An infrared image quality evaluation method and infrared equipment detection method using the same

Abstract

The present invention relates to the field of infrared equipment processing technology, and specifically to an infrared image quality evaluation method and an infrared equipment detection method using the same. The infrared image quality evaluation method includes the following steps: S1: establishing an image quality evaluation environment; S2: photographing a heating area with an infrared device to obtain an infrared image, and then proceeding to step S3 or step S4; S3: determining whether the clarity of the infrared image detected by the clarity detection is greater than a preset clarity threshold; if so, determining that the infrared image detected by the clarity detection is clear; otherwise, determining that the infrared image detected by the clarity detection is blurred; S4: determining whether the uniformity of the infrared image detected by the uniformity detection meets a preset uniformity requirement; if so, determining that the uniformity of the infrared image detected by the uniformity detection is qualified; otherwise, determining that the uniformity of the infrared image detected by the uniformity detection is unqualified. The present invention can perform quality evaluation on infrared images with high detection accuracy.

Description

Technical Field

[0001] The present invention relates to the field of infrared equipment processing technology, and in particular to an infrared image quality evaluation method and an infrared equipment detection method using the same. Background Art

[0002] In recent years, cameras have been widely used in various industries such as intelligent transportation, intelligent attendance, and security monitoring. Among them, infrared cameras, as a special type of camera, have started slowly in China. Therefore, for the production and manufacturing of infrared equipment, domestic manufacturers have relatively confusing testing standards and cumbersome testing steps when testing various parameters of infrared equipment after production. The existing testing process generally adopts manual subjective judgment. Due to the non-standard testing environment, the same person often tests the same equipment in different environments with different test results, or the same batch of equipment has poor imaging consistency after testing.

[0003] Or, as disclosed in a Chinese patent, an infrared thermal imaging lens imaging quality detection system and its control method (publication number: CN202210542456.5). In this patented technology, a thermal image of the target is acquired through an image acquisition module, and then the thermal image is analyzed through an image analysis module to obtain the detection result of the tested lens. On the one hand, the detection result is quantified to avoid the influence of the operator's subjective judgment on the detection result, making the detection result more accurate and realizing the digitization of the detection result. However, it can only detect the clarity of the infrared device, and the detection range is narrow, and it cannot quantify the various parameters of the infrared device in many aspects. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that the detection standards of the existing infrared image quality evaluation methods are relatively confusing, the detection steps are relatively complicated, and the detection range is relatively narrow.

[0005] To solve the above technical problems, the first aspect of the present invention adopts the following technical solution: a method for evaluating infrared image quality, comprising the following steps:

[0006] S1: Initialize the infrared image quality evaluation method and build the image quality evaluation environment;

[0007] S2: Use an infrared device to photograph the heating area and obtain an infrared image. When the clarity of the infrared image needs to be tested, use the infrared device to photograph the heating area with clear edges to obtain a clarity test infrared image, and then proceed to step S3. When the uniformity of the infrared image needs to be tested, use the infrared device to photograph the heating area with uniform heating to obtain a uniformity test image, and then proceed to step S4.

[0008] S3: Determine whether the clarity of the infrared image detected by the clarity test is greater than a preset clarity threshold. If it is greater than the clarity threshold, the infrared image detected by the clarity test is determined to be clear. Otherwise, the infrared image detected by the clarity test is determined to be blurred. If no detection is required or the uniformity of the infrared image has been detected, the quality evaluation is terminated and all judgment results are output. Otherwise, the process proceeds to step S2.

[0009] S4: Determine whether the uniformity of the uniformity detection infrared image meets the preset uniformity requirement. If it does, determine that the uniformity of the uniformity detection infrared image is qualified. Otherwise, determine that the uniformity of the uniformity detection infrared image is unqualified. When the clarity of the infrared image is not needed or has been detected, end the quality evaluation and output all judgment results. Otherwise, go to step S2.

[0010] When the present invention is working, it can evaluate the quality of infrared images, standardize the image quality evaluation environment, and detect the clarity and uniformity of infrared images with fewer detection steps, high detection accuracy and a wide detection range.

