JP5072752B2 - Image analysis method, image analysis apparatus, pipeline inspection system, and program for pipeline inspection using luminance and color difference - Google Patents

Description

  The present invention relates to a pipeline inspection image analysis method, an image analysis apparatus, a pipeline inspection system, and a program using luminance and color difference, and in particular, a pipeline inspection image for color-analyzing and quantifying a situation inside a pipeline. The present invention relates to an analysis method, an image analysis device, a pipeline inspection system, and a program.

  Conventionally, as a method of color-analyzing and quantifying the deterioration status of rust, corrosion, etc. in underground pipes such as communication pipes, power pipes, etc. There is a technique for acquiring a still image of a deteriorated portion using a camera with a visual function or a camera with a wide-angle fisheye lens, and performing color analysis using the RGB method for expressing the acquired still image using R, G, and B primary color components. (See, for example, Non-Patent Document 1).

Burnham Co., Ltd., “Camera / Radar Combined In-Pipe Search System“ P-BESE ”[online], [Search May 15, 2008], Internet, <http://www.burn-am.com /products_sub1_2.html>

  However, in the technique according to Non-Patent Document 1, image analysis of a still image for each deterioration portion for obtaining data (quantification data) quantifying the deterioration state in the tube is performed after measurement / inspection in the tube. Therefore, there is a drawback that the quantification data of the deterioration state cannot be acquired continuously in real time at the time of measurement / inspection. Furthermore, in the technique according to Non-Patent Document 1, in order to perform image analysis of a still image by an RGB method that does not consider luminance, when color analysis is performed on an image irradiated by a light attached to the camera body in a dark place such as in a tube, It is difficult to distinguish subtle color differences. Therefore, it is impossible to accurately analyze only rust and corrosion in a pipe mixed with earth and sand having a color similar to rust.

  The object of the present invention is to solve the above-mentioned problems and obtain a technique (image analysis method for pipe inspection, image analysis apparatus, pipe) that can acquire data obtained by quantifying the situation in the pipe with high accuracy in real time. Road inspection system and program).

In order to solve the above-mentioned problem, the image analysis method for pipeline inspection according to the present invention is:
Obtaining an image (and an insertion distance information) (and an analog of the primary color signal) in the underground pipe (taken by the pipe inspection pipe camera);
(Analog / digital conversion step of converting the analog image acquired by the acquiring step into a digital image)
An image processing step of analyzing the image acquired by the acquiring step and extracting a portion having a predetermined range of colors;
Calculating a ratio between the location extracted by the image processing step and the area of the underground buried pipe;
Look including a step of correcting the ratio calculated by said step of calculating,
The correcting step subtracts a portion other than the underground pipe from the image acquired by the acquiring step using a predetermined correction coefficient .

Moreover, the image analysis method for pipeline inspection according to the embodiment of the present invention includes:
The image processing step includes
Setting an analysis range in the image acquired by the acquiring step, and converting a primary color component of a pixel in the analysis range into a luminance component and a color difference component;
Determining whether the luminance component and color difference component values of the pixels in the analysis range converted by the converting step are in the predetermined range;
The method further includes the step of replacing the color of the pixel determined to have the values of the luminance component and the color difference component in the predetermined range by the predetermined step with a predetermined color.

An image analysis method for pipeline inspection according to another embodiment of the present invention includes:
The method further includes an output step of outputting to the monitor an image in which the color of the pixel having the color in the predetermined range is replaced with the predetermined color by the replacing step.

  As described above, the solution of the present invention has been described as a method. However, the present invention can also be realized as an apparatus for executing the steps of these methods, and these are also included in the scope of the present invention. Please understand.

For example, an image analysis apparatus that implements the present invention as an apparatus is:
An acquisition unit for acquiring an image (and an insertion distance information) (and an analog of the primary color signal) in the underground pipe (taken by a pipe camera for pipe inspection);
(An analog / digital conversion unit that converts an analog image acquired by the acquisition unit into a digital image)
An image processing unit that analyzes the image acquired by the acquisition unit and extracts a portion having a predetermined range of colors;
A calculation unit that calculates a ratio between the location extracted by the image processing unit and the area of the underground buried pipe;
A correction unit that corrects the ratio calculated by the calculation unit ,
The correction unit is
A part other than the underground pipe is subtracted from the image acquired by the acquisition unit using a predetermined correction coefficient .

