associated with the first image. The first image comprises the plurality of colors. The method (900) includes determining, by a contour engine (212), a contour associated with each binary image amongst the plurality of binary images based on a limit associated with each binary image. The method (900) includes drawing, by the contour engine (212), the contour associated with plurality of binary images on a zero image. The method (900) includes overlaying, by an overlaying engine (214), the contour associated with each binary image amongst the plurality of images on a second image amongst the at least two images to generate an output image. The output image is monitored to determine a structural health of the object. {To be published with fig. 3}

Specification

Description:A METHOD AND SYSTEM FOR A STRUCTURAL HEALTH MONITORING OF AN OBJECT USING INFRARED THERMOGRAPHY
[0001] The present subject matter relates to a process for monitoring structural health of an object, particularly, the present subject matter relates to the process for monitoring structural health of an object to detect deformation in the object.
BACKGROUND OF THE INVENTION
[0002] Background description includes information that may be useful in understanding the present subject matter.

[0003] As industrial systems become more complex and are subjected to increasingly harsh operational environments, the need for highly reliable, real-time monitoring systems that can accurately assess structural integrity without compromising the functionality or security of the structures has become critical.

[0004] Traditional Non-Destructive Testing (NDT) methods, such as ultrasound, X-ray, acoustic emission (AE), and thermography, have been instrumental in identifying internal faults and assessing structural integrity. However, each technique comes with inherent limitations. For instance, AE is highly sensitive and capable of detecting microscopic deformations and predicting fatigue crack propagation. Yet, its effectiveness is often constrained in environments with restricted sensor accessibility or where security protocols limit the use of certain sensors. Furthermore, the complexity and time-intensive nature of conventional NDT methods make them impractical for real-time or remote monitoring applications, which are increasingly required in modern industrial and defense contexts.

[0005] Infrared thermography (IRT) has emerged as a promising alternative within this domain. It enables non-intrusive inspection by generating surface temperature maps, which can reveal underlying structural anomalies. However, current IRT systems are hampered by several deficiencies, notably the lack of precision and real-time processing capabilities necessary for accurately localizing deformations and conducting comprehensive structural health assessments. These shortcomings are particularly pronounced in scenarios where access to the structure is limited, or where there is a need for continuous monitoring under dynamic load conditions.

[0006] Therefore, there is a need for a solution to overcome the above-mentioned drawbacks.
SUMMARY OF THE INVENTION
[0007] This summary is provided to introduce concepts related to a method for a structural health monitoring of an object. The concepts are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0008] The present subject matter discloses a method for a structural health monitoring of an object. The method includes receiving, by a receiving engine, a plurality of images comprising a first image and a second image as an input. The method includes thresholding, by a thresholding engine, the first image to generate a plurality of binary images of a plurality of colors, associated with the first image. The first image comprises the plurality of colors. The method includes determining, by a contour engine, a contour associated with each binary image amongst the plurality of binary images based on a limit associated with each binary image. The method includes drawing, by the contour engine, the contour associated with plurality of binary images on a zero image. The method includes overlaying, by an overlaying engine, the contour associated with each binary image amongst the plurality of images on a second image amongst the at least two images to generate an output image. The output image is monitored to determine a structural health of the object.
