In-tube inspection device, in-tube inspection system, in-tube inspection method and program

The pipe inspection device uses sensor-guided camera operations to enhance imaging clarity and accuracy in diagnosing pipe abnormalities, addressing the challenge of unclear imaging in existing methods.

JP2024159110APending Publication Date: 2024-11-08KK TOSHIBA +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2023074890
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08

Smart Images

  • Figure 2024159110000001_ABST
    Figure 2024159110000001_ABST
Patent Text Reader

Abstract

To facilitate appropriate imaging of an abnormal portion in a tube.SOLUTION: An in-tube inspection device according to an embodiment includes: a detection unit which detects an abnormality in a tube that may appear in a main area being a diagnostic object of the abnormality in an image and detects an abnormality in the tube that may appear in a sub area that shows the depth side or front side of the tube relative to the main area in the image on the basis of the image of a camera that images the inside of the tube; and a camera operation support unit which generates information for guiding the operation the camera. The camera operation support unit guides the operation of moving the camera so that the abnormality of the tube that appears in the sub area appears in the main area when the abnormality of the tube is detected from the sub area.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] An embodiment of the present invention relates to an inside-pipe inspection device, an inside-pipe inspection system, an inside-pipe inspection method, and a program. [Background technology]

[0002] When sediment or rust accumulates inside pipes such as water pipes after many years of use, various abnormalities occur inside the pipes, including the accumulation and adhesion of foreign matter and deterioration and peeling of the inner surface of the pipe.

[0003] In a pipe inspection such as a water pipe, for example, the inside of the pipe is photographed in advance with a camera, and then a diagnosis is made based on the image captured by the camera after the inspection to determine whether there are any abnormalities in the pipe, the type of abnormality, and the level (or rank) of the abnormality. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6668106 [Patent Document 2] Patent No. 5764238 [Patent Document 3] JP 2019-138754 A [Patent Document 4] JP 2004-069711 A Summary of the Invention [Problem to be solved by the invention]

[0005] Many methods have been proposed for determining whether or not there is an abnormality in a pipe based on images captured by a camera. For example, a method is known in which the optimal image is synthesized and selected from the captured images, and then the image is used to determine whether or not there is an abnormality. However, if the abnormal part of the pipe is not captured properly (for example, if the abnormal part is captured in the distance or on the periphery of the image), the part becomes unclear, making it difficult to correctly perform a specific diagnosis, such as determining the level of the abnormality.

[0006] The problem that the invention aims to solve is to provide an inside-pipe inspection device, an inside-pipe inspection system, an inside-pipe inspection method, and a program that make it possible to easily take appropriate photographs of abnormal parts of a pipe. [Means for solving the problem]

[0007] The pipe inspection device of the embodiment is equipped with a detection unit that detects pipe abnormalities that may be captured in a main area in the image taken by a camera that captures the inside of the pipe, which is the subject of abnormality diagnosis, and detects pipe abnormalities that may be captured in a sub-area in the image that captures a part of the pipe further back or in front of the main area, and a camera operation support unit that generates information to guide the operation of the camera, and when a pipe abnormality is detected in the sub-area, the camera operation support unit guides the operation of moving the camera so that the pipe abnormality captured in the sub-area is captured in the main area. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an inside-pipe inspection device according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of a state in which a camera 3 used for the inside-pipe inspection by the inside-pipe inspection device is inserted into a pipe. [Diagram 3] FIG. 3 is a diagram showing the main area and the sub-area recognized by the detection unit 30 when the moving direction of the camera 4 is a forward direction (forward). [Figure 4]FIG. 4 is a diagram showing the main area and the sub-area recognized by the detection unit 30 when the moving direction of the camera 4 is a backward direction (rearward). [Diagram 5] FIG. 5 is a diagram showing an example of an image before the camera 4 moves forward. [Figure 6] FIG. 6 is a diagram showing an example of an image after the camera 4 moves forward. [Figure 7] FIG. 7 is a diagram showing an example of an image before the camera 4 moves backward. [Figure 8] FIG. 8 is a diagram showing an example of an image after the camera 4 moves backward. [Figure 9] FIG. 9 is a diagram showing an example of an image in which no tubal abnormality is present in the sub-areas A2 and A3. [Figure 10] FIG. 10 shows an example of an image when visibility is poor to a certain degree due to a large amount of floating particles inside the pipe. [Figure 11] FIG. 11 is a diagram showing an example of an image in which the center of a tube shown in the image is away from the center of the image by a certain distance or more. [Figure 12] FIG. 12 is a diagram showing an example of a screen display when no abnormality is present in the video. [Figure 13] FIG. 13 is a diagram showing an example of a screen display when an abnormality is present in the video. [Figure 14] FIG. 14 is a flowchart showing an example of a basic operation of the inside of pipe inspection device 1. [Figure 15] FIG. 15 is a flowchart showing an example of the operation of the camera movement support process performed mainly by the detection unit 30 and the camera operation support unit 50. [Figure 16] FIG. 16 is a flowchart showing an example of the operation of the camera direction adjustment support process performed mainly by the detection unit 30 and the camera operation support unit 50. [Figure 17] FIG. 17 is a diagram showing a modification of the configuration of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment will be described with reference to the drawings.

[0010] (composition) Fig. 1 shows an example of the configuration of an inside-pipe inspection device according to an embodiment. Fig. 2 shows an example of a state in which a camera used for inside-pipe inspection by the inside-pipe inspection device is inserted into a pipe. Note that some or all of the functions of the individual elements shown in Fig. 1 can be realized as a program to be executed by a computer (PC).

[0011] In this embodiment, the explanation will be given assuming that an inspection of the inside of a water pipe (boiling water pipe) is performed as an example, in particular an inspection without interruption to the water supply, when the pipe is filled with water. However, this embodiment is not limited to this example, and can also be applied to the inspection of the inside of various types of pipes, such as sewer pipes and piping.

[0012] The inside-pipe inspection device 1 shown in Fig. 1 is realized using a computer, and inspects the inside of a water pipe 3 installed at a site 2 based on images captured by a camera 4 that captures the inside of the pipe as shown in Fig. 2. At least the inside-pipe inspection device 1 and the camera 4 constitute an inside-pipe inspection system. In addition to including the inside-pipe inspection device 1 and the camera 4, the inside-pipe inspection system may further include a cable 6, which will be described later, and may further include sensors such as a gyro sensor and an acceleration sensor, which will be described later.

[0013] Camera 4 can be moved in the longitudinal direction of water pipe 3 (advancing or retreating in a predetermined direction) or temporarily stopped by external operation. For example, camera 4 can be advanced by pushing cable 6 in from the outside. Camera 4 can be retreated by pulling back cable 6. The direction in which camera 4 takes images is the direction in which camera 4 advances.