In addition, an image analysis apparatus according to an embodiment of the present invention includes:
The image processing unit
A conversion unit that sets an analysis range in the image acquired by the acquisition unit, and converts a primary color component of a pixel in the analysis range into a luminance component and a color difference component;
A determination unit that determines whether the luminance component and color difference component values of the pixels in the analysis range converted by the conversion unit are in the predetermined range;
The image processing apparatus further includes a replacement unit that replaces the color of the pixel determined by the determination unit as a value of the luminance component and the color difference component within the predetermined range with a predetermined color.

An image analysis apparatus according to yet another embodiment of the present invention,
The image processing apparatus further includes an output unit that outputs an image in which the color of the pixel having the color in the predetermined range is replaced with a predetermined color by the replacement unit to a monitor.

In addition, a pipe inspection system comprising a pipe camera for pipe inspection of underground pipes according to the present invention and an image analysis device,
The image analyzer is
An acquisition unit that acquires an image (and insertion distance information) (and an analog of the primary color signal) in the underground pipe photographed by the pipe camera;
(An analog / digital conversion unit that converts an image acquired by the acquisition unit into a digital image)
An image processing unit that analyzes the image acquired by the acquisition unit and extracts a portion having a predetermined range of colors;
A calculation unit that calculates a ratio between the location extracted by the image processing unit and the area of the underground buried pipe;
A correction unit that corrects the ratio calculated by the calculation unit ,
The correction unit is
A part other than the underground pipe is subtracted from the image acquired by the acquisition unit using a predetermined correction coefficient .

  Further, the present invention can be realized as a program and a storage medium storing the program, and it should be understood that these are also included in the scope of the present invention. For example, an image analysis program that implements the present invention as a program causes a computer that constitutes an apparatus that executes the above-described image analysis method to execute processing of each step in the image analysis method.

  According to the present invention, even when color analysis is performed on an image obtained by irradiating a light attached to a camera in a dark place such as in a tube, a subtle color difference can be determined, and a color similar to rust is obtained. It is possible to detect rust and corrosion with high accuracy in a pipe mixed with earth and sand. Furthermore, even when there is an existing housing cable or the like in the pipe, the area covered with the existing housing cable or the like and cannot be measured can be canceled, and the accuracy of data can be improved.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a schematic view of a pipeline inspection system according to the present invention. As shown in FIG. 1, the pipe inspection system according to the present invention is a system for inspecting the deterioration condition (rust, corrosion, etc.) of underground pipes 2 connecting between manholes 1, pipe inspection pipe camera 4, An image analysis device 3 for collecting and analyzing data such as images taken by the pipe inspection pipe camera 4 is included. The underground buried pipe 2 has an existing accommodation cable 5 that accommodates a cable for communication or the like. The image analysis device 3 performs image analysis using luminance and color difference, collects moving images by the pipe inspection pipe camera 4, that is, shoots the image, and quantifies data (data that quantifies the deterioration state in the tube). Is calculated. Hereinafter, a method using luminance and color difference is referred to as “luminance color difference method (YCbCr method)”. The monitor (display unit) 6 displays an image analyzed by the image analysis device 3. In the example of FIG. 1, the image analysis device 3 and the monitor 6 are separate devices, but the image analysis device 3 may include a monitor (display unit).

  FIG. 2 is a block diagram of an image analysis apparatus according to the present invention. In the figure, a pipe inspection pipe camera 4, a system control unit 7, and a monitor (display unit) 6 coupled to the image analysis device 3 are also shown. As illustrated, the image analysis apparatus 3 includes an input unit (acquisition unit) 10, an A / D (analog / digital) conversion unit 20, an image processing unit 30, a D / A (digital / analog) conversion unit 40, and an output unit. 50, the control part 60, the memory | storage part 70, and the power supply part 80 are provided. The input unit 10 in the image analysis apparatus 3 receives an image signal inside the underground pipe taken by the pipe inspection pipe camera 4 and insertion distance information of the pipe inspection pipe camera 4 via the system control unit 7. get. The image from the pipe inspection pipe camera 4 is an analog color image signal composed of three primary color components in RGB format. The insertion distance information is the insertion distance of the pipe camera 4 for pipe inspection from the manhole 1 into the underground pipe 2. The system control unit 7 that controls the system sends the distance (inspection section) of the underground buried pipe 4 to be inspected in advance, the traveling speed of the pipe inspection pipe camera 4, and the image to be analyzed by the pipe inspection pipe camera 4. Parameters such as resolution are set in advance, and the system control unit 7 calculates the insertion distance of the pipe inspection pipe camera 4 based on the set parameters, and transmits it to the image analysis apparatus 3 as insertion distance information. .