[0009] The present subject matter discloses a system for a structural health monitoring of an object. The system includes a receiving engine configured to receive a plurality of images comprising a first image and a second image as an input. The system includes a thresholding engine configured to threshold the first image to generate a plurality of binary images of a plurality of colors, associated with the first image. The first image comprises the plurality of colors. The system includes a contour engine configured to determine a contour associated with each binary image amongst the plurality of binary images based on a limit associated with each binary image, and draw the contour associated with plurality of binary images on a zero image. The system includes an overlaying engine configured to overlay the contour associated with each binary image amongst the plurality of images on a second image amongst the at least two images to generate an output image. The output image is monitored to determine a structural health of the object
[0010] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
[0011] The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
[0012] Fig. 1 illustrates an environment depicting a camera unit and a system 104 configured to perform a structural health monitoring of an object, in accordance with an embodiment of the present subject matter;
[0013] Fig. 2 illustrates a schematic block diagram depicting the system, in accordance with an embodiment of the present subject matter;
[0014] Fig. 3 illustrates an operational flow diagram depicting a process for performing a structural health monitoring of an object, in accordance with an embodiment of the present subject matter;
[0015] Fig. 4a and 4b illustrate images depicting a tensile test setup of CT specimen by varying displacement and a tensile test setup of a dog bone shaped sample by varying load, in accordance with an embodiment of the present subject matter;
[0016] Fig. 5 illustrates a diagram depicting an IRT methodology used for a deformation detection in an object, in accordance with an embodiment of the present subject matter;
[0017] Fig. 6a-6c illustrate images depicting a resizing of an RGB image, in accordance with an embodiment of the present subject matter;
[0018] Fig. 7a-7f illustrate an images depicting results of the process, in accordance with an embodiment of the present subject matter;
[0019] Fig. 8a-8d illustrate a number of images depicting a number of user interfaces displayed on a device incorporating the system for performing a structural health monitoring of an object, in accordance with an embodiment of the present subject matter; and
[0020] Fig. 9 illustrates a schematic block diagram depicting a method for performing a structural health monitoring of an object, in accordance with an embodiment of the present subject matter.
[0021] The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

DETAILED DESCRIPTION
[0022] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0023] Fig. 1 illustrates an environment 100 depicting a camera unit 102 and a system 104 configured to perform a structural health monitoring of an object, in accordance with an embodiment of the present subject matter. The object may be made up of one of mild steel and DMR 249 grade ship steel. The system 104 may be configured to perform an enhanced deformation localization of the object through a fusion of Infrared (IR) thermography and RGB imaging. The system 104 may be specifically designed to enhance an accuracy, a precision, and real-time capabilities of structural health monitoring systems. The system 104 may be optimized for a broad spectrum of structural applications, facilitating localization of deformation across various severity levels. The system 104 may perform a Non-Destructive Testing (NDT) method that ensures a structural integrity without compromising an integrity of the object under inspection.
[0024] The system 104 may be configured to communicate with the camera unit 102 for performing the structural health monitoring of the object. The system 104 may utilize IRT that leverages leveraging thermal energy in an infrared spectrum to generate a surface temperature map of the object, independent of a geometry of the object. Active infrared thermal imaging, a subset of IRT, is highly effective for NDT analysis. The system 104 may utilize active infrared thermal imaging where the camera unit 102 may capture an electromagnetic radiation emitted by the object above absolute zero, producing a thermogram of the object. In an embodiment, the camera unit 102 may be an infrared camera. In a preferred embodiment, the camera unit 102 may be a camera with a number of lenses. The number of lenses may include an IR lens for capturing an IR image of the object and a RGB lens for capturing an RGB image of the object.
[0025] Continuing with the above embodiment, the system 104 may integrate the IRT with an embedded system for a real-time, and a remote structural health monitoring. The system 104 may be designed for a seamless operation, where a device incorporating the system 104 is affixed to the object and may provide a continuous monitoring through an application (APP) and a web-based interface. The system 104 may include an image processing technique that may combine IRT data with corresponding RGB images captured by the RGB lens, enhancing the accuracy and detail of the deformation localization. The system 104 may be highly precise and capable of real-time performance in a variety of industrial and defense settings.
[0026] The camera unit 102 may be configured to capture a number of images through the number of lenses. The number of images may include a first image and a second image. The first image may be the IR image captured a by a first lens, specifically the IR lens, and the second image may be the RGB image captured by a second lens, specifically the RGB lens. Upon capturing the number of images, the camera unit 102 may be configured to transmit the number of images to the system 104. The camera unit 102 may be communicating with the system 104 via one of a wireless communication standard, and a wired communication standard. Examples of the wireless communication standard may include, but are not limited to, WiFi, Infrared, Bluetooth. Examples of the wired communication standard may include, but are not limited to, a Local Area Network (LAN), a Metropolitan Area Network (MAN), and a Wide Area Network (WAN).
