CN109447011B - Real-time monitoring method for infrared leakage of steam pipeline - Google Patents
Real-time monitoring method for infrared leakage of steam pipeline Download PDFInfo
- Publication number
- CN109447011B CN109447011B CN201811309793.XA CN201811309793A CN109447011B CN 109447011 B CN109447011 B CN 109447011B CN 201811309793 A CN201811309793 A CN 201811309793A CN 109447011 B CN109447011 B CN 109447011B
- Authority
- CN
- China
- Prior art keywords
- steam
- image
- area
- leakage
- infrared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 238000004891 communication Methods 0.000 claims description 56
- 238000001931 thermography Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 230000000875 corresponding effect Effects 0.000 description 16
- 238000001514 detection method Methods 0.000 description 7
- 230000002596 correlated effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 208000003164 Diplopia Diseases 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 208000029444 double vision Diseases 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Examining Or Testing Airtightness (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a real-time monitoring method for infrared steam pipeline leakage, which comprises the following steps: receiving an infrared thermal image and temperature parameters of a monitoring area acquired by an infrared camera in real time; detecting whether a steam leakage area exists in the monitoring area or not by utilizing the current frame infrared thermal image and the temperature parameter; and judging whether the steam leakage area exists at the position related to the steam leakage area detected in the next frame of infrared thermal image, if so, sending an alarm signal and feeding back the position information of the steam leakage area in the related position until the judgment of all related positions is completed. The real-time monitoring method for the steam pipeline leakage by the infrared ray considers the relevance of the targets in the previous and next frame pictures, adopts a target tracking method, and correlates the coordinate selection of the suspected target area of the next frame with the target coordinate of the current frame, so that the judgment speed of the existence of steam in the next frame picture can be accelerated, and the accuracy of the steam leakage judgment is improved by a mode of joint judgment of two frames.
Description
Technical Field
The invention relates to the field of steam leakage detection, and particularly provides an infrared real-time monitoring method for steam pipeline leakage.
Background
The pipeline leakage detection is mainly aimed at the deeply buried pipeline, and generally adopts an acoustic wave detection method and non-real-time monitoring. The leakage problem of the indoor pipeline is mostly detected by a manually operated portable instrument, and the method has poor real-time performance and is easy to miss detection. The Chinese invention patent CN201711423014 proposes a method for detecting gas leakage by using a robot to carry a visible light camera and a thermal imager through double-vision fusion, and can realize detection of abnormal leakage of a steam pipeline of a spot scene of inspection.
However, this method has the following problems:
1. the steam leakage generated at the flange joint is short in generation time, and the leakage detection is easy to occur by using a robot inspection method.
2. For a scene without a light source, the visible light camera will be completely disabled, and the method is no longer applicable.
Therefore, a new real-time monitoring method for steam pipeline leakage is proposed, so that the method is no longer limited by a light source, and the instantaneous leakage of steam can be rapidly and accurately monitored in a dark environment, which is a problem to be solved urgently.
Disclosure of Invention
In view of this, the present invention aims to provide a real-time infrared monitoring method for steam pipeline leakage, so as to at least solve the problems that the existing steam leakage detection method is not suitable for dark environment and cannot accurately detect instantaneous leakage of steam in time.