[0011] Preferably, in step S2, when obtaining a definition detection infrared image by photographing a heating area with clear edges through an infrared device, the following steps are adopted: photographing a heating area with clear edges through an infrared device, converting the obtained infrared image into a grayscale image, filtering the grayscale image, and then filtering the grayscale image. Figure 2 After quantization, the spots are removed and the outline of the heating area is obtained. The effective detection area in the acquired infrared image is segmented by the outline to obtain a clear infrared detection image.

[0012] When working, it can segment the effective detection area in the infrared image, thereby avoiding the influence of the surrounding environment on the detection results and improving the detection accuracy.

[0013] Preferably, in step S3, when judging whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold, the following steps are adopted: the acquired clarity detection infrared image is converted into a grayscale image, and after convolving the acquired grayscale image with the Laplace operator, a variance value is obtained by calculation. The variance value is the clarity of the clarity detection infrared image, and it is judged whether the variance value is greater than the preset clarity threshold.

[0014] When working, the use of Laplace operator can quickly and simply quantify the clarity of the infrared image, making it convenient to judge whether the infrared image is clear and the judgment accuracy is high.

[0015] Preferably, in step S3, when performing convolution on the acquired grayscale image using the Laplacian operator, the sign of the edge portion is set to be opposite to the sign of the middle portion.

[0016] When working, it can keep consistent with the original infrared image and avoid data loss during binarization.

[0017] Preferably, in step S3, when determining whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold, the following steps are adopted:

[0018] A1: Convert the acquired clarity detection infrared image into a grayscale image;

[0019] A2: Use fast Fourier transform to perform a two-dimensional Fourier transform on the grayscale image, converting the grayscale image from the spatial domain to the frequency domain, shifting the spectrum, moving the low-frequency components to the center of the spectrum, and placing the zero frequency of the spectrum at the center.

[0020] A3: Calculate the square of the amplitude of the spectrum, take the absolute values ​​of the real and imaginary parts of the spectrum, square them, and then sum them to obtain the energy value of the spectrum. Determine whether the energy value is greater than the preset clarity threshold.

[0021] When working, by calculating the energy value of the spectrum, it can accurately judge the clarity of the infrared image when the shooting distance is too close, with high judgment accuracy and strong anti-interference ability.

[0022] Preferably, in step S4, when judging whether the uniformity detection infrared image meets the preset uniformity requirement, the following steps are adopted: converting the obtained uniformity detection infrared image into a grayscale image, obtaining the grayscale values ​​of each part of the uniformity detection infrared image, and obtaining the average grayscale value of the uniformity detection infrared image by calculation, comparing the grayscale values ​​of each part of the uniformity detection infrared image with the average grayscale value, and judging whether the grayscale values ​​of each part of the uniformity detection infrared image all meet the condition of being within the allowable error range of the average grayscale value.

[0023] Preferably, step S4 further includes a step of marking bright and dark corners in the uniformity detection infrared image, and setting an average grayscale floating range according to the average grayscale value of the uniformity detection infrared image. When it is necessary to mark the bright corners in the uniformity detection infrared image, the parts of the uniformity detection infrared image whose grayscale values ​​are greater than the maximum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a bright corner mark binary image. When it is necessary to mark the dark corners in the uniformity detection infrared image, the parts of the uniformity detection infrared image whose grayscale values ​​are less than the minimum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a dark corner mark binary image.

[0024] A second aspect of the present invention provides an infrared device detection method, which applies the above-mentioned infrared image quality evaluation method, including the following steps:

[0025] B1: Initialize the infrared image quality evaluation method, build the image quality evaluation environment, locate the infrared equipment to be tested, and prepare the clarity and uniformity detection tools;

[0026] B2: After the image quality evaluation environment meets the standards, run the device preview demo and enable preview of the infrared device to be tested;

[0027] B3: Position the clarity detection tool or the uniformity detection tool according to the field of view of the infrared device to be tested, activate the image quality evaluation tool, and capture the infrared image. When the clarity of the infrared device to be tested needs to be tested, the infrared device to be tested photographs the clarity detection tool to obtain a clarity detection infrared image, and then proceed to step B4. When the uniformity of the infrared device to be tested needs to be tested, the infrared device to be tested photographs the uniformity detection tool to obtain a uniformity detection image, and then proceed to step B5.