[0014] The camera 4 may be realized as, for example, a camera head equipped with an ITV camera. The ITV camera can digitize optical information obtained through a camera lens using an A / D converter and output the digitized information as video data.

[0015] In addition, the camera 4 may be waterproofed as a whole, since it moves inside the water pipe 3 at the site 2. The camera 4 may also be equipped with a function to turn on the light to brighten the inside of the pipe, and a rotation mechanism to keep the camera 4 vertical and horizontal at all times. A long cable 6 is connected to the camera 4, and the camera 4 is inserted into the water pipe 3 by pushing the cable 6 from a fire hydrant 7 or the like, and takes pictures of the inside of the water pipe 3. For taking pictures, the camera 4 may be inserted both upstream and downstream. To achieve this, the direction in which the camera 4 is inserted may be controlled by a jig placed between the fire hydrant 7 and the water pipe 3.

[0016] Furthermore, in order to obtain information on the orientation (direction of the optical axis) and movement of the camera 4, a sensor such as a gyro sensor or an acceleration sensor may be mounted on the camera 4 or an attachment of the camera 4 to detect the orientation and movement of the camera 4. In this case, any type of sensor may be used as long as it can measure the movement and position of the camera 4. The information on the orientation and movement of the camera 4 can be used when the camera position / movement detection unit 20 described later detects the movement and position of the camera 4.

[0017] The image from the camera 4 may be recorded on a recording medium by a recording device (not shown) outside the fire hydrant 7 via a cable 6. The image may be recorded in any format, and the format is not important. For example, the image may be recorded in an analog NTSC format, or in a digital uncompressed format or a digitally encoded format.

[0018] The image captured by the camera 4 is supplied to the inside-pipe inspection device 1. In addition, attribute information indicating attributes associated with the camera 4 is also supplied to the inside-pipe inspection device 1. The inside-pipe inspection device 1 takes in the image and attribute information recorded on a recording medium, and uses them to inspect the inside of the water pipe 3.

[0019] The inside of pipe inspection device 1 includes a video input unit 10, an attribute information input unit 11, a camera position / movement detection unit 20, a detection unit 30, an integrated judgment unit 40, a camera operation support unit 50, and an output processing unit 60. However, the integrated judgment unit 40 is an element that can be omitted as described below, and is not necessarily required.

[0020] The image input unit 10 inputs image data from a camera 4 that captures the inside of a water pipe 3 .

[0021] The attribute information input unit 11 inputs attribute information of the camera 4. The attribute information is supplied to the camera position / motion detection unit 20, the detection unit 30, and the integrated determination unit 40, and is used as necessary in the processing of each unit.

[0022] The camera position / movement detection unit 20 uses the video data input by the video input unit 10 and the attribute information input by the attribute information input unit 11 to detect the position and movement of the camera 4 within the pipe.

[0023] Based on the video data supplied from the video input unit 10 and the position and movement information of the camera 4 supplied from the camera position / motion detection unit 20, the detection unit 30 determines the presence or absence of an abnormality in the pipe that may be captured within a specified area of ​​the image of the camera 4, the type of abnormality, and the level (or rank) of the abnormality, and generates these results as an abnormality detection result.

[0024] Types of abnormalities include (1) rust, (2) deposits, (3) localized adhesion of foreign matter and deterioration of corrosion protection on the pipe surface, (4) film-like dirt adhering to the entire inside of the pipe, and (5) floating objects.

[0025] There are three levels of abnormality: S, A, B, C, and D. S means "no abnormality," and A, B, C, and D indicate that the level of abnormality increases from A to D, and the severity of the abnormality increases.

[0026] Further, the detection unit 30 includes, as various functions, a current location anomaly detection unit 31, a destination anomaly detection unit 32, and a visibility state detection unit 33. These will be described later.

[0027] The integrated determination unit 40 integrates the abnormality detection results generated by the detection units 30 to generate an integrated determination result indicating the level of abnormality within the pipe.

[0028] The camera operation support unit 50 generates information (hereinafter referred to as "camera operation support information") to guide the user in operating the camera 4, using the abnormality detection result generated by the detection unit 30 and the position and movement information of the camera 4 supplied from the camera position / movement detection unit 20 (supplied through the detection unit 30).

[0029] The output processing unit 60 outputs camera operation support information generated by the camera operation support unit 50, and outputs information including the abnormality detection result generated by the detection unit 30 and the integrated judgment result generated by the integrated judgment unit 40.

[0030] (Details of individual components) Each element constituting the inside of pipe inspection device 1 will be described in detail below.

[0031] Video input section 10 As described above, the video input unit 10 inputs video data from the camera 4 capturing images of the inside of the water pipe 3. The video data is used by the camera position / movement detection unit 20 to detect the position and movement of the camera 4 inside the pipe, and is also used by the detection unit 30 to determine the presence or absence and type of abnormality in the pipe that may be captured in the image from the camera 4, and to determine the visibility inside the pipe.

[0032] It is possible to configure the video input unit 10 to include the camera 4, but here the video input unit 10 does not include the camera 4, and the video data from the camera 4 is input from outside the video input unit 10.

[0033] ·Attribute information input section 11 As described above, the attribute information input unit 11 inputs attribute information related to the camera 4. The attribute information is supplied to the camera position / motion detection unit 20, the detection unit 30, and the integrated determination unit 40, and is used as necessary in the processing of each unit.

[0034] The attribute information may be input, for example, through the camera 4 or through an input device such as a keyboard or mouse. Also, information obtained from a sensor in the camera 4 may be used as the attribute information.

[0035] Although it is possible to inspect the inside of a pipe if the video input unit 10 is provided even without the attribute information input unit 11, in this embodiment, an attribute information input unit 11 is provided for inputting attribute information related to the camera in order to enable accurate diagnosis of pipe abnormalities.

[0036] The attribute information input by the attribute information input unit 11 includes, for example, information indicating the length of the cable 6 when the camera 4 is inserted into the water pipe 3, which becomes the position information of the camera 4 within the pipe. The position information of the camera 4 may be obtained by using GPS (Global Positioning System) technology.

[0037] The information indicating the cable length can be used in the camera position / motion detection unit 20, which will be described later, by superimposing the information on a predetermined position of the video data and recording it. If the video is recorded in a digital format, the information indicating the cable length may be recorded in synchronization with the video data, rather than being superimposed on the video data.

[0038] The function of the attribute information input unit 11 for inputting these pieces of attribute information may be mounted in a camera unit shared with the camera 4, or may be mounted in a separate unit different from the camera unit, or may be mounted in a separate unit connected to the end of the cable 6 to which the camera 4 is connected.