  The A / D conversion unit 20 performs analog / digital conversion on the analog color image signal from the input unit 10 to generate digital color image data. The image processing unit 30 performs image analysis (image processing) such as color analysis of the image data generated by the A / D conversion unit 20 (details will be described later). The D / A converter 40 converts the digital image data color-analyzed by the image processor 30 into an analog image signal. The output unit 50 outputs the color-analyzed image data as an analog image signal. The storage unit 70 is realized by, for example, a semiconductor memory such as a RAM or a ROM, and stores control information for controlling the entire apparatus, arithmetic expressions used for image analysis such as color analysis, correction processing described later, various parameters, and the like. Store. The storage unit 70 may temporarily store the image data analyzed by the image processing unit 30, the quantification data, and the unprocessed digital image data input from the A / D conversion unit. The control unit 60 controls the entire control based on the control information stored in the storage unit 70. The power supply unit 80 supplies power for driving each component included in the image analysis device 3. The storage unit 70 is not limited to a semiconductor memory, and may be realized by a detachable storage medium such as a magnetic recording tape, an external hard disk, or a large-capacity semiconductor memory. FIG. 3 is a more detailed configuration diagram of the image processing unit 30. As illustrated in FIG. 3, the image processing unit 30 includes a color information conversion unit 31, an encoding / decoding unit 32, a determination unit 33, a color information output unit 34, a calculation unit 35, and a correction unit 36.

  Hereinafter, the function of each component of the image analysis apparatus 3 according to the present invention and the image analysis method (color analysis method) will be described with reference to the flowcharts of FIGS. 4 and 5. FIG. 4 is a flowchart of an example of an image analysis method according to the present invention. First, when the camera head of the pipe inspection pipe camera 4 is inserted into the underground pipe 2 and is operated by the operator, photographing by the pipe inspection pipe camera 4 is started. The image analysis device 3 acquires a moving image (analog color image signal) and insertion distance information captured by the pipe inspection pipe camera 4 via the input unit 10 (step S11).

  Here, an image inside the underground pipe 2 taken by the pipe inspection pipe camera 4 will be described. FIG. 7 is an example of an image (pipeline image) inside the underground pipe 2 taken by the pipe inspection pipe camera 4 and displayed on the monitor (display unit) 6. 7A shows an example of a pipeline image before image analysis, and FIG. 7B shows an example of a pipeline image after image analysis. As shown to Fig.7 (a), the pipe line image 21 is an image by which the inner wall of the underground pipe | tube 2 was image | photographed as the whole. Further, the existing housing cable 5 is photographed and covers a part of the inner wall of the underground pipe 2. The image processing unit 30 sets an analysis range for the pipeline image 21 and performs color analysis on the analysis range. FIG. 6 is an explanatory diagram of the pipeline image displayed on the monitor 6 and its analysis range. As shown in the figure, the analysis range 22 has a shape surrounded by two concentric circles having a radius R from the center of the underground buried pipe and a radius shorter than the circle by the detection width L. A target sphere 23 exists at approximately the center of the two concentric circles. This is a deterioration judgment sphere that is an accessory of the pipe camera. If there is a step due to breakage (bending) in the pipe, a part of the target sphere 23 is hidden and cannot be seen. It is for discriminating.

Returning to the flowchart of FIG. The A / D conversion unit 20 performs analog / digital conversion on the analog color image signal from the input unit 10 to generate digital image data that becomes the above-described pipeline image 21 and outputs the digital image data to the image processing unit 3 (step S12). ). The image analysis apparatus 3 extracts a preset analysis range 22 from the pipeline image 21 for each designated detection width (distance) L (for example, every 5 cm) based on the acquired insertion distance information. Then, color analysis by the luminance color difference method is performed based on a preset color designation to determine rust / corrosion in the analysis range 22 (step S13). Here, the image analysis in step S13 will be described. FIG. 5 is a flowchart of an example of image analysis. First, the color information conversion unit 31 in the image processing unit 30 outputs the image data in the RGB format (red (R), green (G), blue (B) primary color components) output from the A / D conversion unit 20. The luminance component (Y) and the color difference component (Cb, Cr) are converted (step S21). This is done by the following equation.
Y = 0.29891 × R + 0.58661 × G + 10.1448 × B (Formula 1)
Cb = −0.16874 × R−0.33126 × G + 0.50000 × B (Formula 2)
Cr = 0.50,000 × R−0.41869 × G−0.0811 × B (Formula 3)