[0027] In accordance with an embodiment of the present subject matter, the system 104 may be configured to receive the plurality of images as an input from the camera unit 102. Upon receiving the number of images, the system 104 may be configured to threshold the first image to generate a plurality of binary images of a plurality of colors. The plurality of binary images of a plurality of colors may be related to the first image. The first image may include number of colors.
[0028] Upon thresholding the first image, the system 104 may be configured to determine a contour associated with each binary image amongst the number of binary images. The contour may be determined based on a limit associated with each binary image. Moving forward, the system 104 may be configured to draw the contour associated with plurality of binary images on a zero image.
[0029] Subsequent to drawing the contour, the system 104 may be configured to overlay the contour associated with each binary image amongst the plurality of images. The contour may be overlayed on the second image amongst the plurality of images to generate an output image. The output image may be monitored to determine a structural health of the object.
[0030] Fig. 2 illustrates a schematic block diagram 200 depicting the system 104, in accordance with an embodiment of the present subject matter. The system 104 may be configured to monitor the structural health may be performed by the system 104 to identify a presence and an absence of a deformation on the object. The system 104 may be configured to perform a structural health monitoring of an object. The system 104 may be configured to utilize a fusion of Infrared (IR) thermography and RGB imaging to perform a NDT method that ensures a structural integrity without compromising an integrity of the object under inspection. The system 104 may be configured to leverage thermal energy in an infrared spectrum to generate a surface temperature map of the object. The object may be made up of one of mild steel and DMR 249 grade ship steel. The system 104 may be configured to communicate with a camera unit to receive a number of images of the object captured by the camera unit. Based on the number of images, the system 104 may be configured to perform the structural health monitoring of the object. The system 104 may be able to provide an integrated solution that addresses demands for ease of use, security, and real-time analysis. The system 104 may further have a user-friendly interface, accessible via a mobile application or web-based platform, allowing operators to monitor structural integrity remotely, with immediate feedback on a status of a structure being analyzed, successful in environments where traditional NDT methods are either impractical or impossible to implement due to logistical constraints or the need for minimal disruption to operations.
[0031] The system 104 may include a processor 202, a memory 204, data 206, a receiving engine 208, a thresholding engine 210, a contour engine 212, and an overlaying engine 214. The processor 202, the memory 204, the data 206, the receiving engine 208, the thresholding engine 210, the contour engine 212, and the overlaying engine 214 may be communicatively coupled with one another.
[0032] In an aspect, the processor 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the processor 202 may be configured to fetch and execute computer-readable instructions stored in the memory 204 of the systems 104. The processor 202 may be the CPU whose temperature is being maintained by the system 104.
[0033] In an aspect, the processor 202 may be implemented as a combination of hardware and programming device(s) (for example, programmable instructions) to implement one or more functionalities of the processing device. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. In one example, the programming for the processor 202 may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processor 202 may include a processing resource (for example, one or more processors), to execute such instructions. In other examples, the processor 202 may be implemented by an electronic circuitry.
[0034] Further, in an aspect, the memory 204 may store one or more computer-readable instructions or routines, which may be fetched and executed to create or share data units over a network service. The memory 204 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like.
[0035] In an aspect, the memory 204 may include any non-transitory computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and/or dynamic random-access memory (DRAM), and/or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM (EPROM), flash memory, hard disks, optical disks, and/or magnetic tapes. The memory 204 may further include the data 206.
[0036] The data 210 serves, amongst other things, as a repository for storing data processed, received, and generated by the system 104.
[0037] Continuing with the above embodiment, the receiving engine 208 may be configured to receive the number of images from the camera unit 102 as referred in fig. 1. The receiving engine 208 may be communicating with the camera unit 102 via one of a wireless communication standard, and a wired communication standard. Examples of the wireless communication standard may include, but are not limited to, WiFi, Infrared, Bluetooth. Examples of the wired communication standard may include, but are not limited to, a Local Area Network (LAN), a Metropolitan Area Network (MAN), and a Wide Area Network (WAN). The number of images may include a first image and a second image. The first image may be an IR image captured by an IR lens of the camera unit 102 and the second image may be an RGB image captured by an RGB lens of the camera unit 102.