[0039] Camera position and motion detection section 20 As described above, the camera position / movement detection unit 20 detects the position and movement of the camera 4 within the pipe using the video data input by the video input unit 10 and the attribute information input by the attribute information input unit 11.

[0040] Here, it is assumed that the video data and attribute information are input to the camera position / motion detection unit 20 via the video input unit 10 and the attribute information input unit 11, and the camera position / motion detection unit 20 detects the position and motion of the camera 4 using the video data and attribute information. However, the present invention is not limited to this example, and the camera position / motion detection unit 20 may be mounted on the hardware of the camera 4 itself (or on an accessory of the camera 4). In this case, for example, a sensor such as a gyro sensor or an acceleration sensor may be mounted on the hardware of the camera 4, and the motion of the camera 4 may be detected using the sensor information, or similar detection may be performed by software processing by a CPU (Central Processing Unit).

[0041] A method for detecting the position and movement of the camera 4 using video data will be described below.

[0042] (1) Detecting the camera position First, detection of the position of camera 4 will be described. The simplest method for detecting the position of camera 4 is to read information indicating the cable length (i.e., position information of camera 4) from the attribute information input by attribute information input unit 11. If the video data is in digital format, detection can be realized by simply embedding information indicating the cable length in association with each frame (image) in the video data and reading that value.

[0043] Information indicating the cable length may be superimposed on the video data and recorded. In that case, the information may be read using optical character recognition (OCR). In this case, recognition is possible by finding an area in which characters are lined up horizontally from each image without specifying a character display area in the camera 4. For example, the digits 0 to 9 and the decimal point "·" may be registered as templates, and the image may be searched for by template matching to find an area in which characters matching any of the characters are lined up horizontally, and at the same time, a numerical value may be read from the template information of the number that matches the most.

[0044] For example, when recording 16.4(m) in the upper right area of ​​the screen as information indicating the cable length, the template of "1", "6", "·", and "4" has a high matching score in the upper right area of ​​the screen, and the value can be read as 16.4 because they are lined up left and right with almost the same vertical position. For character recognition in this case, for example, the technology of "O. Hori, "A video text extraction method for character recognition", Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318)" (hereinafter referred to as "Reference 1") may be used.

[0045] Also, by previously including information designating the model of the camera 4 in the attribute information, an area for displaying information indicating the cable length may be set according to the model.

[0046] In the case of a cable push-in type camera, the cable 6 bends when pushed and stretches when pulled back, so that the length of the cable 6 tends to be displayed differently even at the same point. Therefore, the accuracy of the position may be improved by comparing images of the round trip when pushed and pulled back, and correcting the value of the cable length at the time of pulling back as the official value for similar images. In this case, a method of comparing similar images may be used, or a more accurate position may be obtained by using a 3D information reconstruction technique using a monocular camera shown in "Seki, "3D Shape Reconstruction and Self-Localization from Moving Camera Images (SLAM) and High-Density 3D Shape Reconstruction", Information Processing Society of Japan Research Report Computer Vision and Image Media (CVIM), 2014-CVIM-190, 2014" (hereinafter referred to as "Reference 2").

[0047] Furthermore, if the type of water pipe 3 is known, the positions of each joint (seam) between the pipes can be known. Therefore, if the positions of each seam appear as concentric edges in the image with a certain or greater change in brightness, the position of the camera 4 may be found by counting the number of times the concentric edges are detected.

[0048] (2) Camera movement detection Next, we will explain how to detect the movement of the camera 4. A simple method is to find the optical flow for the entire image, and when the vanishing point is found from the flow direction, if it is found that many flow vectors have the vanishing point as their starting point or end point, it can be determined that the camera 4 is moving.

[0049] However, when photographing the inside of a water pipe 3, if there is any floating matter in the water pipe 3, the floating matter will flow toward the back of the pipe or from the back of the pipe to the front, and a vector in the vanishing point direction may be generated even if the camera 4 is stationary. Therefore, the presence or absence of movement of the camera 4 may be determined by detecting that when the camera 4 moves, the image changes during the exposure time, causing a blur (motion blur) and blurring the entire image. For example, the edge strength in the image may be calculated and the value may be accumulated to determine that the state where the edge is stationary is reached when the accumulated strength is greater than a certain threshold, and that the state where the edge is less than a certain threshold is determined to be moving due to blurring.

[0050] To reduce the effect of floating objects, the area of ​​pixels to be accumulated may be limited, for example, to the periphery of the tube (excluding the center). Also, edge strength may be calculated by accumulating the power of high-frequency components by applying FFT to the entire image, rather than to edges with adjacent pixels. For example, the frequency generated by floating objects may be calculated in advance, and then the frequency may be excluded, allowing accurate detection of the presence or absence of movement.

[0051] In addition, this method is limited to images saved in the analog signal format of NTSC (National Television Standards Committee), but in this case, the images are recorded alternately line by line in the vertical direction by the interlace method, so that striped noise called combing noise occurs when the camera 4 moves. This is because the shooting times of odd-numbered and even-numbered rows are different, so that striped luminance changes occur where changes in brightness occur. Therefore, for this striped portion, when Y(x,y) is the luminance value Y of the coordinates x,y, with a predetermined coefficient α, if there are a predetermined number of pixels that satisfy the following formula or more, it may be determined that combing noise has occurred and that the camera 4 is moving.

[0052] |Y(x,y)-Y(x,y-1)| > |(x,y)-y(x,y-2)|+α According to the above formula, normally the luminance changes smoothly in space, so the luminance difference between the two rows above is larger than the luminance difference between the row above, but when combing noise occurs, the luminance difference between the row above is larger than the luminance difference between the row above. This method makes use of this phenomenon.

[0053] If information from sensors such as a gyro sensor and an acceleration sensor mounted on the camera 4 is input from the attribute information input unit 11 to the camera position / movement detection unit 20, the movement of the camera 4 can be easily detected by reading the information. In this case, it is possible to accurately detect the movement of the camera 4 regardless of the underwater conditions.

[0054] In this way, it is possible to detect the current position of the camera 4 and whether or not the camera 4 is moving.

[0055] Detection unit 30 As described above, the detection unit 30 judges the presence or absence of an abnormality in a pipe that may be captured within a predetermined area of ​​the image of the camera 4, the type of abnormality, and the level of the abnormality based on the image data supplied from the image input unit 10 and the position and movement information of the camera 4 supplied from the camera position and movement detection unit 20, and generates the result of the judgment as an abnormality detection result. The abnormality detection result is generated, for example, on a frame (image) basis.

[0056] As described above, the detection unit 30 includes a current location anomaly detection unit 31, a destination anomaly detection unit 32, and a visibility condition detection unit 33.