  Next, the encoding / decoding unit 32 performs encoding / decoding processing of luminance color difference (YCbCr) format data (step S22). First, Cb and Cr after conversion are thinned out to 1/4, respectively, and Cb and Cr are requantized to 16 gradations in order to further reduce the amount of information and speed up processing. Thereafter, the information of Cb and Cr is embedded in Y and encoded (grayscale). Next, the encoded gray scale image is read in units of 2 × 2 blocks, and Cb and Cr information is restored (decoded) from the lower 2 bits of each. Then, Cb and Cr are each multiplied by 16 to obtain a value of 0 to 255, which is a value of Cb and Cr in each pixel (pixel) in the analysis range 22.

  Thereafter, the determination unit 33 compares the color range of rust / corrosion set in advance with respect to the color range of Y, Cb, and Cr (takes values from 0 to 255) in each pixel (pixel) in the analysis range 22. Then, it is determined whether or not the location corresponding to the pixel is rust / corrosion (step S23). For example, if the color range of rust / corrosion is preset to 0 to 24 for all of Y, Cb, and Cr, “rust / corrosion” if all three elements of Y, Cb, and Cr are within the set color range. (Step S24). On the other hand, if even one of these elements is out of the color range, it is not judged as “rust / corrosion”. Then, the determination process of steps S23 and S24 is repeated until it is determined that the determination of the color range for all the pixels in the analysis range 22 is completed (step S25). The determination result by the determination unit 33 is output to the color information output unit 34. For example, earth and sand other than rust and corrosion can be accurately determined in the same manner as rust and corrosion by setting in advance the color range of Y, Cb, and Cr to be judged as earth and sand.

  Returning to the flowchart of FIG. Based on the determination result of the determination unit 33, the color information output unit 34 replaces the pixel at the location determined as rust / corrosion with a predetermined color. In addition, in the case where earth and sand are determined in addition to rust and corrosion, the pixels in the place of earth and sand are replaced with a predetermined color different from the case of rust and corrosion. That is, the color information output unit 34 assigns a different color to each determined type, and performs the coloring of the analysis range 22 based on the determination result of the determination unit 33 (step S17). The D / A conversion unit 40 converts the digital image data in the analysis range 22 colored by the color information output unit 34 into an analog image signal (step S18). The output unit 50 outputs the analog image signal from the D / A conversion unit 40 to the monitor 6. Thereafter, the control unit 60 determines whether there is a next image to be color analyzed (step S20). This is performed by determining from the detection width L and the number of image captures whether or not the inspection section (distance between the manholes 1 in FIG. 1) has been captured. Alternatively, when the pipe inspection pipe camera 4 reaches the manhole 1 as the destination and it is determined that the photographed image is a manhole, it is determined that there is no next image. If it is determined that there is a next image, the process returns to step S11 and the above-described processing is continued.

  FIG. 7B shows an example of a pipeline image after performing the image analysis of FIG. 4 according to the present invention. On the monitor 6, the image of the analysis range 22 colored in real time is superimposed on the image photographed by the pipe inspection pipe camera 4 and displayed. As shown in the figure, it can be seen that rust, corrosion, and the like have been replaced with a predetermined color.

Next, calculation of the corrosion rate will be described. The calculation unit 35 calculates the corrosion rate in the analysis range 22 based on the color analysis result in step S13 (step S14). This indicates the rust / corrosion determined in step S13 in pixel units, and calculates the corrosion rate at a ratio to the analysis range 22 also shown in pixel units. In other words, the following expression is obtained.
Corrosion rate = Number of pixels of rust / corrosion / Number of pixels in analysis range (Formula 4)
This corresponds to obtaining the ratio of the number of pixels replaced with a predetermined color corresponding to rust / corrosion. For example, when discrimination of earth and sand or a hole is also performed, an image substituted with a predetermined color is generated for each discriminated type. Therefore, by calculating the color area ratio of the analysis result for each specified color within the analysis range, the sediment rate, the occurrence rate of holes, and the like can be calculated.