[0038] Upon a successful reception of the first image and the second image by the receiving engine, the thresholding engine 210 may be configured to perform a thresholding operation on the first image. The thresholding operation may be performed in order to generate a plurality of binary images of a plurality of colors, associated with the first image. The first image may include the plurality of colors. The thresholding engine 210 may be configured to perform the thresholding operation by selecting a plurality of threshold ranges associated with each color gradient of the plurality of colors. Upon selecting the number of threshold ranges, the thresholding engine 210 may be configured to set a pixel value for each color amongst the plurality of colors to one of 1 and 0. The pixel value may be set based on a threshold range amongst the plurality of threshold ranges associated with each color to generate the plurality of binary images. In one embodiment of the present subject matter, the pixel value of each color may be set to 1 if the pixel value lies within the plurality of threshold ranges. In another embodiment of the present subject matter, the pixel value of each color may be set to 0 if the pixel value lies outside the plurality of the threshold ranges.
[0039] Subsequent to thresholding of the first image by the thresholding engine 210, the contour engine 212 may be configured to determine a contour associated with each binary image amongst the plurality of binary images. The contour engine 212 maybe configured to determine the contour by determining the limit associated with each binary image, and connecting one or more boundary points corresponding to the limit on a zero image. The zero image may be of a size similar to a first size of the first image, with pixel value set to 0. The contour may be determined based on a limit associated with each binary image. To that understanding, the contour engine 212 may further be configured to draw the contour associated with plurality of binary images on the zero image.
[0040] Continuing with the above embodiment, the overlaying engine 214 may be configured to determine whether a first size associated with the first image and a second size associated with the second image is equal to one another or not. The overlaying engine may proceed with overlaying if the first size is same as the second size. In an embodiment, where it is determined that the first size is not same as the second size by the overlaying engine 214, the overlaying engine 214 may be configured to resize the second image prior to overlaying the contour associated with each binary image. The resizing of the second image may include adjusting a size of a Region of Interest of the second image with respect to the first image to align contents of the first image and the second image. Furthermore, the overlaying engine 214 may be configured to resize the contour associated with each binary image with respect to the second image prior to overlaying.
[0041] To that understanding, the overlaying engine 214 may further be configured to overlay the contour associated with each binary image amongst the plurality of images on the second image received from the camera unit 102. The output image may be monitored to determine the structural health of the object. The output image may indicate one of the presence and the absence of the deformation on the object.
[0042] Fig. 3 illustrates an operational flow diagram depicting a process 300 for performing a structural health monitoring of an object, in accordance with an embodiment of the present subject matter. The process 300 may be performed by the system 104 and the camera unit 102 as referred in fig. 1.
[0043] The process 300 may pertain to an advanced methodology in structural health monitoring, with particular emphasis on enhancing NDT techniques to meet growing demands for durable and damage-resistant industrial machinery and components.
[0044] The process 300 may utilize an advanced IRT-based system designed to deliver precise, real-time structural health monitoring. The process 300 may integrate a novel image processing technique that synergizes data from IRT images with high-resolution RGB images, enhancing an accuracy of deformation localization, and ensuring that the system 104 performing the process 300 may be deployed effectively in remote or otherwise inaccessible environments.
[0045] The process 300 may employ advanced image fusion techniques to enhance a precision of a deformation detection. By combining thermal data from IR images with the spatial detail from RGB images, the process 300 may pinpoint deformations with a high degree of accuracy, even in complex or cluttered environments. The hybrid approach may improve a reliability of the monitoring process, and may also expand an applicability of IRT to a wider range of industrial and defense settings. The process 300 may be configured to provide a precise localization of structural deformations using a combination of infrared (IR) and RGB imaging techniques. An accuracy of 97 % is noted for the process 300. The process 300 may also provide a video streaming with real time processing of images in remote device (Edge computing).