[0057] The current location anomaly detection unit 31 detects the presence or absence of pipe anomalies and the type of anomalies that may be captured in a predetermined area (hereinafter referred to as the "main area") in the image captured by the camera 4 that is to be diagnosed for anomalies. The main area is an area for detecting anomalies that may exist near the current location of the camera 4. This area is the area in which the captured image is the clearest and where an accurate diagnosis of anomalies can be obtained. Therefore, for anomalies detected from the main area, the current location anomaly detection unit 31 further determines the level of the anomaly.

[0058] Destination anomaly detection unit 32 detects the presence or absence and type of abnormality in the pipe that may be captured in an area of ​​the image captured by camera 4 that is further in front or behind the main area of ​​the pipe (hereinafter referred to as the "secondary area"). The secondary area is an area for detecting abnormalities that may exist at the destination in front or behind camera 4. This area does not capture an image as clear as the main area, and it is not necessarily an area from which a correct diagnosis of an abnormality can be obtained. For this reason, no determination is made as to the level of abnormality for abnormalities detected in the secondary area.

[0059] Here, the relationship between the main region and the sub-region in the image of the camera 4 is shown typically in FIG. 3 and FIG.

[0060] 3 shows the main area and the sub-area recognized by the detection unit 30 when the moving direction of the camera 4 is a forward direction (forward). Specifically, when the moving direction of the camera 4 is a forward direction, the current location anomaly detection unit 31 recognizes the annular area A1 as the main area and detects anomalies, and the destination anomaly detection unit 32 recognizes the area A2 inside the area A1 as the sub-area and detects anomalies. The area A2 is an area that shows the inner side of the pipe than the area A1. In this case, no anomaly is detected for the area A3 outside the area A1.

[0061] 4 shows the main area and the sub-area recognized by the detection unit 30 when the camera 4 moves backward (rearward). Specifically, when the camera 4 moves backward, the current location anomaly detection unit 31 recognizes the annular area A1 as the main area and detects anomalies, and the destination anomaly detection unit 32 recognizes the area A3 outside the area A1 as the sub-area and detects anomalies. The area A3 is an area that captures the near side of the pipe compared to the area A1. In this case, no anomaly is detected for the area A2 inside the area A1.

[0062] In this embodiment, the shape of the region A1, which is the main region, is annular in shape to match the shape of the pipe. This allows any part of the inner surface of the pipe reflected in the region A1 to have a certain level of clarity or more, and an image optimal for detecting abnormalities in the pipe and judging the abnormality level can be obtained. In addition, once the annular region A1 is determined, the inner region is defined as region A2, and the outer region is defined as region A3, so that two types of sub-regions can be easily and appropriately specified. The visibility state detection unit 33 judges whether the inside of the pipe is in a state of poor visibility of a certain level or more, or judges whether the inside of the pipe is in a state of good visibility of a certain level or more. For each judgment criterion, a threshold based on the physical quantity such as the amount, concentration, and turbidity per unit volume of a specific substance (such as suspended matter) present in the pipe may be applied, or a threshold based on the hue shown by the image of the camera 4 may be applied. A specific substance such as suspended matter may be recognized from its shape or hue. In addition, the visibility state detection unit 33 may be configured to improve its detection accuracy by applying AI (Artificial Intelligence) technology. For example, an AI can be given a large amount of video data of the inside of a pipe through which suspended matter and other substances flow, as well as data such as judgment criteria, and allowed to learn from it, and the results indicated by the AI ​​can be used.

[0063] Integrated Judgment Section 40 The integrated determination unit 40 integrates the anomaly detection results generated by the current location anomaly detection unit 31 of the detection unit 30 to generate an integrated determination result indicating the level of anomaly in the pipe. The integration is performed on a frame-by-frame basis, a predetermined number of frames-by-predetermined section-by-section basis, or on a pipe-by-pipe basis (a section between pipe joints).

[0064] For example, the integrated judgment unit 40 detects each of the five types of abnormality described above, and then uses the mutual relationships between those results to output the final result. Note that there is no problem if the results are output as the final result without using the mutual relationships.

[0065] When obtaining the integrated anomaly determination result, for example, the calculation method (weighted addition method, etc.) for generating the integrated determination result may be changed (for example, merging or excluding) depending on the mutual relationship between the anomaly detection results for each type of anomaly. For example, it is possible to use only rust when determining rust, but use both rust and deposits when determining deposits. In this case, the integrated determination unit 40 may have the following functions.

[0066] (1) A function for generating an integrated judgment result by changing the calculation method for generating the integrated judgment result according to the mutual correlation between the anomaly detection results for each type of anomaly. As a method for calculating the integrated abnormality determination result, for example, Y(1) to Y(5) may be the final results of each of the five types of abnormalities, X1 to X5 may be the anomaly detection results calculated individually, and a to e may be the respective weighting coefficients, and the final result may be calculated by weighting each anomaly detection result by multiplying it by a predetermined coefficient as shown in the following formula.

[0067] Y(i) = a*X1 + b*X2 + c*X3 + d*X4 + e*X5 This formula can be applied to any unit, be it a frame unit, a section unit, or the entire unit.

[0068] By adjusting each coefficient in the formula, appropriate action can be taken when the individual dependencies are clear. For example, when determining the abnormal level of deposits, the result of ORing the abnormal detection results of rust and deposits can be determined as the abnormality detection result (this can also be achieved by using the coefficient of the above Y formula), and if a certain abnormality is found, it can be excluded from other abnormality detection results using the above formula.

[0069] Also, the detection result of a predetermined abnormality may be obtained first, and the result may be used to adjust the detection result of another abnormality. For example, the abnormality level of a predetermined abnormality may be adjusted depending on whether or not different types of abnormalities affect each other (for example, since sediments are easily confused with floating matter, the abnormality level may be adjusted depending on whether or not floating matter is present). In this case, the integrated judgment unit 40 may have the following functions.

[0070] (2) A function that adjusts the anomaly level of a given anomaly depending on whether or not different types of anomalies affect each other, and generates an integrated assessment result. For example, since floating objects occur across the entire area of ​​the image, the presence or absence of anomalies in the floating objects and the level of the anomalies may be determined first, and when there are a lot of floating objects, the criteria for the detection results of other anomalies may be corrected. When there are a lot of floating objects, it becomes difficult to see abnormalities in the image, so that an abnormality that actually exists may be missed, or conversely, it may be easier to determine an abnormality when there is no abnormality. It is also possible to lower or raise the level of the abnormality at a predetermined level, and the length of the area (section) in which the abnormality is determined may be changed depending on the amount of floating objects. For example, when there are a lot of floating objects, the influence of noise can be reduced by performing the level determination from the anomaly detection results obtained over a long range.