The technical scheme provided by the invention is as follows: an infrared real-time monitoring method for steam pipeline leakage comprises the following steps:
s1: receiving an infrared thermal image and temperature parameters of a monitoring area acquired by an infrared camera in real time;
s2: detecting whether a steam leakage area exists in the monitoring area by using the current frame infrared thermal image and the temperature parameter, if so, executing S3, if not, returning to S1 to continue executing,
the method comprises the following steps of detecting whether a steam leakage area exists in a monitoring area by utilizing a current frame infrared thermal image and temperature parameters:
s21: carrying out median filtering on the received infrared thermograph to obtain a de-noised image f (x, y) with part of noise filtered;
s22, performing frame difference on each two adjacent frames of denoised images by using a current frame and two previous frames of images thereof by using a three-frame joint method to obtain two frame difference images, and performing OR operation on each pixel point on the two frame difference images to obtain an image P, wherein the three adjacent frames of denoised images are respectively f1(x, y), f2(x, y), f3(x, y), and f3(x, y) are denoised images corresponding to the infrared thermograph of the current frame, and the image P is P (x, y) ═ f2(x, y) -f 1(x, y) | × | f3(x, y) -f 2(x, y) |;
s23: carrying out binarization processing on the image P to obtain a binarized image Q;
s24: marking and communicating the binary image Q to obtain information of a communicated region, and eliminating an interference communicated region according to the height, width and area of the communicated region;
s25: performing histogram equalization on the image of each reserved communication area, and then performing fixed-size scaling on the equalized image by using a bilinear interpolation method to respectively obtain an image M corresponding to the image of each reserved communication area one by one;
s26: respectively carrying out LBP with the size of 3 x 3 on the image M to obtain LBP images, then sequentially judging whether steam exists in each LBP image, if so, executing S27 until the judgment on all LBP images is finished, and if not, returning to S1 to continue executing;
s27: judging whether a temperature maximum value in a communication area corresponding to an LBP image with steam is larger than a preset steam leakage temperature threshold value or not according to temperature parameters acquired by an infrared camera, if so, primarily judging that the communication area is a steam leakage area and a steam leakage point exists in the communication area, and if not, primarily judging that the communication area is a non-steam leakage area and no steam leakage point exists in the communication area;
s3: judging whether a steam leakage area exists at the position related to the steam leakage area detected in S2 in the next frame of infrared thermography, if so, sending an alarm signal and feeding back the position information of the steam leakage area in the related position until the judgment of all the related positions is completed, if the judgment results of all the related positions are that no steam leakage area exists, returning to execute S1,
wherein, the method for judging whether the steam leakage region exists at the position related to the steam leakage region detected in S2 in the next infrared thermography is as follows:
s31: enlarging the rectangular frame corresponding to the steam leakage area preliminarily determined in the step S2 to obtain a new rectangular frame, taking the new rectangular frame as a position related to the steam leakage area, then extracting a gray scale image of an image in the new rectangular frame in the next frame of infrared thermography, and performing median filtering on the gray scale image to obtain an image P1;
s32: calculating the variance of the image P1, comparing the variance value with a preset variance threshold value iTH, judging whether steam exists in the image P1, if so, executing S33, otherwise, returning to S3, and continuing to further judge the next steam leakage area detected in S2, wherein the variance threshold value iTH is used for distinguishing a steam image from a non-steam image;
s33: performing histogram equalization on the image P1, then performing marking communication to obtain information of a communication region, and eliminating an interference communication region according to the height, width and area of the communication region;
s34: performing histogram equalization on the image of each reserved communication area, and then performing fixed-size scaling on the equalized image by using a bilinear interpolation method to respectively obtain an image M1 corresponding to the image of each reserved communication area one by one;
s35: respectively carrying out LBP with the size of 3 x 3 on the image M1 to obtain LBP images, then sequentially judging whether steam exists in each LBP image, if so, executing S36 until the judgment on all LBP images is finished, and if not, returning to S1 to continue executing;
s36: according to the temperature parameters collected by the infrared camera, whether the temperature maximum value in the communication area corresponding to the LBP image with steam is larger than a preset steam leakage temperature threshold value or not is judged, if yes, the communication area is judged to be a steam leakage area, steam leakage points exist in the communication area, if not, the communication area is judged to be a non-steam leakage area, and the steam leakage points do not exist in the communication area.
Preferably, in S23, the threshold value T for the binarization processing is obtained by the maximum inter-class variance method.
More preferably, in the step of discharging the interference connected region in S24, the threshold ranges of the height and width of the interference connected region are 2 to 10 pixels, and the threshold range of the area is 50 to 80 pixels.
More preferably, in S25, the aspect ratio of the zoomed image is 2 to 10: 1.
more preferably, in S26, the method for determining whether steam is present in the LBP image is as follows: and taking a column vector obtained by connecting the LBP images according to columns as a characteristic vector, classifying the characteristic vector by LDA to obtain a numerical value, and then judging whether steam exists in the LBP image according to the numerical value.