[0046] At step 302, the process 300 may include, receiving a number of images from the camera unit 102. The number of images may include a first image and a second image of the object. The first image may be an IR image and the second image may be an RGB image. The first image and the second image may be received by the receiving engine 208 as referred in the fig. 2.
[0047] At step 304, the process 300 may include, performing a thresholding operation on the first image. The thresholding operation may be performed by the thresholding engine 210 as referred in fig. 2. The thresholding operation may be performed in order to generate a plurality of binary images of a plurality of colors, associated with the first image. The first image may include the plurality of colors. The thresholding operation may include selecting a plurality of threshold ranges associated with each color gradient of the plurality of colors. Upon a selection of the number of threshold ranges, the thresholding operation may include setting a pixel value for each color amongst the plurality of colors to one of 1 and 0. The pixel value may be set based on a threshold range amongst the plurality of threshold ranges associated with each color to generate the plurality of binary images. In one embodiment of the present subject matter, where it is determined that the pixel value lies within the plurality of threshold ranges, the pixel value of each color may be set to 1. In another embodiment of the present subject matter, where it is determined that the pixel value lies outside the plurality of the threshold ranges, the pixel value of each color may be set to 0.
[0048] At step 306, the process 300 may include determining a limit associated with each binary image. The limit may be determined by the contour engine 212 as referred in fig. 2.
[0049] At step 308, the process 300 may include connecting one or more boundary points corresponding to the limit on a zero image. The one or more boundary points may be connected to the limit by the contour engine 212. The zero image may be of a size similar to a first size of the first image, with pixel value set to 0. The contour may be determined based on a limit associated with each binary image. The step 306 and step 308 may be performed to determine a contour associated with each binary image amongst the plurality of binary images.
[0050] At step 310, the process 300 may include drawing the contour associated with plurality of binary images on a zero image. The contour may be drawn by the contour engine 212.
[0051] At step 312, the process 300 may include determining whether a first size associated with the first image and a second size associated with the second image is equal to one another or not. The determination may be made by the overlaying engine 214 as referred in fig. 2. In an embodiment, where it is determined that the first size is not equal to the second size, the process 300 may proceed towards step 314a. In another embodiment, where it is determined that the first size is equal to the second size, the process 300 may proceed towards step 314b.
[0052] At step 314a, the process 300 may include resizing the second image prior to overlaying the contour associated with each binary image. The resizing may be performed by the overlaying engine 214. The resizing of the second image may include adjusting a size of a Region of Interest of the second image with respect to the first image to align contents of the first image and the second image. Furthermore, the overlaying engine 214 may be configured to resize the contour associated with each binary image with respect to the second image prior to overlaying.
[0053] At step 314b, the process 300 may include overlaying the contour associated with each binary image amongst the plurality of images on the second image received from the camera unit 102. The overlaying may be performed by the overlaying engine 214.
[0054] The output image may be monitored to determine the structural health of the object. The output image may indicate one of the presence and the absence of the deformation on the object. While monitoring, the process 300 may be configured to accurately identify and localize various types of deformations, including cracks, bends, corrosion, and plastic zone formation at the crack tip. The process 300 may be configured to assess and differentiate deformation severity levels, enabling clear identification of regions ranging from highly deformed to structurally safe areas of the object. The process 300 may facilitate remote monitoring and assessment of structural health status of the object. The process 300 may effectively detect and indicate defects present within the object. The deformations detected may be marked with different coloured contours like red, yellow and green corresponding to the most deformed, moderately deformed and safer regions on the structure.
[0055] Fig. 4a and 4b illustrate images 400a and 400b depicting a tensile test setup of CT specimen by varying displacement and a tensile test setup of a dog bone shaped sample by varying load, in accordance with an embodiment of the present subject matter. The CT sample may be a DMR 249A high strength low alloy steel. The dog bone shaped sample may be made of mild steel. DMR 249 grade A ship steel samples may be moulded into CT specimens, while mild steel samples may be cut into rectangular and dog bone shapes. Some of the mild steel rectangular samples developed cracks during milling and machining, while others rusted. Fresh DMR 249 grade A CT samples may be tested, with some different degrees of distortion. An experimental setup disclosed in fig. 4a and fig. 4b include a FLIR C5 Compact Infrared camera and all needed samples. The deformations may be created using a fatigue 25KN machine under various loading conditions.