[0071] In addition, instead of being limited to five types of abnormality detection, one overall judgment result may be output as the overall judgment result for the entire pipe, regardless of the type of abnormality detection. This can be realized by calculating the worst value, average value, weighted addition, etc. of the five types of abnormality level judgment results.

[0072] Camera operation support section 50 As described above, the camera operation support unit 50 generates camera operation support information that guides the user in operating the camera 4, using the abnormality detection result generated by the detection unit 30 and the position and movement information of the camera 4 supplied from the camera position / movement detection unit 20 (supplied through the detection unit 30).

[0073] For example, when the camera 4 moves forward and an abnormality in the pipe is detected from the sub-area A2 shown in Fig. 3, the camera operation support unit 50 uses the camera operation support information to guide the user to move the camera 4 forward so that the abnormality in the pipe reflected in the sub-area A2 is reflected in the main area A1. Also, when the camera 4 moves backward and an abnormality in the pipe is detected from the sub-area A3 shown in Fig. 4, the camera operation support unit 50 uses the camera operation support information to guide the user to move the camera 4 backward so that the abnormality in the pipe reflected in the sub-area A3 is reflected in the main area A1.

[0074] Here, with reference to Figs. 5 and 6, a specific example of an image when the moving direction of the camera 4 is a forward direction will be shown.

[0075] Fig. 5 shows an example of an image before the camera 4 moves forward. Fig. 6 shows an example of an image after the camera 4 moves forward. Here, the positions of the main area A1 and the sub-areas A2 and A3 in the images of Fig. 5 and Fig. 6 will be confirmed by referring to Fig. 3 and Fig. 4 as appropriate.

[0076] In the example of FIG. 5, a rust portion R1 is captured in the main area A1 in the image, and a rust portion R1' is captured in the sub-area A2. The rust portion R1 in the main area A1 is located near the current location of the camera 4. On the other hand, the rust portion R1' in the sub-area A2 is located at a pipe joint (seam) C1 in the forward direction (forward) of the camera 4. The information indicating the cable length obtained from the attribute information described above is displayed in the upper right corner of the image. In this case, the camera operation support unit 50 detects the rust portion R1 on the pipe from the main area A1, and further determines the abnormality rank of the rust portion R1. The camera operation support unit 50 also detects the rust portion R1' on the pipe from the sub-area A2. However, since the image of the sub-area A2 is not clear, what is detected from this area may not actually be rust (it may be an abnormality other than rust). When the camera operation support unit 50 detects the chorus R1 from the sub-area A2, it guides the user to move the camera 4 forward a necessary distance and pause it so that the chorus R1' shown in the sub-area A2 is shown in the main area A1. The distance in this case may be estimated from various parameters included in the attribute information of the camera 4 and information such as the diameter of the pipe.

[0077] When the user operates the camera 4 according to the above instructions, as shown in FIG. 6, the chorus R1' that was captured in the sub-area A2 will be captured in the main area A1, which displays a clear image, and the camera operation support unit 50 will not only detect the chorus R1, but also determine the abnormality rank of the chorus R1.

[0078] Next, with reference to Figs. 7 and 8, a specific example of an image when the moving direction of the camera 4 is a backward direction will be shown.

[0079] Fig. 7 shows an example of an image before the camera 4 retreats. Fig. 8 shows an example of an image after the camera 4 retreats. Here, the positions of the main region A1 and the sub-regions A2 and A3 in the images of Fig. 7 and Fig. 8 will be confirmed by referring to Fig. 3 and Fig. 4 as appropriate.

[0080] In the example of Fig. 7, no abnormal part is captured in the main area A1 in the image, but a crack R2 is captured in the sub-area A3 in the image. In this case, the camera operation support unit 50 detects the crack R2 in the sub-area A3, and therefore guides the user to move the camera 4 back a necessary distance and temporarily stop the camera 4 so that the crack R2 captured in the sub-area A3 is captured in the main area A1. The distance in this case may be estimated from various parameters included in the attribute information of the camera 4 and information such as the diameter of the pipe.

[0081] When the user operates the camera 4 in accordance with the above instructions, as shown in Figure 8, the crack R2 that was captured in the sub-area A3 will be captured in the main area A1, which displays a clear image, so that the camera operation support unit 50 will not only accurately detect the crack R2, but will also accurately determine the abnormality rank of the crack R2.

[0082] In addition, the camera operation support unit 50 has a function of guiding the user to continue moving the camera 4 until the abnormality is detected when no abnormality in the pipe is detected from the sub-area A2 when the camera 4 is moving forward, or when no abnormality in the pipe is detected from the sub-area A3 when the camera 4 is moving backward.

[0083] Fig. 9 shows an example of an image in which no pipe abnormality is present in the sub-areas A2 and A3. When no pipe abnormality is present in the sub-areas A2 and A3 as in Fig. 9, the user may be guided to continue moving the camera 4 until the abnormality is detected (for example, the user may be prompted to move the camera 4 at the current speed or at a predetermined reference speed). In this way, unnecessary temporary stops of the camera 4 can be reduced, the inspection time can be shortened, and the inspection efficiency can be improved.

[0084] In addition, the camera operation support unit 50 has a function of guiding the user to increase (accelerate) the movement speed of the camera 4 when the state in which no abnormality in the pipe is detected from the sub-area A2 continues for a certain distance or for a certain period of time when the camera 4 is moving forward, or when the state in which no abnormality in the pipe is detected from the sub-area A3 continues for a certain distance or for a certain period of time when the camera 4 is moving backward.

[0085] In this way, if a state where no abnormality in the pipe is detected from the sub-area A2 or A3 continues for a certain distance or for a certain time, the user may be guided to increase the moving speed of the camera 4 (for example, the user may be prompted to move the camera 4 at a speed higher than the current speed or at a speed higher than the reference speed). In this way, the inspection time can be further shortened and the inspection efficiency can be further improved.

[0086] Furthermore, the camera operation support unit 50 has a function of guiding the user to operate the camera 4 continuously until the visibility inside the pipe is reduced to a certain level.

[0087] FIG. 10 shows an example of an image in which visibility is poor to a certain degree due to a large amount of floating matter inside the pipe. For example, if poor visibility is detected from sub-area A2 when the camera 4 is moving forward, or poor visibility is detected from sub-area A3 when the camera 4 is moving backward, it is no longer possible to detect an abnormality, so the user may be guided to continue moving the camera 4 until the condition is resolved (for example, by encouraging the user to move the camera 4 at the current speed or at a predetermined reference speed). In this way, unnecessary temporary stops of the camera 4 can be reduced, the inspection time can be shortened, and the inspection efficiency can be improved.