[0028] B4: Determine whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold. If it is greater than the clarity threshold, the clarity detection infrared image is determined to be clear, and the clarity of the infrared device to be tested is determined to be qualified. Otherwise, the clarity detection infrared image is determined to be blurred, and the clarity of the infrared device to be tested is determined to be unqualified. If no detection is required or the uniformity of the infrared device to be tested has been detected, the quality evaluation is terminated and all judgment results are output. Otherwise, the process proceeds to step B3.

[0029] B5: Determine whether the uniformity of the uniformity detection infrared image meets the preset uniformity requirement. If so, determine that the uniformity of the uniformity detection infrared image is qualified, and at the same time determine that the uniformity of the infrared device to be tested is qualified. Otherwise, determine that the uniformity of the uniformity detection infrared image is unqualified, and at the same time determine that the uniformity of the infrared device to be tested is unqualified. When the clarity of the infrared device to be tested is not needed or has been tested, end the quality evaluation and output all judgment results. Otherwise, go to step B3.

[0030] During operation, it can realize the detection of infrared equipment, standardize the detection environment and detection steps, and can detect the clarity and uniformity of infrared equipment. It has fewer detection steps, high detection accuracy, and a wide detection range. At the same time, it can quantify various parameters of the infrared equipment, making it convenient for operators to carry out the next step of work.

[0031] Preferably, in step B1, when preparing the clarity detection tooling and the uniformity detection tooling, the following steps are adopted: by dividing an opening on the partition and setting marking points around the opening, the partition is covered and installed on the heating plate to prepare the clarity detection tooling; using a heating plate that heats evenly and has a heating area larger than the shooting area of ​​the infrared device to be tested, the uniformity detection tooling is prepared.

[0032] Preferably, in step B3, when it is necessary to detect the clarity of the infrared device to be tested, the clarity detection tooling is photographed by the infrared device to be tested, and when a clarity detection infrared image is obtained, the following steps are adopted to use marking points to segment the effective detection area in the captured infrared image to obtain a clarity detection infrared image.

[0033] During operation, by dividing the openings on the partition, a heating area with clear edges can be obtained, which can reduce environmental interference, facilitate the calculation of the clarity algorithm, and improve detection accuracy. At the same time, by setting marking points, it is convenient to divide the effective detection area in the infrared image, thereby avoiding the influence of the surrounding environment on the detection results and improving detection accuracy.

[0034] The beneficial technical effects of the present invention include:

[0035] 1. The present invention can evaluate the quality of infrared images, standardize the image quality evaluation environment, and detect the clarity and uniformity of infrared images. It has fewer detection steps, higher detection accuracy, and a wider detection range.

[0036] 2. The present invention can segment the effective detection area in the infrared image by setting marking points, thereby avoiding the influence of the surrounding environment on the detection results and improving the detection accuracy.

[0037] 3. The present invention uses the Laplace operator to quickly and simply quantify the clarity of the infrared image, making it convenient to judge whether the infrared image is clear with high judgment accuracy.

[0038] 4. The present invention can accurately judge the clarity of the infrared image when the shooting distance is too close by calculating the energy value of the spectrum, with high judgment accuracy and strong anti-interference ability.

[0039] 5. The present invention can realize the detection of infrared equipment, standardize the detection environment and detection steps, and can detect the clarity and uniformity of infrared equipment. It has fewer detection steps, high detection accuracy, and a wide detection range. At the same time, it can quantify various parameters of the infrared equipment, making it convenient for operators to carry out the next step of work.