[0056] The system 104 may include an IR camera lens and a standard RGB camera lens, both interfaced with a processor, which may serve as a Single Board Computer (SBC) for processing. The processor may handle image processing and video streaming over internet. To monitor a product or structure, a user may access the system 104 by connecting to the processor using an assigned IP address. Once connected, the user may view a live video stream and capture images via a web or mobile application. When the user presses a capture button on a device, a request to the processor may be sent. The board may the capture, process, and analyze the images to detect and differentiate defects, and sends the processed results back to the web or mobile application for review.
[0057] Fig. 5 illustrates a diagram depicting an IRT methodology 500 used for a deformation detection in an object, in accordance with an embodiment of the present subject matter. The detection may be performed by the system 104 by performing the process 300 as referred in fig. 2 and fig. 3. An IR camera may capture both RGB and IR images. The IR camera may have an image resolution of about 160 x 120. The IR picture resolution may be 320×240, and the RGB image resolution may be 640 × 480. The IR image may be restricted to the acquired sample. However, the RGB image may include sample's whole background. Digital images may be represented as matrices. The resizing procedure may demonstrate cropping an image as a matrix. The region of interest (ROI) may be defined as [87:462] rows and [80:580] columns, aligning the contents of the IR and RGB images. Further, image processing may pe performed that may include steps 302- 314a and 314b as disclosed in fig 3.
[0058] Fig. 6a-6c illustrate images 600a-600c depicting a resizing of an RGB image, in accordance with an embodiment of the present subject matter. Fig. 6a depicts the RGB image of an object. Fig.6b discloses a blue rectangular box representing the ROI. The ratios reflect the omission of 140 x 105 rows and columns. Cropping involves picking sub-matrices from a whole matrix depending on pixel values. Cropping may be defined as follows: B = A[i1: i2, j1: j2], where A is the entire image of size m × n and B is the cropping area of size p × q. The cropping part of the image may be represented by 1 ≤ i1 ≤ i2 ≤ m and 1 ≤ j1 ≤ j2 ≤ n for rows and columns, respectively. If A = [aij] for i=1,2,...m and j=1,2,...n, the cropped section B can be calculated as B = [bxy] = a(i1+x−1)(j1+y−1) for x=1,2,...p and y=1,2,...q. Therefore, the scaled RGB image has a resolution of 500×375. Now, the contents of RGB and IR photographs are comparable. Figure 6a-6c illustrates the complete technique. Thresholding extracts binary pictures of a certain colour. The threshold ranges are chosen based on the colour gradients that represent each colour. Typically, the colour gradient falls between 0 and 255, with 0 representing black and 255 representing white colours. Pixel values represent the intensity of the relevant pixel. Pixel values are checked and set to 1 if they fall within the necessary range, or 0 otherwise. This is represented by the expression below. The red threshold function is defined as:
Bred(xy)= 1 if 180 <= Bxy ≤ 200, 0 Otherwise
[0059] Similarly for the hues yellow and green. Next, the contour may be fixed by determining limits of the binary pictures. The Moore-neighbour contour tracing technique may be used to determine the contour.
In an example, a pixel with a value of one may be selected. The contour detection technique may check all surrounding pixel values for a 1. Upon discovery, a checking procedure may follow a consistent pattern. Similarly, all 1s may be organized into sets. The sets may serve as border points for contours. Thus, the list of contours may be fixed. A similar procedure may be used to all three binary pictures.