[0088] In addition, the camera operation support unit 50 has a function of guiding the user to reduce (slow down) the movement speed of the camera 4 until the repetition of conditions inside the pipe that are poorly visible to a certain degree or more and conditions that are good enough to see to a certain degree or more repeatedly occurs.

[0089] In this way, when the state inside the pipe repeatedly changes between a certain level of poor visibility and a certain level of good visibility, the user may be guided to operate to reduce the movement speed of the camera 4 until the repetition is resolved (for example, the user may be prompted to move the camera 4 at a speed slower than the current speed or at a speed slower than the above-mentioned reference speed). In this way, it is possible to prevent abnormalities in the pipe from being overlooked as much as possible.

[0090] In addition, the camera operation support unit 50 has a function of guiding the user to adjust the direction of the camera 4 (direction of the optical axis) so that it faces the center of the tube when the tip of the tube (the center position of the circular tube) shown in the image is away from the center of the image by a certain distance or more.

[0091] Fig. 11 shows an example of an image in which the center of the pipe shown in the image is at a certain distance from the center of the image. As in Fig. 11, when the center of the pipe shown in the image is located, for example, in the upper left corner, which is at a certain distance from the center of the image, the user may be guided to adjust the orientation of camera 4 so that it faces the center of the pipe (for example, the user may be prompted to adjust the orientation of camera 4 so that the center of the pipe shown in the image faces the center of the image). In this way, it is possible to prevent abnormalities in the pipe from being overlooked as much as possible, and stable abnormality detection results can be obtained.

[0092] In the image, there is a brightness gradient from the center of the tube to the periphery, and the brightness decreases (becomes darker) as the distance from the imaging unit of camera 4 to the inner surface of the tube increases. Therefore, the center position of the tube may be detected based on the change in brightness. Also, the center position of the tube may be detected based on the joint (seam) C1 of the tube. Furthermore, the accuracy of detecting the center position of the tube may be improved through machine learning using AI.

[0093] Furthermore, the orientation of the camera 4 may be adjusted by automatic control using AI technology. In that case, guidance on the operation for adjusting the orientation of the camera 4 becomes unnecessary.

[0094] Output processing unit 60 The output processing unit 60 has a function of outputting the camera operation support information generated by the camera operation support unit 50 in the form of either a screen display or sound, or both, through a display device (display) and / or sound output device (speaker). The display device and sound output device may be inside the inside pipe inspection device 1 or outside the inside pipe inspection device 1. In either case, the inside pipe inspection device 1 can detect abnormalities that may exist at the destination of the camera 4 in real time from the captured video, and can notify the user of camera operation support information according to the detection results through the display device and sound output device.

[0095] (display screen) 12 and 13, the screens displayed by the output processing unit 60 will be described.

[0096] Fig. 12 shows an example of the screen display when no abnormality is found in the image. Fig. 13 shows an example of the screen display when an abnormality is found in the image. To simplify the explanation, an example is shown here in which three types of abnormality are detected: rust, deposits, and cracks.

[0097] The output processing unit 60 can display and output various information through a screen 61 of the display device, and can output various information as sound through a speaker 62. In particular, the output processing unit 60 displays information on the screen 61 that can be confirmed by comparing the image input to the inside-pipe inspection device 1 with the abnormality detection result. Various display areas 100, 110, 120, 130, 140 are provided within the screen 61.

[0098] The display area 100 displays the image of the camera 4 supplied from the image input unit 10, and also displays the abnormal parts detected by the current location anomaly detection unit 31 and the destination anomaly detection unit 32 of the detection unit 30 in an easy-to-visually-recognizable representation format (framing, coloring, hatching, etc.) in the image. The information indicating the cable length described above is displayed in the upper right corner of the image.

[0099] The display area 110 is used to display the type of abnormality detected by the current location abnormality detection unit 31 from the main area A1 described above and the determined abnormality rank.

[0100] The display area 120 is used to display the types of abnormalities (presence or absence of various types of abnormalities) detected by the destination abnormality detection unit 32 from the sub-area A2 or A3 described above.

[0101] The display area 130 is used to display information indicating the current movement of the camera 4 (current camera movement information) supplied from the camera position / movement detection unit 20. Items include the camera state (whether the camera is stopped or moving), movement direction (whether the camera is set to move forward or backward), movement speed (speed at which the camera moves), location (position of the camera within the pipe), camera direction (direction of the camera's optical axis), pan, tilt, zoom (setting information for the camera's PTZ function), etc. However, these items are merely examples and are not limited to these examples.

[0102] The display area 140 is used to display the camera support information described above. Items include camera movement, movement speed, camera direction, pan, tilt, zoom, and description. However, these items are merely examples and are not limited to these examples.

[0103] In the screen display example of FIG. 12, no abnormality exists in the image in the display area 100. In this case, the abnormality ranks of rust, deposits, and cracks are "S" in the display area 110, indicating that none of the abnormalities exist. Also, in the display area 120, rust, deposits, and cracks are all displayed as "none", indicating that none of the abnormalities exist. In the display area 130, the camera state is displayed as "stopped", the moving direction is "forward" (forward direction), the moving speed is "10 cm / sec", and the location is "16.4 m". Although the camera direction is not shown here, it may be expressed by, for example, the degree to which the optical axis of the camera is shifted horizontally and vertically from the reference direction, as an angle or the like. Also, pan, tilt, and zoom are displayed as "10 degrees", "3 degrees", and "none", respectively.

[0104] In the display area 140, the camera movement, movement speed, camera direction, pan, tilt, and zoom are displayed as "maintain the current state." In the explanation display area, for example, "There is no particular operation to be changed" may be displayed.

[0105] On the other hand, in the screen display example of Fig. 13, an abnormality exists in the image of the display area 100. Specifically, the current location anomaly detection unit 31 detects chorus R1 from the above-mentioned main area A1, and displays the abnormal part surrounded by a frame 101 so that it is easy to recognize. Also, the destination anomaly detection unit 32 detects chorus R1' from the above-mentioned sub-area A2, and displays the abnormal part surrounded by a frame 102 so that it is easy to recognize. The colors and shapes of the frames 101 and 102 may be appropriately changed so that they can be easily distinguished from each other.

[0106] In the display area 110, the abnormality ranks of deposits and cracks are displayed as "S", but the abnormality rank of rust is displayed as "B". In other words, rust has been detected by the current location anomaly detection unit 31, and the result that the abnormality rank of the rust has been determined to be B is displayed. In addition, in the display area 120, rust has been detected by the destination anomaly detection unit 32, so rust is displayed as "present". The display area 130 is similar to the screen display example of FIG. 12.

[0107] In this manner, in the example screen display of Figure 13, since the destination abnormality detection unit 32 has detected the chorus R1' from the aforementioned sub-area A2, the camera operation support unit 50 guides the user to move the camera 4 so that the chorus R1' of the pipe reflected in the sub-area A2 is reflected in the main area A1.