Next, the correction unit 36 performs a correction process for the calculated corrosion rate (step S15). As shown in FIGS. 6 and 7, when there is an existing housing cable 5 or the like in the pipe, the portion covered with the existing housing cable or the like cannot be measured for rust and corrosion. Therefore, in the present invention, the ratio of the area of the existing housing cable to the total area in the pipe is calculated in advance as a correction coefficient, and the quantification data such as the corrosion rate obtained is corrected with the correction coefficient, thereby Avoid impacts on quantified data. This correction coefficient can be expressed by the following equation, where α is a correction coefficient, β is the inner circumference of the pipe, and γ is the diameter of an existing housing cable or the like.
α = (β−γ) / β (Formula 5)
By multiplying the quantification data of the corrosion rate calculated in step S14 by the reciprocal of the correction coefficient α obtained in Equation 5, that is, in Equation 4 for obtaining the corrosion rate, the “number of pixels in the analysis range” of the denominator is obtained. By multiplying by the correction coefficient α, it is possible to subtract (cancel) an area that is covered by an existing housing cable or the like and cannot be measured, and to improve the accuracy of the obtained quantification data. In addition, not only a corrosion rate but the ratio of earth and sand etc. can be corrected similarly. Thereafter, the calculated corrosion rate is stored in the storage unit 70.

  By repeating the processing of step S11 to step S20 for each distance (detection width) L (cm) designated based on the insertion distance information (for example, every 5 cm), color analysis inside the pipeline in the inspection section is performed in real time. be able to. The quantification data calculated for each detection width L and stored in the storage unit 70 can be summed when the above-described processing over the inspection section is completed, and the rust / corrosion rate of the entire inspection section can be calculated. At that time, the effect of the existing housing cable is corrected for each analysis range using the above-mentioned correction coefficient. As a result, the entire area of the pipeline in the inspection section is covered with the existing housing cable and cannot be measured. Accurate quantification data can be obtained in which a large area is canceled.

  The features and effects of the present invention will be described again. The present invention sets an analysis range of a shape surrounded by two concentric circles for a pipeline image photographed by a pipeline inspection camera, and performs image analysis using a luminance color difference method within the analysis range. The rust / corrosion part is detected, the ratio of the detected rust / corrosion area to the pipe inner area is calculated, and the calculated ratio is corrected based on the correction coefficient obtained from the pipe inner circumference and the diameter of the existing housing cable. According to the present invention, since the moving image acquired by the pipe inspection pipe camera can be directly color-analyzed by the image analysis software, it is not necessary to record a still image for analysis, and the deterioration state is quantified in real time. It is possible. Further, by applying the luminance color difference method (YCbCr method) as the color analysis method, it becomes possible to obtain quantification data with higher accuracy than the conventional quantification method by the RGB method.

  As described above, the apparatus for realizing the image analysis method of the embodiment can be suitably realized by a computer. In that case, the processing content for executing each step (see FIGS. 4 and 5) of the image analysis method by the image analysis apparatus is described by a program. Therefore, a program for causing a computer functioning as such an image analysis apparatus to execute the steps shown in FIGS. 4 and 5 is a storage device such as a hard disk connected to the computer, or a ROM or RAM provided in the computer. Or the like can be appropriately stored in a storage device. That is, the image analysis method of the present invention is realized on a computer by executing such a program by a central processing unit (CPU) included in a computer functioning as an image analysis device. In this case, each process of the image analysis method may be realized by a part of hardware.

  Further, the program describing the processing contents can be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include a magnetic recording device, an optical disc, a magneto-optical recording device, and a semiconductor memory.

  In addition, the program describing the processing content can be distributed by selling, transferring, or lending a portable recording medium such as a DVD or a CD-ROM, and such a program can be distributed to a server computer on a network. The program can be distributed by storing it in a recording device and transferring the program from the server computer to another computer via a network.

  Although the present invention has been described based on the drawings and examples, it should be noted that those skilled in the art can easily make various modifications and corrections based on the present disclosure. Therefore, it should be noted that these variations and modifications are included in the scope of the present invention. For example, the functions included in each unit, each step, etc. can be rearranged so that there is no logical contradiction, and a plurality of components, steps, etc. can be combined or divided into one. . For example, the method of acquiring luminance / chrominance format image data from RGB format image data is not limited to the above-described method, and any method that can acquire luminance / chrominance format image data can be used for image analysis. It can be appropriately changed according to the processing capability of the apparatus 3 and the required image resolution.