[0060] After determining the outlines, a sketching may be performed for the outlines. Contours may be commonly created by connecting boundary points on a zero image. The zero image may have a same size as the IR image and all pixel values set to 0. The contours may be produced with a set thickness based on the threshold colour. Next, the zero image may be resized using contours to match the size of the resized RGB image. resizing stresses the merging of RGB and IR images. The contour points may be resized first by calculating a scaling factor for both ′x′ and ′y′ directions using original and resized sizes (sfx and sfy). Further, to resize contour points, the scaling factor (sfx * x) and (sfy * y) may be used as (x,y) coordinates. After determining the resizing contour points, distance between the original and resized points may be calculated. Pixel weight may be estimated based on displacement. An average weight of each pixel may be determined to determine an intensity of each new pixel. The image may be resized using the contour points. Further, IR and RGB image be integrated. To overlay the resized RGB image with the outlines from the IR image, resized RGB image may be drawn on the resized zero image first. Overlays may combine the two images by adjusting the blending factor, 'α'. The value of 'α' is '1' for the scaled RGB image, and '0.5' for the resized zero image with contours. The formula for overlay intensity is
(1∗IresizedRGB)+(0.5∗Iresizedzeroimage).
[0061] The final image may blend a resized RGB image with full intensity and a resized zero image with half intensity to depict contours.
[0062] Fig. 7a-7f illustrate an images 700a-700f depicting results of the process 300, in accordance with an embodiment of the present subject matter. Figure 7a-7f depict a number of deformations, including cracks in fig. 7a, bends in fig. 7b, corrosion in fig. 7c, stress-induced necking in fig. 7d, and plastic zone growth in fig. 7e and fig. 7f. The approach may demonstrate good results for several materials and achieving a goal of detecting and pinpointing deformations in structures by combining IR and RGB pictures.
[0063] This present subject matter discloses a methodology combining IR thermography, RGB imaging, and image processing algorithms. The present subject matter may successfully localize deformations and may be used on diverse materials with variable dimensions. The results may be displayed in three coloured contours to illustrate severity levels. The approach revealed different deformations, including cracks, bends, corrosion, stress-induced necking, and plastic zone forms. The present subject matter may be validated using optical microscopy. Microscopic images may show accurate localization of varying degrees of deformation.
[0064] Fig. 8a-8d illustrate a number of images 800a-800d depicting a number of user interfaces displayed on a device incorporating the system 104 for performing a structural health monitoring of an object, in accordance with an embodiment of the present subject matter. The device may be an User Equipment (UE). Examples of the UE may include, but are not limited to, a smartphone, a tablet, a Personal Computer (PC), and a laptop.
[0065] Fig. 9 illustrates a schematic block diagram depicting a method 900 for performing a structural health monitoring of an object, in accordance with an embodiment of the present subject matter. The method 800 may be performed by the system 104 and components thereof.
[0066] At block 902, the method 900 includes receiving, by a receiving engine, a plurality of images comprising a first image and a second image of the object as an input.
[0067] At block 904, the method 900 includes thresholding, by a thresholding engine, the first image to generate a plurality of binary images of a plurality of colors, associated with the first image, wherein the first image comprises the plurality of colors.
[0068] At block 906, the method 900 includes determining, by a contour engine, a contour associated with each binary image amongst the plurality of binary images based on a limit associated with each binary image.
[0069] At block 908, the method 900 includes drawing, by the contour engine, the contour associated with plurality of binary images on a zero image.
[0070] At block 910, the method 900 includes overlaying, by an overlaying engine, the contour associated with each binary image amongst the plurality of images on a second image amongst the plurality of images to generate an output image, wherein the output image is monitored to determine the structural health of the object
[0071] While the embodiments of the disclosure are subject to various modifications and alternative forms, specific embodiment thereof have been shown by way of example in the figures and will be described below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.
[0072] The terms "comprises", "comprising", or any other variations thereof used in the disclosure, are intended to cover a non-exclusive inclusion, such that a device, system, assembly that comprises a list of components does not include only those components but may include other components not expressly listed or inherent to such system, or assembly, or device. In other words, one or more elements in a system or device proceeded by "comprises… a" does not, without more constraints, preclude the existence of other elements or additional elements in the system or device.