[0108] In this example, since the current moving direction of the camera 4 is set to "forward", the camera operation support unit 50 guides the user to "move forward" the camera 4 by a predetermined distance and then "pause". In this case, in the display area 140, "move forward" is displayed first as the camera movement, and then "pause". The moving speed, camera direction, pan, tilt, and zoom are displayed as "maintain current status". In the display area for the explanation, for example, it may be displayed that "move the camera forward at the current speed until the cable length is 17.4 m, and then pause", or it may be displayed that "move the camera forward at the current speed and pause just before the joint". In addition, such an explanation may be output by voice.

[0109] Depending on the situation, the movement speed, camera direction, pan, tilt, and zoom may be displayed as arbitrary values ​​for change, rather than "maintaining the status quo."

[0110] For example, if, as described above, no abnormality in the pipe is detected from sub-area A2 or A3 for a certain distance or for a certain period of time, a display may be displayed urging the user to increase (accelerate) the movement speed of camera 4, or if there are repeated alternations between a certain level of poor visibility inside the pipe and a certain level of good visibility inside the pipe, a display may be displayed urging the user to decrease (slow down) the movement speed of camera 4.

[0111] In addition, if it is necessary to change the pan, tilt, zoom, etc. values ​​in order to accurately capture the abnormal part, such as when the size of the detected abnormality is larger than a specified value, or smaller than a specified value, or when the abnormality spreads over a wide area, a display may be displayed prompting the user to change those values.

[0112] In addition, the explanation display area may display specific operations for camera 4, such as "Please make sure the joint fills the entire screen" or "Please make sure the rust in the center of the screen is the largest."

[0113] (Basic operation) Next, an example of the basic operation of the inside of the pipe inspection device 1 will be described with reference to the flowchart in Fig. 14. Note that the individual processes shown in Fig. 14 are not necessarily performed in the order of the step numbers, and can be changed as appropriate. For example, the order of steps S1 and S2 may be interchanged, or steps S1 and S2 may be processed simultaneously.

[0114] First, the video input unit 10 inputs video data from the camera 4 capturing images inside the water pipe 3 (step S1). In addition, the attribute information input unit 11 inputs attribute information indicating attributes associated with the camera 4 (step S2).

[0115] Next, the camera position / movement detection unit 20 detects the position or movement of the camera 4 within the pipe using the video data input by the video input unit 10 and the attribute information input by the attribute information input unit 11 (step S3).

[0116] Next, based on the video data supplied from the video input unit 10 and the position and movement information of the camera 4 supplied from the camera position / motion detection unit 20, the detection unit 30 determines whether or not there is an abnormality in the pipe that may be captured within a specified area of ​​the image of the camera 4, the type of abnormality, and the level (or rank) of the abnormality, and generates these results as an abnormality detection result (step S4).

[0117] Next, the camera operation support unit 50 generates camera operation support information that guides the user in operating the camera 4, using the abnormality detection result generated by the detection unit 30 and the position and movement information of the camera 4 supplied from the camera position / movement detection unit 20 (supplied through the detection unit 30) (step S5).

[0118] Next, the integrated determination unit 40 integrates the abnormality detection results generated by the detection units 30 to generate an integrated determination result indicating the level of abnormality in the pipe (step S6).

[0119] The output processing unit 60 outputs camera operation support information generated by the camera operation support unit 50, and outputs information including the abnormality detection result generated by the detection unit 30 and the integrated judgment result generated by the integrated judgment unit 40 (step S7).

[0120] (Camera movement support processing operation) Next, an example of the operation of the camera movement support process (processing for guiding the user to move the camera 4) performed mainly by the detection unit 30 and the camera operation support unit 50 will be described with reference to the flowchart in Fig. 15. Note that the individual processes shown in Fig. 15 are not necessarily performed in the order of the step numbers, and can be changed as appropriate. For example, the order of the processes of steps S12 and S13 may be interchanged, or they may be processed simultaneously.

[0121] First, the detection unit 30 reads the image captured by the camera 4 (step S11) and detects the tip of the pipe (i.e., the center position of the annular pipe) from the image (step S12). The detection unit 30 also detects the movement of the camera 4 (step S13).

[0122] In the detection unit 30, the current location anomaly detection unit 31 detects anomalies in the main area A1 (step S14). If an anomaly is detected in the main area A1, the current location anomaly detection unit 31 also determines the anomaly rank. In addition, the destination anomaly detection unit 32 detects anomalies in the sub-areas A2 or A3 (step S15) and determines whether an anomaly has been detected (step S16).

[0123] If an abnormality is detected in the sub-area A2 or A3 (Yes in step S16), the camera operation support unit 50 outputs camera operation support information to enable the abnormal part to be captured clearly (step S17). That is, when a pipe abnormality is detected in the sub-area A2 or A3, the camera operation support unit 50 uses the camera operation support information to guide the user to an operation of moving the camera 4 so that the pipe abnormality reflected in the sub-area is reflected in the main area A1. The user operates the camera 4 according to the above guidance (step S19). As a result, the abnormality reflected in the sub-area A2 or A3 is reflected in the main area A1 which displays a clear image, so that the camera operation support unit 50 not only accurately detects the abnormality, but also accurately determines the abnormality rank of the abnormality.

[0124] On the other hand, if no abnormality is detected from the sub-area A2 or A3 (No in step S16), the camera operation support unit 50 outputs camera operation support information for emphasizing the efficiency of the pipe inspection (step S18). For example, if no abnormality in the pipe is detected because no abnormality exists in the pipe, the user is guided to continue moving the camera 4 until the abnormality is detected. Also, for example, if no abnormality in the pipe is detected because the inside of the pipe is in a state of poor visibility to a certain degree or more, it is no longer possible to detect the abnormality, so the user is guided to continue moving the camera 4 until the state is resolved. The user operates the camera 4 according to the above guidance (step S19). This reduces unnecessary temporary stops of the camera 4, shortens the inspection time, and improves the inspection efficiency. If the inspection inside the pipe is not completed after the processing of step S19, the processing from step S1 is repeated.

[0125] (Camera orientation adjustment support processing operation) Next, an example of the operation of the camera direction adjustment support process (processing for guiding the user to adjust the direction of the camera 4) performed mainly by the detection unit 30 and the camera operation support unit 50 will be described with reference to the flowchart in FIG.

[0126] First, the detection unit 30 reads the image captured by the camera 4 (step S21) and detects the end of the pipe (i.e., the center position of the circular pipe) from the image (step S22). Next, the detection unit 30 calculates the relative distance between the end of the pipe and the center of the image (step S23) and determines whether the relative distance is within a predetermined normal range (step S24).