More preferably, in S31, the height of the new rectangular frame is extended by 1/3 to 1 times in the vertical direction with respect to the height of the rectangular frame corresponding to the steam leakage area preliminarily determined in S2, and the width of the new rectangular frame is extended by 1/4 to 1/2 times in the horizontal direction with respect to the width of the rectangular frame corresponding to the steam leakage area preliminarily determined in S2.
More preferably, in S32, the method for determining iTH is: selecting a great number of images with steam and non-steam images, counting the variance value of the two types of images, selecting iTH value to enable the proportion of the number of the steam images exceeding iTH value to the total number of the steam images to be maximum, and the proportion of the number of the non-steam images exceeding iTH value to the total number of the non-steam images to be minimum, and judging that steam exists in the image P1 when the variance of the image P1 exceeds a threshold value iTH.
More preferably, in S35, the method for determining whether steam is present in the LBP image is as follows: and taking a column vector obtained by connecting the LBP images according to columns as a characteristic vector, classifying the characteristic vector by LDA to obtain a numerical value, and judging whether steam exists in the LBP image according to the numerical value.
According to the infrared real-time monitoring method for steam pipeline leakage, the relevance degree of the target (steam) in the previous and next frame pictures is considered, the target tracking method is adopted, the coordinate selection of the suspected target area of the next frame is correlated with the target coordinate of the current frame, the judgment speed of the existence of the steam in the next frame picture can be increased, and the accuracy of steam leakage judgment is improved through a mode of joint judgment of two frames.
Detailed Description
The invention will be further explained with reference to specific embodiments, without limiting the invention.
The invention provides an infrared real-time monitoring method for steam pipeline leakage, which comprises the following steps:
s1: receiving an infrared thermal image and temperature parameters of a monitoring area acquired by an infrared camera in real time;
s2: detecting whether a steam leakage area exists in the monitoring area by using the current frame infrared thermal image and the temperature parameter, if so, executing S3, if not, returning to S1 to continue executing,
the method comprises the following steps of detecting whether a steam leakage area exists in a monitoring area by utilizing a current frame infrared thermal image and temperature parameters:
s21: performing median filtering on the received infrared thermograph to obtain a denoised image f (x, y) with part of noise filtered, wherein the noise of the infrared image is similar to salt-pepper noise, so that a median filtering method is preferably adopted in the step to better remove the noise of the infrared image;
s22, performing frame difference on each two adjacent frames of denoised images by using a current frame and two previous frames of images thereof by using a three-frame joint method to obtain two frame difference images, and performing OR operation on each pixel point on the two frame difference images to obtain an image P, wherein the three adjacent frames of denoised images are respectively f1(x, y), f2(x, y), f3(x, y) and f3(x, y) are denoised images corresponding to the infrared thermograph of the current frame, and the image P is P (x, y) ═ f2(x, y) -f 1(x, y) | × | f3(x, y) -f 2(x, y) |, wherein in the step, the background exposed by motion can be eliminated by using the three-frame joint method to obtain more accurate contour information;
s23: performing binarization processing on the image P to obtain a binarized image Q, preferably, obtaining a threshold value T of the binarization processing by a maximum inter-class variance method, namely an OTSU Otsu method;
s24: marking and communicating the binary image Q to obtain information of a communicated region, and eliminating an interference communicated region according to the height, width and area of the communicated region; preferably, the preset range of the height and width thresholds of the communication area is 2-10 pixels, and the range of the area threshold is 50-80 pixels; in the step, the suspected steam area can be accurately positioned through mark communication;
s25: performing histogram equalization on the image of each reserved communication area, and then performing fixed-size scaling on the equalized image by using a bilinear interpolation method to respectively obtain an image M corresponding to the image of each reserved communication area one by one; wherein the fixed size of zooming is related to the steam form of leakage, preferably, the aspect ratio of the zoomed image is 2-10: 1, optionally 32 x 16 or 24 x 8;
through the step of processing, the suspected steam area is further enhanced to obtain higher contrast ratio of steam and background, the sizes are unified, and classification work can be better carried out;