[0040] 6. The present invention can obtain a heating area with clear edges by dividing the opening on the partition, reducing environmental interference, facilitating the calculation of the clarity algorithm, and improving detection accuracy. At the same time, by setting marking points, it is convenient to divide the effective detection area in the infrared image, thereby avoiding the influence of the surrounding environment on the detection results and improving detection accuracy.

[0041] Other features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the accompanying drawings:

[0043] Figure 1 This is a flow chart of Embodiment 1 of the present invention;

[0044] Figure 2 This is a flowchart of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0045] The following is an explanation and description of the technical solutions of the embodiments of the present invention in conjunction with the drawings of the embodiments of the present invention. However, the following embodiments are only preferred embodiments of the present invention and are not exhaustive. Based on the embodiments in the implementation manner, other embodiments obtained by those skilled in the art without creative work are all within the scope of protection of the present invention.

[0046] Example 1

[0047] Please see the attached Figure 1 This embodiment discloses a method for evaluating infrared image quality, comprising the following steps:

[0048] S1: Initialize the infrared image quality evaluation method and build the image quality evaluation environment;

[0049] S2: Use an infrared device to photograph the heating area and obtain an infrared image. When the clarity of the infrared image needs to be tested, use the infrared device to photograph the heating area with clear edges to obtain a clarity test infrared image, and then proceed to step S3. When the uniformity of the infrared image needs to be tested, use the infrared device to photograph the heating area with uniform heating to obtain a uniformity test image, and then proceed to step S4.

[0050] S3: Determine whether the clarity of the infrared image detected by the clarity test is greater than a preset clarity threshold. If it is greater than the clarity threshold, the infrared image detected by the clarity test is determined to be clear. Otherwise, the infrared image detected by the clarity test is determined to be blurred. If no detection is required or the uniformity of the infrared image has been detected, the quality evaluation is terminated and all judgment results are output. Otherwise, the process proceeds to step S2.

[0051] S4: Determine whether the uniformity of the uniformity detection infrared image meets the preset uniformity requirement. If it does, determine that the uniformity of the uniformity detection infrared image is qualified. Otherwise, determine that the uniformity of the uniformity detection infrared image is unqualified. When the clarity of the infrared image is not needed or has been detected, end the quality evaluation and output all judgment results. Otherwise, go to step S2.

[0052] When working, it can evaluate the quality of infrared images, standardize the image quality evaluation environment, and detect the clarity and uniformity of infrared images. It has fewer detection steps, high detection accuracy, and a wide detection range.

[0053] Preferably, in step S2, when obtaining a definition detection infrared image by photographing a heating area with clear edges through an infrared device, the following steps are adopted: photographing a heating area with clear edges through an infrared device, converting the obtained infrared image into a grayscale image, filtering the grayscale image, and then filtering the grayscale image. Figure 2 After quantization, the spots are removed and the outline of the heating area is obtained. The effective detection area in the acquired infrared image is segmented by the outline to obtain a clear infrared detection image.

[0054] When working, it can segment the effective detection area in the infrared image, thereby avoiding the influence of the surrounding environment on the detection results and improving the detection accuracy.

[0055] In specific implementation, the following code can be used to achieve the above functions:

[0056] gray=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)

[0057] blurred=cv2.GaussianBlur(gray,(11,11),0)

[0058] ret = cv2.meanStdDev(gray)

[0059] thresh=cv2.threshold(blurred,av_rgb+rgb_range,255,cv2.THRESH_BINARY)[1]

[0060] thresh=cv2.erode(thresh,None,iterations=2)

[0061] thresh=cv2.dilate(thresh,None,iterations=4)

[0062] labels=measure.label(thresh,connectivity=2,background=0)

[0063] mask=np.zeros(thresh.shape,dtype="uint8")

[0064] ifnumPixels>100:

[0065] mask=cv2.add(mask,labelMask)

[0066] cnts=cv2.findContours(mask.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

[0067] (boundingRect)

[0068] (x,y,w,h)=cv2.boundingRect(c)

[0069] grab_r=ImageGrab.grab((x,y,w,h))

[0070] img=ImageTk.PhotoImage(image=grab_r)

[0071] Preferably, in step S3, when determining whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold, the following steps are adopted: the acquired clarity detection infrared image is converted into a grayscale image, and after convolving the acquired grayscale image with the Laplace operator, a variance value is obtained by calculation. The variance value is the clarity of the clarity detection infrared image, and it is determined whether the variance value is greater than the preset clarity threshold.