[0127] If the relative distance is not within a predetermined normal range (No in step S24), the detection unit 30 or the camera operation support unit 50 calculates the relative distance in the lateral direction (horizontal direction) and the relative distance in the vertical direction (step S25), and outputs support information that guides the user to adjust the orientation of the camera 4 using the calculated relative distances (step S26). The user adjusts the orientation of the camera 4 according to the above guidance (step S27). After this, the process from step S1 is repeated.

[0128] On the other hand, in step S24, if the relative distance is within the predetermined normal range (Yes in step S24), there is no need to adjust the orientation of the camera 4, and the process ends as it is.

[0129] (Modification) Next, a modified example of the configuration in Fig. 1 will be described with reference to Fig. 17. The following description will focus on the differences from the configuration in Fig. 1.

[0130] FIG. 17 shows a modification of the configuration of FIG.

[0131] In the configuration of Fig. 17, the integrated judgment unit 40 is omitted from the configuration of Fig. 1. Therefore, the anomaly detection result that was supplied from the detection unit 30 to the integrated judgment unit 40 is supplied directly to the output processing unit 60 without passing through the integrated judgment unit 40.

[0132] Therefore, the output processing unit 60 does not output the integrated judgment result, but instead outputs the abnormality detection result generated by the detection unit 30 and / or outputs camera operation support information generated by the camera operation support unit 50.

[0133] The other configurations are the same as those in FIG.

[0134] As for the operation, the process in step S6 in FIG. 14 is omitted.

[0135] According to this modification, the functional configuration of the inside of the pipe inspection device 1 can be simplified, and the integrated judgment process can be omitted, thereby reducing the processing load.

[0136] (summary) As described above in detail, according to the embodiment, it is possible to easily perform appropriate imaging of abnormal parts of a pipe. In particular, since the camera operation support information can guide the user on how to operate the camera to appropriately detect abnormalities in the pipe, it is possible to avoid a situation in which the abnormal part is imaged in a blurred state, and it is possible to avoid difficulties in diagnosing the abnormality. In addition, since the abnormality can be accurately detected from a clear image, the abnormality rank of the abnormality can also be accurately determined, and it is possible to easily perform a correct diagnosis of the abnormality.

[0137] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0138] 1...pipe inspection device, 2...site, 3...water pipe, 4...camera, 10...video input unit, 11...attribute information input unit, 12...setting unit, 20...camera position / movement detection unit, 30...detection unit, 31...current location abnormality detection unit, 32...destination abnormality detection unit, 33...visibility condition detection unit, 40...integrated judgment unit, 50...camera operation support unit, 60...output processing unit, 61...screen, 62...speaker

Claims

1. A detection unit detects abnormalities in the pipe that may appear in a main area of ​​the image captured by a camera that captures the inside of the pipe, the main area being a diagnostic target for abnormalities, and detects abnormalities in the pipe that may appear in a sub-area that captures a portion of the pipe that is further inward or closer than the main area in the image; a camera operation support unit that generates information for guiding the operation of the camera; Equipped with When an abnormality in a pipe is detected from the sub-area, the camera operation support unit guides an operation of moving the camera so that the abnormality in the pipe reflected in the sub-area is reflected in the main area. Pipe inspection equipment.

2. An output processing unit that outputs the information in the form of either a screen display or sound, or both. The pipe inspection device according to claim 1 .

3. The main region is a region having a circular ring shape, The sub-region is an area inside or outside the main region. The pipe inspection device according to claim 1 .

4. The detection unit is When the camera moves forward, the sub-area is recognized as being inside the main area and the detection is performed; When the camera is moving backward, the sub-area is recognized as being outside the main area and the detection is performed. The pipe inspection device according to claim 3.

5. The camera operation support unit includes: when an abnormality in the pipe is detected from the sub-area, a position of the abnormality in the pipe is determined, a moving distance of the camera is determined from the position of the abnormality and the position of the camera, and an operation of moving and pausing the camera is guided based on the moving distance. The pipe inspection device according to any one of claims 1 to 4.

6. The camera operation support unit includes: If no abnormality in the pipe is detected from the sub-area, an operation of continuously moving the camera is guided until the abnormality is detected. The pipe inspection device according to claim 5.

7. The camera operation support unit includes: When a state where no abnormality in the pipe is detected from the sub-area continues for a certain distance or for a certain period of time, an operation to increase the moving speed of the camera is guided. The pipe inspection device according to claim 6.

8. The camera operation support unit includes: When visibility inside the pipe is poor to a certain level, the system guides the user to continue moving the camera until the poor visibility is resolved. The pipe inspection device according to claim 5.

9. The camera operation support unit includes: When a state where visibility is poor or above a certain level inside the pipe is repeatedly changed to a state where visibility is good or above a certain level, a guidance is given to an operation to reduce the movement speed of the camera until the repetition is eliminated. The pipe inspection device according to claim 5.

10. The camera operation support unit includes: When the center position of the tube shown in the image is away from the center of the image by a certain amount or more, an operation to adjust the direction of the camera is guided. The pipe inspection device according to claim 1 .

11. The output processing unit outputs, as the information, at least information indicating whether the camera is moving forward, backward, or temporarily stopped, and the speed at which the camera is moving, in the form of either the screen display or sound, or both. The pipe inspection device according to claim 2.

12. The pipe inspection device according to claim 1 , The camera; An in-pipe inspection system including:

13. Based on an image captured by a camera photographing the inside of a pipe, a pipe abnormality that may appear in a main area in the image that is to be diagnosed as an abnormality is detected, and a pipe abnormality that may appear in a sub-area that shows the inner side or the front side of the pipe relative to the main area in the image is detected. generating information that guides an operation of moving the camera so that the pipe abnormality reflected in the sub-area is reflected in the main area when the pipe abnormality is detected from the sub-area; An in-pipe inspection method comprising:

14. On the computer, A function for detecting abnormalities in a pipe that may appear in a main area of ​​the image taken by a camera that captures the inside of the pipe, which is a diagnosis target for abnormalities, and for detecting abnormalities in a sub-area that shows the inner side or the front side of the pipe relative to the main area of ​​the image, based on the image taken by the camera that captures the inside of the pipe; a function of generating information that guides an operation of moving the camera when an abnormality in a pipe is detected from the sub-area so that the abnormality in the pipe reflected in the sub-area is reflected in the main area; A program to achieve this.

Citation Information

Patent Citations

  • Color resolution system in case of printing

    JP1982064238A

  • Conduit investigation system

    JP2004069711A

  • Conduit line inspection information display device and conduit line inspection information display method

    JP2019138754A

  • Pipe inspection method and flexible joints

    JP6668106B2