s26: respectively carrying out LBP with the size of 3 x 3 on the image M to obtain LBP images, then sequentially judging whether steam exists in each LBP image, if so, executing S27 until the judgment on all LBP images is finished, and if not, returning to S1 for continuous execution, wherein the judgment method for judging whether steam exists in the LBP images is as follows: taking a column vector obtained by connecting the LBP images according to columns as a characteristic vector, classifying the characteristic vector by LDA to obtain a numerical value, and then judging whether steam exists in the LBP images according to the numerical value;
s27: judging whether a temperature maximum value in a communication area corresponding to an LBP image with steam is larger than a preset steam leakage temperature threshold value or not according to temperature parameters acquired by an infrared camera, if so, primarily judging that the communication area is a steam leakage area and a steam leakage point exists in the communication area, and if not, primarily judging that the communication area is a non-steam leakage area and no steam leakage point exists in the communication area;
the temperature extreme value in the area acquired by the thermal infrared imager is compared with a preset temperature threshold value, so that whether steam exists in the area can be judged more accurately;
s3: judging whether a steam leakage area exists at the position related to the steam leakage area detected in S2 in the next frame of infrared thermography, if so, sending an alarm signal and feeding back the position information of the steam leakage area in the related position until the judgment of all the related positions is completed, if the judgment results of all the related positions are that no steam leakage area exists, returning to execute S1,
wherein, the method for judging whether the steam leakage region exists at the position related to the steam leakage region detected in S2 in the next infrared thermography is as follows:
s31: enlarging the rectangular frame corresponding to the steam leakage area preliminarily determined in the step S2 to obtain a new rectangular frame, taking the new rectangular frame as a position related to the steam leakage area, then extracting a gray scale image of an image in the new rectangular frame in the next frame of infrared thermography, and performing median filtering on the gray scale image to obtain an image P1; preferably, the height of the new rectangular frame is increased by 1/3-1 times relative to the height of the rectangular frame corresponding to the steam leakage area preliminarily determined in S2, and the width of the new rectangular frame is increased by 1/4-1/2 times relative to the width of the rectangular frame corresponding to the steam leakage area preliminarily determined in S2;
s32: calculating the variance of the image P1, comparing the variance value with a preset variance threshold value iTH, judging whether steam exists in the image P1, if so, executing S33, otherwise, returning to S3, and continuing to further judge the next steam leakage area detected in S2, wherein the variance threshold value iTH is used for distinguishing a steam image from a non-steam image, and the determination method of iTH is preferably as follows: selecting a great number of images with steam and non-steam images, counting the variance value of the two images, selecting iTH value to enable the proportion of the number of the steam images exceeding iTH value to the total number of the steam images to be maximum, and the proportion of the number of the non-steam images exceeding iTH value to the total number of the non-steam images to be minimum, and judging that steam exists in the image P1 when the variance of the image P1 exceeds a threshold value iTH;
s33: performing histogram equalization on the image P1, then performing marking communication to obtain information of a communication region, and eliminating an interference communication region according to the height, width and area of the communication region;
s34: performing histogram equalization on the image of each reserved communication area, and then performing fixed-size scaling on the equalized image by using a bilinear interpolation method to respectively obtain an image M1 corresponding to the image of each reserved communication area one by one;
s35: making 3 × 3 LBPs for the image M1 to obtain LBP images, then sequentially determining whether steam exists in each LBP image, if so, executing S36 until the determination of all LBP images is completed, and if not, returning to S1 to continue executing, wherein the method for determining whether steam exists in an LBP image is preferably as follows: taking a column vector obtained by connecting the LBP images according to columns as a characteristic vector, classifying the characteristic vector by LDA to obtain a numerical value, and judging whether steam exists in the LBP images according to the numerical value;
s36: according to temperature parameters collected by an infrared camera, judging whether a temperature maximum value in a communication area corresponding to an LBP image with steam is larger than a preset steam leakage temperature threshold value or not, if so, judging that the communication area is a steam leakage area, wherein steam leakage points exist in the communication area, otherwise, judging that the communication area is a non-steam leakage area, and no steam leakage points exist in the communication area, wherein the preset steam leakage temperature threshold value is preferably 70% -90% of a steam temperature value in an actual scene.