[0072] When working, the use of Laplace operator can quickly and simply quantify the clarity of the infrared image, making it convenient to judge whether the infrared image is clear and the judgment accuracy is high.

[0073] In specific implementation, a 3×3 Laplace operator can be used for convolution to obtain a variance value, and a clarity threshold can be set according to actual needs, which is suitable for detecting corresponding infrared images.

[0074] In specific implementation, the following code can be used to achieve the above functions:

[0075] mage=cv2.imread(file_name)

[0076] gray=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)

[0077] value=cv2.Laplacian(image,cv2.CV_64F).var()

[0078] Preferably, in step S3, when the Laplacian operator is used to perform convolution with the obtained grayscale image, the sign of the edge part is set to be opposite to the sign of the middle part. In the specific implementation, a 3×3 Laplacian operator is used for convolution, and the depth data type of the cv2.CV_64F output image can use -1 to keep it consistent with the original image. np.uint8 can be used to set the depth data type of the output image to be consistent with the original image through the parameter -1 to avoid data loss.

[0079] As a further improvement to this embodiment, when the shooting distance is too close, the following steps can be used to determine the clarity:

[0080] A1: Convert the acquired clarity detection infrared image into a grayscale image;

[0081] A2: Use fast Fourier transform to perform a two-dimensional Fourier transform on the grayscale image, converting the grayscale image from the spatial domain to the frequency domain, shifting the spectrum, moving the low-frequency components to the center of the spectrum, and placing the zero frequency of the spectrum at the center.

[0082] A3: Calculate the square of the amplitude of the spectrum, take the absolute values ​​of the real and imaginary parts of the spectrum, square them, and then sum them to obtain the energy value of the spectrum. Determine whether the energy value is greater than the preset clarity threshold.

[0083] When working, by calculating the energy value of the spectrum, it can accurately judge the clarity of the infrared image when the shooting distance is too close, with high judgment accuracy and strong anti-interference ability.

[0084] In specific implementation, the following code can be used to achieve the above functions:

[0085] spectrum=scipy.fft.fftshift(scipy.fft.fft2(image))

[0086] energy=numpy.sum(numpy.abs(spectrum)**2)

[0087] Preferably, in step S4, when judging whether the uniformity detection infrared image meets the preset uniformity requirement, the following steps are adopted: converting the obtained uniformity detection infrared image into a grayscale image, obtaining the grayscale values ​​of each part of the uniformity detection infrared image, and obtaining the average grayscale value of the uniformity detection infrared image by calculation, comparing the grayscale values ​​of each part of the uniformity detection infrared image with the average grayscale value, and judging whether the grayscale values ​​of each part of the uniformity detection infrared image all meet the condition of being within the allowable error range of the average grayscale value.

[0088] Preferably, the step S4 further includes the step of marking the bright and dark corners in the uniformity detection infrared image, and setting the average grayscale floating range according to the average grayscale value of the uniformity detection infrared image. When it is necessary to mark the bright corners in the uniformity detection infrared image, the parts of the uniformity detection infrared image whose grayscale values ​​are greater than the maximum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a bright corner mark binary image. When it is necessary to mark the dark corners in the uniformity detection infrared image, the parts of the uniformity detection infrared image whose grayscale values ​​are less than the minimum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a dark corner mark binary image.

[0089] In specific implementation, the following code can be used to achieve the above functions:

[0090] image=cv2.imread(path)

[0091] gray=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)

[0092] av_rgb=int(cv2.meanStdDev(gray)[0][0][0])

[0093] thresh=cv2.threshold(blurred,av_rgb+rgb_range,255,cv2.THRESH_BINARY)[1]

[0094] thresh=cv2.threshold(blurred,av_rgb+rgb_range,255,cv2.THRESH_BINARY_INV)[1]

[0095] Example 2

[0096] Please see the attached Figure 2 This embodiment provides an infrared device detection method. The similarities with the first embodiment are not repeated here. The differences are described in detail below with reference to the accompanying drawings.