[0073] It will be further appreciated that functions or structures of a number of components or steps may be combined into a single component or step, or the functions or structures of one-step or component may be split among plural steps or components. The present invention contemplates all of these combinations. Unless stated otherwise, dimensions and geometries of the various structures depicted herein are not intended to be restrictive of the invention, and other dimensions or geometries are possible. In addition, while a feature of the present invention may have been described in the context of only one of the illustrated embodiments, such feature may be combined with one or more other features of other embodiments, for any given application. It will also be appreciated from the above that the fabrication of the unique structures herein and the operation thereof also constitute methods in accordance with the present invention. The present invention also encompasses intermediate and end products resulting from the practice of the methods herein. The use of "comprising" or "including" also contemplates embodiments that "consist essentially of" or "consist of" the recited feature.

, Claims:We Claim:
1. A method (900) for a structural health monitoring of an object, comprising:
receiving, by a receiving engine (208), a plurality of images comprising a first image and a second image of the object as an input;
thresholding, by a thresholding engine (210), the first image to generate a plurality of binary images of a plurality of colors, associated with the first image, wherein the first image comprises the plurality of colors;
determining, by a contour engine (212), a contour associated with each binary image amongst the plurality of binary images based on a limit associated with each binary image;
drawing, by the contour engine (212), the contour associated with plurality of binary images on a zero image; and
overlaying, by an overlaying engine (214), the contour associated with each binary image amongst the plurality of images on a second image amongst the plurality of images to generate an output image, wherein the output image is monitored to determine the structural health of the object.
2. The method (900) as claimed in claim 1, wherein thresholding the first image comprises:
selecting, by the thresholding engine (210), a plurality of threshold ranges associated with each color gradient of the plurality of colors; and
setting, by the thresholding engine (210), a pixel value for each color amongst the plurality of colors to one of 1 and 0 based on a threshold range amongst the plurality of threshold ranges associated with each color to generate the plurality of binary images, wherein the pixel value of each color is set to 1 if the pixel value lies within the plurality of threshold ranges and the pixel value of each color is set to 0 if the pixel value lies outside the plurality of the threshold ranges.
3. The method (900) as claimed in claim 1, wherein determining the contour associated with each binary image comprises:
determining, by the contour engine (212), the limit associated with each binary image; and
connecting, by the contour engine (212), one or more boundary points corresponding to the limit on the zero image, wherein the zero image is of a size similar to a first size of the first image, with pixel value set to 0;
4. The method (900) as claimed in claim 1, wherein the output image indicates one of a presence and an absence of a deformation on the object.
5. The method (900) as claimed in claim 1, wherein the object is made up of one of mild steel and DMR 249 grade ship steel.
6. The method (900) as claimed in claim 1, comprising:
determining, by the overlaying engine (214), a first size associated with the first image and a second size associated with the second image is not equal to one another;
resizing, by the overlaying engine (214), the second image prior to overlaying the contour associated with each binary image upon the determination, wherein resizing the second image adjusts a size of a Region of Interest of the second image with respect to the first image to align contents of the first image and the second image.
7. The method (900) as claimed in claim 1, comprising:
resizing, by the overlaying engine (214), the contour associated with each binary image with respect to the second image prior to overlaying.
8. The method (900) as claimed in claim 1, wherein the first image and the second image are captured by a first lens and a second lens of a camera unit (102).
9. The method (900) as claimed in claim 1 or 7, wherein the first lens is an IR lens and the first image is an IR image, and the second lens is an RGB lens and the second image is an RGB image.
10. A system (104) for a structural health monitoring of an object, comprising:
a receiving engine (208) configured to receive a plurality of images comprising a first image and a second image of the object as an input;
a thresholding engine (210) configured to threshold the first image to generate a plurality of binary images of a plurality of colors, associated with the first image, wherein the first image comprises the plurality of colors;
a contour engine (212) configured to:
determine a contour associated with each binary image amongst the plurality of binary images based on a limit associated with each binary image; and
draw the contour associated with plurality of binary images on a zero image; and
an overlaying engine (214) configured to overlay the contour associated with each binary image amongst the plurality of images on a second image amongst the plurality of images to generate an output image, wherein the output image is monitored to determine a structural health of the object.

Documents