According to the infrared real-time monitoring method for steam pipeline leakage, the relevance degree of the target (steam) in the previous and next frame pictures is considered, the target tracking method is adopted, the coordinate selection of the suspected target area of the next frame is correlated with the target coordinate of the current frame, the judgment speed of the existence of the steam in the next frame picture can be increased, and the accuracy of steam leakage judgment is improved through a mode of joint judgment of two frames.
The embodiments of the present invention have been written in a progressive manner with emphasis placed on the differences between the various embodiments, and similar elements may be found in relation to each other.
While the embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Claims (8)
1. The real-time infrared monitoring method for steam pipeline leakage is characterized by comprising the following steps:
s1: receiving an infrared thermal image and temperature parameters of a monitoring area acquired by an infrared camera in real time;
s2: detecting whether a steam leakage area exists in the monitoring area by using the current frame infrared thermal image and the temperature parameter, if so, executing S3, if not, returning to S1 to continue executing,
the method comprises the following steps of detecting whether a steam leakage area exists in a monitoring area by utilizing a current frame infrared thermal image and temperature parameters:
s21: carrying out median filtering on the received infrared thermograph to obtain a de-noised image f (x, y) with part of noise filtered;
s22, performing frame difference on each two adjacent frames of denoised images by using a current frame and two previous frames of images thereof by using a three-frame joint method to obtain two frame difference images, and performing OR operation on each pixel point on the two frame difference images to obtain an image P, wherein the three adjacent frames of denoised images are respectively f1(x, y), f2(x, y), f3(x, y), and f3(x, y) are denoised images corresponding to the infrared thermograph of the current frame, and the image P is P (x, y) ═ f2(x, y) -f 1(x, y) | × | f3(x, y) -f 2(x, y) |;
s23: carrying out binarization processing on the image P to obtain a binarized image Q;
s24: marking and communicating the binary image Q to obtain information of a communicated region, and eliminating an interference communicated region according to the height, width and area of the communicated region;
s25: performing histogram equalization on the image of each reserved communication area, and then performing fixed-size scaling on the equalized image by using a bilinear interpolation method to respectively obtain an image M corresponding to the image of each reserved communication area one by one;
s26: respectively carrying out LBP with the size of 3 x 3 on the image M to obtain LBP images, then sequentially judging whether steam exists in each LBP image, if so, executing S27 until the judgment on all LBP images is finished, and if not, returning to S1 to continue executing;
s27: judging whether a temperature maximum value in a communication area corresponding to an LBP image with steam is larger than a preset steam leakage temperature threshold value or not according to temperature parameters acquired by an infrared camera, if so, primarily judging that the communication area is a steam leakage area and a steam leakage point exists in the communication area, and if not, primarily judging that the communication area is a non-steam leakage area and no steam leakage point exists in the communication area;
s3: judging whether a steam leakage area exists at the position related to the steam leakage area detected in S2 in the next frame of infrared thermography, if so, sending an alarm signal and feeding back the position information of the steam leakage area in the related position until the judgment of all the related positions is completed, if the judgment results of all the related positions are that no steam leakage area exists, returning to execute S1,
wherein, the method for judging whether the steam leakage region exists at the position related to the steam leakage region detected in S2 in the next infrared thermography is as follows:
s31: enlarging the rectangular frame corresponding to the steam leakage area preliminarily determined in the step S2 to obtain a new rectangular frame, taking the new rectangular frame as a position related to the steam leakage area, then extracting a gray scale image of an image in the new rectangular frame in the next frame of infrared thermography, and performing median filtering on the gray scale image to obtain an image P1;
s32: calculating the variance of the image P1, comparing the variance value with a preset variance threshold value iTH, judging whether steam exists in the image P1, if so, executing S33, otherwise, returning to S3, and continuing to further judge the next steam leakage area detected in S2, wherein the variance threshold value iTH is used for distinguishing a steam image from a non-steam image;
s33: performing histogram equalization on the image P1, then performing marking communication to obtain information of a communication region, and eliminating an interference communication region according to the height, width and area of the communication region;
s34: performing histogram equalization on the image of each reserved communication area, and then performing fixed-size scaling on the equalized image by using a bilinear interpolation method to respectively obtain an image M1 corresponding to the image of each reserved communication area one by one;
s35: respectively carrying out LBP with the size of 3 x 3 on the image M1 to obtain LBP images, then sequentially judging whether steam exists in each LBP image, if so, executing S36 until the judgment on all LBP images is finished, and if not, returning to S1 to continue executing;
s36: according to the temperature parameters collected by the infrared camera, whether the temperature maximum value in the communication area corresponding to the LBP image with steam is larger than a preset steam leakage temperature threshold value or not is judged, if yes, the communication area is judged to be a steam leakage area, steam leakage points exist in the communication area, if not, the communication area is judged to be a non-steam leakage area, and the steam leakage points do not exist in the communication area.