[0097] In this embodiment, the following steps are included:

[0098] B1: Initialize the infrared image quality evaluation method, build the image quality evaluation environment, locate the infrared equipment to be tested, and prepare the clarity and uniformity detection tools;

[0099] B2: After the image quality evaluation environment meets the standards, run the device preview demo and enable preview of the infrared device to be tested;

[0100] B3: Position the clarity detection tool or the uniformity detection tool according to the field of view of the infrared device to be tested, activate the image quality evaluation tool, and capture the infrared image. When the clarity of the infrared device to be tested needs to be tested, the infrared device to be tested photographs the clarity detection tool to obtain a clarity detection infrared image, and then proceed to step B4. When the uniformity of the infrared device to be tested needs to be tested, the infrared device to be tested photographs the uniformity detection tool to obtain a uniformity detection image, and then proceed to step B5.

[0101] B4: Determine whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold. If it is greater than the clarity threshold, the clarity detection infrared image is determined to be clear, and the clarity of the infrared device to be tested is determined to be qualified. Otherwise, the clarity detection infrared image is determined to be blurred, and the clarity of the infrared device to be tested is determined to be unqualified. If no detection is required or the uniformity of the infrared device to be tested has been detected, the quality evaluation is terminated and all judgment results are output. Otherwise, the process proceeds to step B3.

[0102] B5: Determine whether the uniformity of the uniformity detection infrared image meets the preset uniformity requirement. If so, determine that the uniformity of the uniformity detection infrared image is qualified, and at the same time determine that the uniformity of the infrared device to be tested is qualified. Otherwise, determine that the uniformity of the uniformity detection infrared image is unqualified, and at the same time determine that the uniformity of the infrared device to be tested is unqualified. When the clarity of the infrared device to be tested is not needed or has been tested, end the quality evaluation and output all judgment results. Otherwise, go to step B3.

[0103] During operation, it can realize the detection of infrared equipment, standardize the detection environment and detection steps, and can detect the clarity and uniformity of infrared equipment. It has fewer detection steps, high detection accuracy, and a wide detection range. At the same time, it can quantify various parameters of the infrared equipment, making it convenient for operators to carry out the next step of work.

[0104] Preferably, in step B1, when preparing the clarity detection tooling and the uniformity detection tooling, the following steps are adopted: by dividing an opening on the partition and setting marking points around the opening, the partition is covered and installed on the heating plate to prepare the clarity detection tooling; a heating plate that heats evenly and whose heating area is larger than the shooting area of ​​the infrared device to be tested is used to prepare the uniformity detection tooling. In specific implementation, the temperature of the heating plate is preferably 60 degrees, which can be highlighted in the infrared image to avoid the influence of the external temperature on the detection results. A heating plate that heats evenly and whose heating area is larger than the shooting area of ​​the infrared device to be tested is used to prepare the uniformity detection tooling. In specific implementation, the temperature of the heating plate is preferably 30 degrees, which is lower than the operating temperature of the movement, so that the acquired infrared image can better reflect the uniformity of the infrared device.

[0105] During operation, in order to avoid the blurred edges of the heating plate in the infrared image due to thermal radiation, openings are divided on the partition to obtain a heating area with clear edges, which reduces environmental interference, is conducive to the calculation of the clarity algorithm, and improves detection accuracy.

[0106] Preferably, in step B4, when it is necessary to detect the clarity of the infrared device to be tested, the clarity detection tooling is photographed by the infrared device to be tested, and when obtaining the clarity detection infrared image, the following steps are adopted to use the marking points to segment the effective detection area in the captured infrared image to obtain the clarity detection infrared image.

[0107] During operation, by setting marking points, the effective detection area in the infrared image can be segmented, thereby avoiding the influence of the surrounding environment on the detection results and improving the detection accuracy.

[0108] Preferably, step A5 further includes the step of marking the bright and dark corners of the infrared device to be tested, and setting the average grayscale floating range according to the average grayscale value of the uniformity detection infrared image obtained by taking the infrared device to be tested. When it is necessary to mark the bright corners of the infrared device to be tested, the parts in the uniformity detection infrared image whose grayscale values ​​are greater than the maximum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a bright corner mark binary image. When it is necessary to mark the dark corners of the infrared device to be tested, the parts in the uniformity detection infrared image whose grayscale values ​​are less than the minimum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a dark corner mark binary image.

[0109] During specific implementation, the generated bright corner marker binary image and dark corner marker binary image are provided to the operator, so that the operator can intuitively adjust or repair the infrared equipment based on the bright corner marker binary image and dark corner marker binary image, thereby reducing the operator's labor intensity and improving work efficiency.

[0110] The beneficial technical effects of this embodiment include: being able to evaluate the quality of infrared images, standardizing the image quality evaluation environment, being able to detect the clarity and uniformity of infrared images, having fewer detection steps, high detection accuracy, and a wide detection range.

[0111] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Those skilled in the art will understand that the present invention includes, but is not limited to, the contents described in the drawings and the above specific embodiments. Any modifications that do not deviate from the functional and structural principles of the present invention are intended to be included within the scope of the claims.

Claims

1. A method for evaluating infrared image quality, characterized in that: The following steps are involved: S1: Initialize the infrared image quality evaluation method and build the image quality evaluation environment; S2: Use an infrared device to photograph the heating area and obtain an infrared image. When the clarity of the infrared image needs to be tested, use the infrared device to photograph the heating area with clear edges to obtain a clarity test infrared image, and then proceed to step S3. When the uniformity of the infrared image needs to be tested, use the infrared device to photograph the heating area with uniform heating to obtain a uniformity test image, and then proceed to step S4. S3: Determine whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold, specifically by the following steps: A1: Convert the acquired clarity detection infrared image into a grayscale image; A2: Use fast Fourier transform to perform a two-dimensional Fourier transform on the grayscale image, converting the grayscale image from the spatial domain to the frequency domain, shifting the spectrum, moving the low-frequency components to the center of the spectrum, and placing the zero frequency of the spectrum at the center. A3: Calculate the square of the spectrum amplitude, take the absolute values ​​of the real and imaginary parts of the spectrum, square them, and sum them to obtain the energy value of the spectrum. Determine whether the energy value is greater than the preset clarity threshold. If the value is greater than the definition threshold, the definition detection infrared image is judged to be clear, otherwise the definition detection infrared image is judged to be blurred. If no detection is required or the uniformity of the infrared image has been detected, the quality evaluation is terminated and all judgment results are output. Otherwise, the process goes to step S2. S4: Determine whether the uniformity of the uniformity detection infrared image meets a preset uniformity requirement. Specifically, the following steps are performed: convert the obtained uniformity detection infrared image into a grayscale image, obtain the grayscale value of each part of the uniformity detection infrared image, and calculate the average grayscale value of the uniformity detection infrared image. Compare the grayscale value of each part of the uniformity detection infrared image with the average grayscale value to determine whether the grayscale value of each part of the uniformity detection infrared image satisfies the condition of being within the allowable error range of the average grayscale value. If the uniformity is satisfied, the uniformity of the infrared image is judged to be qualified; otherwise, the uniformity of the infrared image is judged to be unqualified. If the clarity of the infrared image is not required or has been tested, the quality evaluation is terminated and all judgment results are output; otherwise, the process proceeds to step S2; It also includes the steps of marking bright and dark corners in the uniformity detection infrared image, setting the average grayscale floating range according to the average grayscale value of the uniformity detection infrared image, and when it is necessary to mark the bright corners in the uniformity detection infrared image, the parts of the uniformity detection infrared image whose grayscale values ​​are greater than the maximum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a bright corner mark binary image; when it is necessary to mark the dark corners in the uniformity detection infrared image, the parts of the uniformity detection infrared image whose grayscale values ​​are less than the minimum value of the average grayscale floating range are converted to white, and the remaining parts are converted to black to generate a dark corner mark binary image.