It is the schematic of the pipe line inspection system by this invention. It is a block diagram of the image analysis apparatus by this invention. 2 is a more detailed configuration diagram of an image processing unit 30. FIG. It is a flowchart of an example of the image analysis method by this invention. It is a flowchart of an example of an image processing method. It is explanatory drawing about the pipeline image displayed on the monitor 6, and its analysis range. It is an example of the pipeline image before image processing displayed on the monitor. It is an example of the pipeline image after the image processing displayed on the monitor.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Manhole 2 Underground pipe 3 Image analyzer 4 Pipe camera for pipe inspection 5 Existing accommodation cable 6 Monitor 7 System control part 10 Input part 20 A / D conversion part 21 Pipe image 22 Analysis range 23 Target sphere 30 Image processing Unit 31 color information conversion unit 32 encoding / decoding unit 33 determination unit 34 color information output unit 35 calculation unit 36 correction unit 40 D / A conversion unit 50 output unit 60 control unit 70 storage unit 80 power supply unit L detection width R radius

Claims (8)

Acquiring an image in the underground pipe;
An image processing step of analyzing the image acquired by the acquiring step and extracting a portion having a predetermined range of colors;
Calculating a ratio between the location extracted by the image processing step and the area of the underground buried pipe;
Correcting the ratio calculated by the calculating step;
Including
The correcting step comprises:
Using a predetermined correction coefficient, subtract a portion other than the underground pipe from the image acquired by the step of acquiring,
An image analysis method characterized by the above. The image analysis method according to claim 1,
The image processing step includes
Setting an analysis range in the image acquired by the acquiring step, and converting a primary color component of a pixel in the analysis range into a luminance component and a color difference component;
Determining whether the luminance component and color difference component values of the pixels in the analysis range converted by the converting step are in the predetermined range;
Further including the step of replacing the color of the pixel determined to have the values of the luminance component and the color difference component in the predetermined range by the determining step with a predetermined color.
An image analysis method characterized by the above. The image analysis method according to claim 2 ,
An output step of outputting to the monitor an image in which the color of the pixel having the color in the predetermined range is replaced with the predetermined color by the replacing step;
An image analysis method characterized by the above. An acquisition unit for acquiring an image in the underground pipe,
An image processing unit that analyzes the image acquired by the acquisition unit and extracts a portion having a predetermined range of colors;
A calculation unit that calculates a ratio between the location extracted by the image processing unit and the area of the underground buried pipe;
A correction unit that corrects the ratio calculated by the calculation unit;
With
The correction unit is
Using a predetermined correction coefficient, subtract a portion other than the underground pipe from the image acquired by the acquisition unit,
An image analysis apparatus characterized by that. The image analysis apparatus according to claim 4,
The image processing unit
A conversion unit that sets an analysis range in the image acquired by the acquisition unit, and converts a primary color component of a pixel in the analysis range into a luminance component and a color difference component;
A determination unit that determines whether the luminance component and color difference component values of the pixels in the analysis range converted by the conversion unit are in the predetermined range;
A replacement unit that replaces the color of a pixel that has been determined by the determination unit to have a value of a luminance component and a color difference component within the predetermined range;
An image analysis apparatus characterized by that. The image analysis apparatus according to claim 5 , wherein
An output unit that outputs to the monitor an image in which the color of the pixel having the color in the predetermined range is replaced by the predetermined color by the replacement unit;
An image analysis apparatus characterized by that. A pipe camera for pipe inspection of underground pipes,
An image analysis device;
A pipeline inspection system comprising:
The image analyzer is
An acquisition unit for acquiring an image of the underground pipe taken by the pipe inspection pipe camera;
An image processing unit that analyzes the image acquired by the acquisition unit and extracts a portion having a predetermined range of colors;
A calculation unit that calculates a ratio between the location extracted by the image processing unit and the area of the underground buried pipe;
A correction unit that corrects the ratio calculated by the calculation unit;
With
The correction unit is
Using a predetermined correction coefficient, subtract a portion other than the underground pipe from the image acquired by the acquisition unit,
A pipeline inspection system characterized by that.   An image analysis program for causing a computer constituting an apparatus for executing the image analysis method according to any one of claims 1 to 3 to execute processing of each step in the image analysis method.