2. The infrared real-time monitoring method for steam pipeline leakage according to claim 1, characterized in that: in S23, the threshold value T for the binarization processing is obtained by the maximum inter-class variance method.
3. The infrared real-time monitoring method for steam pipeline leakage according to claim 1, characterized in that: in step S24, in the step of excluding the interference connected region, the range of the high and wide thresholds of the interference connected region is 2-10 pixels, and the range of the area threshold is 50-80 pixels.
4. The infrared real-time monitoring method for steam pipeline leakage according to claim 1, characterized in that: in S25, the aspect ratio of the zoomed image is 2-10: 1.
5. the infrared real-time monitoring method for steam pipeline leakage according to claim 1, characterized in that: in S26, the method for determining whether steam is present in the LBP image is as follows: and taking a column vector obtained by connecting the LBP images according to columns as a characteristic vector, classifying the characteristic vector by LDA to obtain a numerical value, and then judging whether steam exists in the LBP image according to the numerical value.
6. The infrared real-time monitoring method for steam pipeline leakage according to claim 1, characterized in that: in S31, the height of the new rectangular frame is respectively extended by 1/3-1 times from the top to the bottom of the rectangular frame corresponding to the steam leakage area preliminarily determined in S2, and the width of the new rectangular frame is respectively extended by 1/4-1/2 times from the left to the right of the rectangular frame corresponding to the steam leakage area preliminarily determined in S2.
7. The infrared real-time monitoring method for steam pipeline leakage according to claim 1, characterized in that: in S32, the determination method iTH is: selecting a great number of images with steam and non-steam images, counting the variance value of the two types of images, selecting iTH value to enable the proportion of the number of the steam images exceeding iTH value to the total number of the steam images to be maximum, and the proportion of the number of the non-steam images exceeding iTH value to the total number of the non-steam images to be minimum, and judging that steam exists in the image P1 when the variance of the image P1 exceeds a threshold value iTH.
8. The method for real-time infrared monitoring of steam line leaks according to any of claims 1 to 7, characterized in that: in S35, the method for determining whether steam is present in the LBP image is as follows: and taking a column vector obtained by connecting the LBP images according to columns as a characteristic vector, classifying the characteristic vector by LDA to obtain a numerical value, and judging whether steam exists in the LBP image according to the numerical value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811309793.XA CN109447011B (en) | 2018-11-06 | 2018-11-06 | Real-time monitoring method for infrared leakage of steam pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811309793.XA CN109447011B (en) | 2018-11-06 | 2018-11-06 | Real-time monitoring method for infrared leakage of steam pipeline |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109447011A CN109447011A (en) | 2019-03-08 |
| CN109447011B true CN109447011B (en) | 2020-07-03 |
Family
ID=65550692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811309793.XA Active CN109447011B (en) | 2018-11-06 | 2018-11-06 | Real-time monitoring method for infrared leakage of steam pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109447011B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109854964B (en) * | 2019-03-29 | 2021-03-19 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN111579080B (en) * | 2020-04-30 | 2021-09-14 | 沈阳天眼智云信息科技有限公司 | Self-calibration method of infrared thermal image body temperature monitor |
| CN113342864B (en) * | 2021-06-02 | 2023-03-24 | 上海蓝色帛缔智能工程有限公司 | Method, system and device for monitoring heat productivity of electronic equipment |