2. The infrared image quality evaluation method according to claim 1, characterized in that: In step S2, when photographing a heating area with clear edges by an infrared device and obtaining a clarity detection infrared image, the following steps are adopted: photographing a heating area with clear edges by an infrared device, converting the obtained infrared image into a grayscale image, filtering the grayscale image, and then binarizing the grayscale image to remove spots, obtaining the outline of the heating area, and segmenting the effective detection area in the obtained infrared image by the outline to obtain a clarity infrared detection image.

3. The infrared image quality evaluation method according to claim 1, characterized in that: In step S3, when determining whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold, the following steps are adopted: the acquired clarity detection infrared image is converted into a grayscale image, and after convolving the acquired grayscale image with the Laplace operator, a variance value is obtained by calculation. The variance value is the clarity of the clarity detection infrared image, and it is determined whether the variance value is greater than the preset clarity threshold.

4. The infrared image quality evaluation method according to claim 3, characterized in that: In step S3, when performing convolution on the acquired grayscale image using the Laplacian operator, the sign of the edge portion is set to be opposite to the sign of the middle portion.

5. A method for detecting infrared equipment, applying the infrared image quality evaluation method according to any one of claims 1 to 4, characterized in that: The following steps are involved: B1: Initialize the infrared image quality evaluation method, build the image quality evaluation environment, locate the infrared equipment to be tested, and prepare the clarity and uniformity detection tools; B2: After the image quality evaluation environment meets the standards, run the device preview demo and enable preview of the infrared device to be tested; B3: Position the clarity detection tool or the uniformity detection tool according to the field of view of the infrared device to be tested, activate the image quality evaluation tool, and capture the infrared image. When the clarity of the infrared device to be tested needs to be tested, the infrared device to be tested photographs the clarity detection tool to obtain a clarity detection infrared image, and then proceed to step B4. When the uniformity of the infrared device to be tested needs to be tested, the infrared device to be tested photographs the uniformity detection tool to obtain a uniformity detection image, and then proceed to step B5. B4: Determine whether the clarity of the clarity detection infrared image is greater than a preset clarity threshold. If it is greater than the clarity threshold, the clarity detection infrared image is determined to be clear, and the clarity of the infrared device to be tested is determined to be qualified. Otherwise, the clarity detection infrared image is determined to be blurred, and the clarity of the infrared device to be tested is determined to be unqualified. If no detection is required or the uniformity of the infrared device to be tested has been detected, the quality evaluation is terminated and all judgment results are output. Otherwise, the process proceeds to step B3. B5: Determine whether the uniformity of the uniformity detection infrared image meets the preset uniformity requirement. If so, determine that the uniformity of the uniformity detection infrared image is qualified, and at the same time determine that the uniformity of the infrared device to be tested is qualified. Otherwise, determine that the uniformity of the uniformity detection infrared image is unqualified, and at the same time determine that the uniformity of the infrared device to be tested is unqualified. When the clarity of the infrared device to be tested is not needed or has been tested, end the quality evaluation and output all judgment results. Otherwise, go to step B3.

6. The infrared device detection method according to claim 5, characterized in that: In step B1, when preparing the clarity detection tooling and the uniformity detection tooling, the following steps are adopted: by dividing an opening on the partition and setting marking points around the opening, the partition is covered and installed on the heating plate to prepare the clarity detection tooling; using a heating plate that heats evenly and has a heating area larger than the shooting area of ​​the infrared device to be tested, the uniformity detection tooling is prepared.

7. The infrared device detection method according to claim 6, characterized in that: In step B3, when it is necessary to detect the clarity of the infrared device to be tested, the clarity detection tooling is photographed by the infrared device to be tested, and when obtaining the clarity detection infrared image, the following steps are adopted to use the marking points to segment the effective detection area in the captured infrared image to obtain the clarity detection infrared image.

Images