| CN113591683A (en) * | 2021-07-28 | 2021-11-02 | 北京百度网讯科技有限公司 | Attitude estimation method, attitude estimation device, electronic equipment and storage medium |
| CN113945570A (en) * | 2021-10-12 | 2022-01-18 | 揭阳市大立模具厂有限公司 | Detection and identification method for micro-leakage steam defects based on steam characteristic infrared characterization |
| CN114689804B (en) * | 2022-04-14 | 2023-10-13 | 北京环拓科技有限公司 | Method for intelligently monitoring dangerous gas leakage based on VOC (volatile organic compound) gas cloud imaging |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7239719B2 (en) * | 2003-08-22 | 2007-07-03 | Bbn Technologies Corp. | Automatic target detection and motion analysis from image data |
| CN1282132C (en) * | 2004-05-20 | 2006-10-25 | 上海交通大学 | Infra-red and visible light dynamic image interfusion method based on moving target detection |
| TWI382762B (en) * | 2008-11-17 | 2013-01-11 | Ind Tech Res Inst | Method for tracking moving object |
| CN103775830B (en) * | 2014-01-20 | 2016-03-23 | 武汉第二船舶设计研究所 | A kind of high-temperature steam Leak Detection and Location System and method |
| CN103810722A (en) * | 2014-02-27 | 2014-05-21 | 云南大学 | Moving target detection method combining improved LBP (Local Binary Pattern) texture and chrominance information |
| US9400936B2 (en) * | 2014-12-11 | 2016-07-26 | Xerox Corporation | Methods and systems for vehicle tag number recognition |
| CN106446799A (en) * | 2016-08-31 | 2017-02-22 | 浙江大华技术股份有限公司 | Thermal imaging target identification method and apparatus |
| CN206875130U (en) * | 2017-06-02 | 2018-01-12 | 深圳钰湖电力有限公司 | A kind of high-temperature steam leakage monitoring system |
-
2018
- 2018-11-06 CN CN201811309793.XA patent/CN109447011B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109447011A (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447011B (en) | Real-time monitoring method for infrared leakage of steam pipeline | |
| US11221107B2 (en) | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing | |
| CN107705288B (en) | Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion | |
| CN111047568B (en) | Method and system for detecting and identifying steam leakage defect | |
| CN106017691B (en) | Contactless melting metallic solution temperature continuous detecting method and system | |
| CN102982537B (en) | A kind of method and system detecting scene change | |
| CN110610150A (en) | Tracking method, device, computing equipment and medium of target moving object | |
| Jadhav et al. | A fruit quality management system based on image processing | |
| CN109544535B (en) | Peeping camera detection method and system based on optical filtering characteristics of infrared cut-off filter | |
| CN108921828B (en) | Method for identifying insignificant weld joint in complex scene | |
| Zhang et al. | Detection method for pulverized coal injection and particles in the tuyere raceway using image processing | |
| CN109389165A (en) | Oil level gauge for transformer recognition methods based on crusing robot | |
| CN112257523A (en) | Smoke identification method and system of image type fire detector | |
| CN111667470A (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
| CN108364306B (en) | Visual real-time detection method for high-speed periodic motion | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN116630332B (en) | PVC plastic pipe orifice defect detection method based on image processing | |
| CN115830021B (en) | Metal surface defect detection method for hardware machining | |
| TWI381735B (en) | Image processing system and method for automatic adjustment of image resolution for image surveillance apparatus | |
| CN109001674B (en) | WiFi fingerprint information rapid acquisition and positioning method based on continuous video sequence | |
| JP2014182637A (en) | Image processor, image processing method and image processing program | |
| CN111353350A (en) | Flame detection and positioning method based on combined sensor image fusion technology | |
| CN105930813B (en) | A method of detection composes a piece of writing this under any natural scene | |
| CN109544520B (en) | Automatic video image distortion detection method | |
| CN106996934A (en) | Polyphaser vision detection system and detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |